PageOne

SMART PRO LATEST PROJECT IDEAS

SmartProjects - An idea to Product .

MATLAB BASED PROJECT IDEAS


SMM1 - Swarm Robotics
SMM2 - Automated Vehicle Parking (BlueSoleil software-Android)
SMM3 - Brain Tumor Detection And Segmentation
SMM4 - An Efficient Dynamic Image Compression Algorithm based on Block Optimization, Byte Compression and Run-Length Encoding along Y-axis.
SMM5 - Canny Edge Detection
SMM6 - Crowd Congestion
SMM7 - Drowsiness Detection For Car Assisted Driver System Using Image Processing Analysis – Interfacing With Hardware
SMM8 - Electrical Meter Reading
SMM9 - Eye Blink Device Control
SMM10 - Face Recognition
SMM11 - Fake Currency Detection Using Image Processing
SMM12 - Iris Recognition
SMM13 - LED Permanent Emergency Lighting System Based on a Single Magnetic Component (IEEE-2009)
SMM14 - Pedestrian & Cars Detection
SMM16 - Smoke Detection in Stationary Video Using Wavelets
SMM17 - Traffic Light Control System
SMM18 - Traffic Sign Recognition by Color Filtering and Particle Swarm optimization
SMM19 - Vehicle License Plate
SMM20 - Data Hiding Scheme For Medical Images Using Lossless Code For Mobile HIMS
SMM21 - Satellite Image Resolution Enhancement Using DWT
SMM22 - Combined DWT-DCT Digital Image Watermarking
SMM23 - Speeds Detection Camera System Using Image Processing Techniques On Video Streams
SMM24 - A Visual Cryptographic Technique To Secure Image Shares
SMM25 - A Matlab Based Face Recognition System Using Image Processing
SMM26 - Classification Of Diabetic Stages Using Image Processing And Ann
SMM27 - Image Fusion
SMM28 - Steganography
SMM29 - Speed Detection Camera System Using Image Processing On Video Streams
SMM30 - Steganography Using Least Significant Bit Algorithm
SMM31 - Bimodal Biometric Person Authentication System Using Speech And Signature Features
SMM32 - Object Recognition Using Sift Algorithm
SMM33 - Two-Stage Image De-noising By Principal Component Analysis With Local Pixel Grouping
SMM34 - Ohta Based Covariance Technique For Tracking Object In Video Scene
SMM35 - Performance Analysis Of Gender Clustering And Classification Algorithms
SMM36 - Image/Video Encryption And Decryption
SMM37 - Image Mosaic Algorithm Based On Sift
SMM38 - Video Mosaic
SMM39 - Virtual Calculator
SMM40 - A Novel Anti Phishing Framework Based On Visual Cryptography
SMM41 - Visual Cryptography Authentication For Data Matrix Codes
SMM42 - Virtual Mouse Using A Webcam
SMM43 - Voice Activated Calculator
SMM44 - Speech Recognition
SMM45 - Facial Expression Recognition
SMM46 - View-Invariant Action Recognition Based On Artificial Neural Networks
SMM47 - Efficient Defect Detection Algorithm For Gray Level Digital Images Using Gabor Wavelet Filter And Gaussian Filter
SMM48 - Hand Vein Biometric Verification Prototype
SMM49 - Data Hiding In Medical Images
SMM51 - Satellite Image Resolution Enhancement
SMM52 - Color Detection In Real Time Video/Image
SMM53 - Basic Image Processing Functionalities

Abstract

Swarm Robotics
By this project we are going to control the direction (forward, backward, left and right) and ON/OFF of robot by Matlab. Swarm robotics is a new approach to the coordination of multi robot systems which consist of large numbers of mostly simple physical robots. It is supposed that a desired collective behavior emerges from the interactions between the robots and interactions of robots with the environment. This approach emerged on the field of artificial swarm intelligence, as well as the biological studies of insects, ants and other fields in nature, where swarm behavior occurs.

Back to Top

Abstract

Automated Vehicle Parking (BlueSoleil software-Android)
Automated car parking system could be used for residential buildings, hotels, offices, shopping center and show rooms, universities, government buildings, airports, hospitals, and stadium. The advantages of automated car parking are efficient usage of spaces; decreasing the land space and increasing the number of parked vehicles, saving time by taking and delivering car in a few seconds; providing security and safety for the car from theft and damages while parking. This project based on the BlueSoleil software-Android.

Back to Top

Abstract

Brain Tumor Detection And Segmentation
Magnetic resonance (MR) images are a very useful tool to detect the tumor growth in brain but precise brain image segmentation is a difficult and time consuming process. In this project we propose a method for automatic brain tumor diagnostic system from MR images. The system consists of three stages to detect and segment a brain tumor. In the first stage, MR image of brain is acquired and preprocessing is done to remove the noise and to sharpen the image. In the second stage, global threshold segmentation is done on the sharpened image to segment the brain tumor. In the third stage, the segmented image is post processed by morphological operations and tumor masking in order to remove the false segmented pixels. Results and experiments show that our propose technique accurately identifies and segments the brain tumor in MR images. "

Back to Top

Abstract

An Efficient Dynamic Image Compression Algorithm based on Block Optimization, Byte Compression and Run-Length Encoding along Y-axis.
In this project, we have proposed a modified version of image compression/decompression algorithm using block optimization and byte compression method (BOBC). After BOBC, it is followed by run-length encoding and its block is optimized by varying block size. The proposed algorithm is very simple in implementation, fast in encoding time. Experimental results show that compression ratio of this algorithm is better than the previous BOBC algorithm and JPEG compression techniques. Image quality (PSNR) is almost the same or better as compared to that of the above mentioned compression techniques.

Back to Top

Abstract

Canny Edge Detection
Canny edge detector is a complex but accurate detector as compared to Marr-Hilderth detector. And it is based on these 3 following objectives: • Low Error Rate: Its says that all edges should be found and these detected edges should be as much close to true edges as possible • Edge points should be well localized: It states that the edges located should be as close to true edges as possible. In other words, the distance between a point detected or marked as an edge by canny detector and the center of the true edge should be minimum. • Single Edge Point Response: The detector must output one edge point for each true edge point.

Back to Top

Abstract

Crowd Congestion
Mass events are always and have been popular in all over the world. Such mass events are sports events, music festivals and concerts etc. In such mass events numbers of visitors are more and safety measures are more and more important. In such mass gatherings the density of the mass becomes high. Due to the high density the crowd members lose their individual control and they move involuntarily. People moving involuntarily induce sudden movement of people nearby. These crowd turbulences propagate through the crowd causing people to stumble and fall down. Crowd turbulence is an unanticipated and unintended irregular motion of individuals into different directions due to strong and rapidly changing forces in crowds of extreme density [2]. As a result, most people die by suffocating due to dangerous pressure of up to 4500 N/m on their chests. This system helps to prevent such crowd disasters.It is the system for the detection and early warning of uncontrolled situations during mass events.

Back to Top

Abstract

Drowsiness Detection For Car Assisted Driver System Using Image Processing Analysis – Interfacing With Hardware
The purpose of this study is to detect drowsiness in drivers to prevent accidents and to improve safety on the highways. A method for detecting drowsiness/sleepiness in drivers is developed by using a camera that point directly towards the driver’s face and capture for the video. Once the video is captured, monitoring the face region and eyes in order to detect drowsy/fatigue. The system able to monitoring eyes and determines whether the eyes are in an open position or closed state. In such a case when drowsy is detected, a warning signal is issued to alert the driver. It can determine a time proportion of eye closure as the proportion of a time interval that the eye is in the closed position. If the driver’s eyes are closed cumulatively more than a standard value, the system draws the conclusion that the driver is falling asleep, and then it will activate an alarm sound to alert the driver.

Back to Top

Abstract

Electrical Meter Reading
This project presents the application of multiple linear regressions (MLR) to estimate the electrical energy consumption in case of the irregularity in the automatic meter reading (AMR) system. This event occurs in a delivery metering system such as problems from setting and connecting meter with the wrong electrical system, broken metering accessories, etc.

Back to Top

Abstract

Eye Blink Device Control

Back to Top

Abstract

Face Recognition
Image recognition is the process of identifying and detecting an object or a feature in a digital image or video. This concept is used in many applications like systems for factory automation, toll booth monitoring, and security surveillance. Face recognition is the algorithm for image recognition.

Back to Top

Abstract

Fake Currency Detection Using Image Processing
Counterfeit money is imitation currency produced without the legal sanction of the state or government. Producing or using this fake money is a form of fraud or forgery. Counterfeiting is as old as money itself, and is sufficiently prevalent throughout history that it has been called "the world's second oldest profession. This has led to the increase of corruption in our country hindering country’s growth. Common man became a scapegoat for the fake currency circulation, let us suppose that a common man went o a bank to deposit money in bank but only to see that some of the notes are fake, in this case he has to take the blame. Counterfeiting, of whatever kind, may be that has been occurring ever since humans grasped the concept of valuable items, and there has been an ongoing race between certifier like (banks, for example) and counterfeiter ever since. Some of the effects that counterfeit money has on society include a reduction in the value of real money; and inflation due to more money getting circulated in the society or economy which in turn dampen our economy and growth - an unauthorized artificial increase in the money supply; a decrease in the acceptability of project money; and loses. And this Some of the methods to detect fake currency are water marking, optically variable ink, security thread, latent image, techniques like counterfeit detection pen and using MATLAB.

Back to Top

Abstract

Iris Recognition
Iris recognition with Matlab is nowadays getting popular because of the efficient programming language. Since Matlab is a fourth-generation language that allows developers to create interfaces for graphics and optical scanners as well, iris recognition with Matlab becomes easier and accurate without any complexities. Many developers now prefer iris recognition with Matlab for testing purposes, before the final iris recognition system is released in the market. The reason behind testing the iris recognition with Matlab is that the final outputs are real-time, hence allow developers to assess the reliability of this latest and more advanced biometric recognition system called iris recognition with Matlab. A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Iris recognition is regarded as the most reliable and accurate biometric identification system available. Most commercial iris recognition systems use patented algorithms developed by Daugman, and these algorithms are able to produce perfect recognition rates. However, published results have usually been produced under favorable conditions, and there have been no independent trials of the technology.

Back to Top

Abstract

LED Permanent Emergency Lighting System Based on a Single Magnetic Component (IEEE-2009)
The use of high-efficiency LEDs in low-power lighting applications is growing continuously due to new advances in LED features. The lifetime of a low-power fluorescent lamp is around 5000 h. This implies short lamp-replacement times and high maintenance costs. The use of high-efficiency LEDs reduces drastically the maintenance costs due to the long lifetime (>50 000 h). One of the applications where using LED is very interesting is permanent emergency light systems. Generally, these circuits are based on a two-stage design, using two magnetic cores. This project presents offline power LED driver and battery charger integrated in one magnetic core topology. Besides, the converter allows driving the LEDs in case of a line failure and it complies with the IEC 61000-3-2 Class C Standard.

Back to Top

Abstract

Pedestrian & Cars Detection
This project describes a target detection system on road environments based on Support Vector Machine (SVM) and monocular vision. The final goal is to provide pedestrian-to-car and car-to-car time gap. The challenge is to use a single camera as input, in order to achieve a low cost final system that meets the requirements needed to undertake serial production in automotive industry. The basic feature of the detected objects are first located in the image using vision and then combined with a SVM based classifier. An intelligent learning approach is proposed in order to better deal with objects variability, illumination conditions, partial occlusions and rotations.

Back to Top

Abstracts

Smoke Detection in Stationary Video Using Wavelets
Early warning systems are critical in providing emergency response in the event of unexpected hazards. Cheap cameras and improvements in memory and computing power have enabled the design of fire detectors using video surveillance systems. This is critical in scenarios where traditional smoke detectors cannot be installed. In such scenarios, it has been observed that the smoke is visible well before flames can be sighted. A novel method for smoke characterization using wavelets and support vector machines is proposed in this project. Forest fire, tunnel fire and news channel videos have been used for testing the proposed method. The results are impressive with limited false alarms. The proposed algorithm is evaluated for its characterization properties using motion segmented images from a commercial surveillance system with good results.

Back to Top

Abstract

Traffic Light Control System
With the developing of urbanization, as well as the significant increasing of automobile in city, the phenomenon of traffic jam has occurred frequently. As a result, municipal administration has widened the city's trunk line, the traffic management bureau has increased traffic lights at crossroads, but we could not see much great change in city traffic condition. These measures, for instance, how to make use of existing urban roads more effectively, how to regulate the time of the traffic lights, and how to use the minimum investment to ease the city's jam, possess realistic significance. The primary goal of this project based on the optimization of phase and time of traffic lights is to achieve the optimal research on both sides not only “Green light wave band” but also “Inverse green light wave band”, and simulates optimization of going through inverse green light wave band by using the software of MATLAB according to the constraint discriminate of bi-directional green light wave band what we calculated in the project.

Back to Top

Abstract

Traffic Sign Recognition by Color Filtering and Particle Swarm optimization
In this project a comprehensive approach to traffic sign detection and recognition is proposed. An RGB roadside image is acquired. Color filtering and segmentation is used to detect the boundary of traffic sign in binary mode. At the feature extraction stage, the RGB traffic sign region is cropped. The image is resized to 100x100 pixels. Finally, particle swarm optimization is used to identify the traffic sign. Experimental results show that our system can give a high recognition rate for all types of traffic signs used in Thailand: namely, prohibitory signs (red or blue), general warning signs (yellow) and construction are a warning signs (amber).

Back to Top

Abstract

Vehicle License Plate
At present, the traffic engineering and automation have developed, and the vehicle license plate recognition technology need get a corresponding improvement also. In case of identifying a car license picture, the principle of automatic license plate recognition is illustrated in this project, and the processing is described in detail which includes the preprocessing, the edge extraction, the license plate location, the character segmentation, the character recognition. The program implementing recognition is edited by Matlab. The example result shows that the recognition method is feasible, and it can be put into practice.

Back to Top

Abstract

Data Hiding Scheme For Medical Images Using Lossless Code For Mobile HIMS
Information Technology advances have bought forth new challenges in healthcare information management, due to the vast amount of medical data that needs to efficiently stored, retrieved and distributed, and the increased security threats that explicitly have to be addressed. In particular, embedding patient information into a medical image through data hiding could improve the level of security and confidentiality that is essential for diffusion of medical information system. Such security provides integrity of medical images and corresponding documentations, along with protection of confidential information. The scheme imperceptibly embeds in medical images patient’s personal information like name and unique identification number. Our objective was to have a simple model which uses minimal resources and hence a strong candidate for use in mobile healthcare applications where the resources of memory, computation and connectivity are extremely limited. To meet these requirements, this project presents a powerful yet simple lossless scheme for the medical image processing. The method is distortion-tolerant in application. The original image can be recovered with almost no distortion. The scheme has been implemented for images of various sizes and a comparative study is presented.

Back to Top

Abstract

Satellite Image Resolution Enhancement Using DWT
Satellite images are being used in many fields of research. One of the major issues of these types of images is their resolution. In this project, we propose a new satellite image resolution enhancement technique based on the interpolation of the high-frequency sub bands obtained by Discrete Wavelet Transform (DWT) and the input image. The proposed resolution enhancement technique uses DWT to decompose the input image into different sub bands. Then, the high-frequency sub band images and the input low-resolution image have been interpolated, followed by combining all these images to generate a new resolution-enhanced image by using inverse DWT. In order to achieve a sharper image, an intermediate stage for estimating the high-frequency sub bands has been proposed. The proposed technique has been tested on satellite benchmark images. The quantitative (peak signal-to-noise ratio and root mean square error) and visual results show the superiority of the proposed technique over the conventional and state-of-art image resolution enhancement techniques.

Back to Top

Abstract

Combined DWT-DCT Digital Image Watermarking
The proliferation of digitized media due to the rapid growth of networked multimedia systems has created an urgent need for copyright enforcement technologies that can protect copyright ownership of multimedia objects. Digital image watermarking is one such technology that has been developed to protect digital images from illegal manipulations. In particular, digital image watermarking algorithms which are based on the discrete wavelet transform have been widely recognized to be more prevalent than others. This is due to the wavelets excellent spatial localization, frequency spread, and multi-resolution characteristics, which are similar to the theoretical models of the human visual system. In this project, we describe an imperceptible and a robust combined DWT-DCT digital image watermarking algorithm. The algorithm watermarks a given digital image using a combination of the Discrete Wavelet Transform (DWT) and the Discrete Cosine Transform (DCT). Performance evaluation results show that combining the two transforms improved the performance of the watermarking algorithms that are based solely on the DWT transform.

Back to Top

Abstract

Speeds Detection Camera System Using Image Processing Techniques On Video Streams
This project, presents a new Speed Detection Camera System (SDCS) that is applicable as a radar alternative. SDCS uses several image processing techniques on video stream in online -captured from single camera- or offline mode, which makes SDCS capable of calculating the speed of moving objects avoiding the traditional radars problems. SDCS offers an-expensive alternative to traditional radars with the same accuracy or even better. SDCS processes can be divided into four successive phases; first phase is Objects detection phase. Which uses a hybrid algorithm based on combining an adaptive background subtraction technique with a three-frame differencing algorithm which ratifies the major drawback of using only adaptive background subtraction? The second phase is Objects tracking, which consists of three successive operations, object segmentation, Object labeling, and Object canter extraction. Objects tracking operation takes into consideration the different possible scenarios of the moving object like; Simple tracking, object has left the scene, object has entered the scene, object cross by another object, and object leaves and another one enters the scene. Third phase is speed calculation phase, which is calculated from the number of frames consumed by the object to pass-by the scene. The final phase is Capturing Objects Picture phase, which captures the image of objects that violate the speed limits. SDCS is implemented and tested in many experiments; it proved to have achieved a satisfactory performance.

Back to Top

Abstract

A Visual Cryptographic Technique To Secure Image Shares
The Visual Cryptography Scheme (VCS) is a secure method that encrypts a secret image by breaking it into shares. A distinctive property of VCS is that one can visually decode the secret image by superimposing shares without computation. The project presents an approach for embedding visual cryptographically generated image shares in the host images to provide authentication for the VC shares and makes these secret shares invisible by embedding them into host images. The secret shares generated from VC encryption are watermarked into some host images using digital watermarking. Digital watermarking is used for providing the double security of image shares. The share is embedded into the host image in frequency domain using Discrete Cosine Transform (DCT). In frequency domain, the obtained marked image must be less distorted when compared to the original image. Thus secret shares are not available for any alteration by the adversaries who try to create fake shares. Every pixel of the binary VC share is invisibly embedded into the individual block of the host image. The process of watermark extraction necessitates only the watermarked image and it does not require the original host image. The scheme provides more secure and meaningful secret shares that are robust against a number of attacks like blurring, sharpening, motion blurring etc.

Back to Top

Abstract

A Matlab Based Face Recognition System Using Image Processing
Face recognition has long been a goal of computer vision, but only in recent years reliable automated face recognition has become a realistic target of biometrics research. New algorithms, and developments spurred by falling costs of cameras and by the increasing availability processing power have led to practical face recognition systems. These systems are increasingly being deployed in a wide range of practical applications, and future improvements promise to spread the use of face recognition further still. In this chapter, were view the field of face Recognition, analyzing its strengths and weaknesses and describe the applications where the technology is currently being deployed and where it shows future potential. We describe the IBM face recognition system and some of its application domains.

Back to Top

Abstract

Classification Of Diabetic Stages Using Image Processing And Ann
Diabetic-related eye disease is a major cause of preventable blindness in the world. It is a complication of diabetes which can also affect various parts of the body. When the small blood vessels have a high level of glucose in the retina, the vision will be blurred and can cause blindness eventually. This is known as diabetic retinopathy. Regular screening is essential in order detect the early stages of diabetic retinopathy for timely treatment to prevent or delay further deterioration. This project detects the presences of abnormalities in the retina such as the structure of blood vessels, micro aneurysms, exudates and texture properties using image processing techniques. These features are input into artificial neural network for automatic detection and can quickly process a large number of funds images obtained from mass screening to help reduce the cost and increase productivity and efficiency for ophthalmologists.

Back to Top

Abstract

Image Fusion
Wavelets are mathematical functions that cut up data into different frequency components, and then study each component with a resolution matched to its scale. Wavelet algorithms process data at different scales or resolutions. Image fusion is processing of images about a given region so that the resultant image is more reliable, clear and more intelligible. To obtain a two-dimensional wavelet transform, one-dimensional transform is applied first along the rows and then along the columns to produce four sub bands: low-resolution, horizontal, vertical, and diagonal. (The vertical sub band is created by applying a horizontal high-pass, which yields vertical edges.). At each level, the wavelet transform can be re-applied to the low Resolution sub band to further decor relate the image. . Wavelet transform is first performed on each source images. The fused wavelet coefficient map can be constructed from the wavelet coefficients of the source images according to the fusion decision map. Finally the fused image is obtained by performing the inverse wavelet transform.

Back to Top

Abstract

Steganography
Steganography is usually confused with cryptography. While related in many aspects, Steganography and cryptography are not the same. The existence of a cryptographic message can easily be noticed by a casual observer as the messages are scrambled to hide the original content. Whereas, Steganography hides the original message in other innocent messages to protect the information from prying eyes. The existence of the hidden message is not obvious to an ordinary observer and cannot be detected by naked eye in most cases.

Back to Top

Abstract

Speed Detection Camera System Using Image Processing On Video Streams
The need to use radar systems is growing in importance. This is not only for military applications but also for civilian applications. The latter includes (but not limited to) monitoring speeds of vehicles on high ways, sport competitions, aeroplanes, etc. The spread of use of radar systems is affected negatively with the high cost of radar systems and also with the increasing requirements on the accuracy of the outputs. This motivated the research on alternative technologies that offer both higher accuracy and be more cost effective. The field of image processing has grown considerably during the past decade. This has been driven by 1) the increased utilization of imagery in myriad applications, coupled with 2) improvements in the size, speed and cost effectiveness of digital computers and related signal processing technologies. Image processing has found a significant role in scientific, industrial, space and government applications. Many systems nowadays can be replaced by image processing alternate systems that perform better than the former systems. An SDCS system is one of these systems that can replace traditional radars. An SDCS system is applicable as an alternative to current radar systems. This is better cost effective system than current ones. It also has accurate outputs as traditional radars or even better. SDCS system can be integrated with Automatic Number Plate Recognition (ANPR) system to form a complete radar system. ANPR system is a mass surveillance method that uses optical character recognition on images to read the license plates on vehicles.

Back to Top

Abstract

Steganography Using Least Significant Bit Algorithm
The rapid development of data transfer through internet made it easier to send the data accurate and faster to the destination. One of the most important factors of information technology and communication has been the security of the information. For security purpose the concept of Steganography is being used. Steganography is art and science of invisible communication. Our project deals with image Steganography. Various Steganography algorithms like Least Significant Bit (LSB) algorithm, Jsteg and F5 algorithms, out of these we are using LSB algorithm. Steganography is the method through which existence of the message can be kept secret. This is accomplished through hiding information in information, thus hiding the existence of the communicated information. This project gives a brief idea about the image Steganography that make use of Least Significant Bit (LSB) algorithm for hiding the data into image which is implemented through the Microsoft .NET framework.

Back to Top

Abstract

Bimodal Biometric Person Authentication System Using Speech And Signature Features
Biometrics offers greater security and convenience than traditional methods of person authentication. Multi biometrics has recently emerged as a means of more robust and efficient person authentication scheme. Exploiting information from multiple biometric features improves the performance and also robustness of person authentication. The objective of this project is to develop a robust bimodal biometric person authentication system using speech and signature biometric features. Speaker based unimodal system is developed by extracting Mel Frequency Cepstral Coefficients (MFCC) and Wavelet Octave Coefficients of Residues (WOCOR) as feature vectors. The MFCCs and WOCORs from the training data are modeled using Vector Quantization (VQ) and Gaussian Mixture Modeling (GMM) techniques. Signature based unimodal system is developed by using Vertical Projection Profile (VPP), Horizontal Projection Profile (HPP) and Discrete Cosine Transform (DCT) as features. A bimodal biometric person authentication system is then built using these two unimodal systems. Experimental results show that the bimodal person authentication system provides higher performance compared with the unimodal systems. The bimodal system is finally evaluated for its robustness using the noisy data and also data collected from the real environments. The robustness of the bimodal system is more compared to the unimodal person authentication systems.

Back to Top

Abstract

Object Recognition Using Sift Algorithm
Image matching is a fundamental aspect of many problems in computer vision, including object or scene recognition, solving for 3D structure from multiple images, stereo correspondence, and motion tracking. This project describes image features that have many properties that make them suitable for matching differing images of an object or scene. The features are invariant to image scaling and rotation, and partially invariant to change in illumination and 3D camera viewpoint. The features that are highly distinctive are called key points, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This project also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

Back to Top

Abstract

Two-Stage Image De-noising By Principal Component Analysis With Local Pixel Grouping
This project presents an efficient image de-noising scheme by using principal component analysis(PCA) with local pixel grouping(LPG).For a better preservation of image local structures, pixel and its nearest neighbors are modeled as a vector variable, whose training samples are selected from the local window by using block matching based LPG. Such an LPG procedure guarantees that only the sample blocks with similar contents are used in the local statistics calculation for PCA transform estimation, so that the image local features can be well preserved after coefficient shrinkage in the PCA domain to remove the noise. The LPG-PCA de-noising procedure is iterating done more time to further improve the de-noising performance, and the noise level is adaptively adjusted in the second stage. Experimental results on bench mark test images demonstrate that the LPG-PCA method achieves very competitive de-noising performance, especially in image fine structure preservation, compared with state-of-the-art de-noising algorithms. "

Back to Top

Abstract

Ohta Based Covariance Technique For Tracking Object In Video Scene
In this project we propose Ohta based covariance method for tracking an object in various challenging situations. In the proposed method covariance matrix is used as the region descriptor. In addition to this other elements of feature vector are color moments, derivatives of the region and the pixel position. We incorporated a model update algorithm based on Riemannian geometry for updating covariance matrix. This method has been applied to four different conditions and the resulting experimental results show the robustness of the technique against occlusion, camera motion appearance and illumination change. Also the performance of this technique is compared with other existing techniques such as the covariance method with RGB features and histograms based method in terms of detection rate and show the superiority against other two.

Back to Top

Abstract

Performance Analysis Of Gender Clustering And Classification Algorithms
In speech processing, gender clustering and classification plays a major role. In both gender clustering and classification, selecting the feature is an important process and the often utilized feature for gender clustering and classification in speech processing is pitch. The pitch value of a male speech differs much from that of a female speech. Normally, there is a considerable frequency value difference between the male and female speech. But, in some cases the frequency of male is almost equal to female or frequency of female is equal to male. In such situation, it is difficult to identify the exact gender. By considering this drawback, here three features namely; energy entropy, zero crossing rate and short time energy are used for identifying the gender."

Back to Top

Abstract

Image/Video Encryption And Decryption
In present times, the protection of multimedia data is becoming very important. The protection of this multimedia data can be done with encryption. There are so many different techniques should be used to protect confidential image data from unauthorized access. With the ever-increasing growth of multimedia applications, security is an important issue in communication and storage of images, and encryption is one the ways to ensure security. Image encryption techniques try to convert original image to another image that is hard to understand; to keep the image confidential between users, in other word, it is essential that nobody could get to know the content without a key for decryption.

Back to Top

Abstract

Image Mosaic Algorithm Based On Sift
This project explores the effectiveness of the Scale Invariant Feature Transform (SIFT) for image matching. There is a popularly used interest point detection method often applied to image matching, the Harris corner detector. The Harris corner detector is non-invariant to scale change. The experiments of image matching based on both the SIFT and the Harris corner detector are performed to show the effectiveness of the scale invariant property of the SIFT method. Furthermore, the image matching method based on SIFT is applied to point tracking, and comparison with Kanade-Lucas-Tomasi feature point tracker studied.

Back to Top

Abstract

Video Mosaic
This project shows how to create a mosaic from a video sequence. Video mosaicking is the process of stitching video frames together to form a comprehensive view of the scene. The resulting mosaic image is a compact representation of the video data, which is often used in video compression and surveillance applications.

Back to Top

Abstract

Virtual Calculator
The main aim if this project is to design a system, where in the user can use the calculator by moving the finger in air in front of the web cam .In this project, we are using MATLAB software. As we run this code in mat lab, the web camera will be initiated and the keypad image will be displayed on the monitor. Now user has to move his finger and has to select a particular button for calculation purpose. Here we can perform basic arithmetic operations. The result will be displayed on the mat lab command window.

Back to Top

Abstract

A Novel Anti Phishing Framework Based On Visual Cryptography
With the advent of internet, various online attacks have been increased and among them the most popular attack is phishing. Phishing is an attempt by an individual or a group to get personal confidential information such as passwords, credit card information from unsuspecting victims for identity theft financial gain and other fraudulent activities. Fake websites which appear very similar to the original ones are being hosted to achieve this. In this project we have proposed a new approach named as ""A Novel Anti-phishing framework based on visual cryptography ""to solve the problem of phishing. Here an image based authentication using Visual Cryptography is implemented. The use of visual cryptography is explored to preserve the privacy of an image captcha by decomposing the original image captcha into two shares (known as sheets) that are stored in separate database servers (one with user and one with server) such that the original image captcha can be revealed only when both are simultaneously available; the individual sheet images do not reveal the identity of the original image captcha. Once the original image captcha is revealed to the user it can be used as the password. Using this website cross verifies its identity and proves that it is a genuine website before the end users.

Back to Top

Visual Cryptography Authentication For Data Matrix Codes
An Identity Card is any document which may be used to verify aspects of an identity. If issued in the form of a small, mostly standard-sized card, it is usually called an identity card (IC). It plays in the society, threats of fraud, tampering, and identity theft arises. Thus, security and authenticity of these ID cards and their owners prove to be of much necessity. This project goal is to make use of Visual Cryptography and 2D data matrix codes to address these issues. Visual Cryptography is a secret sharing scheme where a confidential image is encrypted into noise-like secure shares, which can be reconstructed visually by superimposing the shares. Extended Visual Cryptography on the other hand, makes use of recognizable images as shares to the confidential image. In this project, the information in the ID cards are encoded into two 2D data matrix codes, which then are used in the two levels of extended visual cryptography. The first level provides authentication of the ID card, and the second level secures the identity of the ID card owner.

Back to Top

Abstract

Virtual Mouse Using A Webcam
Since the computer technology continues to grow up; the importance of human computer interaction is enormously increasing. Nowadays most of the mobile devices are using a touch screen technology. However, this technology is still not cheap enough to be used in desktop systems. Creating a virtual human computer interaction device such as mouse or keyboard using a webcam and computer vision techniques can be an alternative way for the touch screen. In this study, finger tracking based a virtual mouse application has been designed and implemented using a regular webcam. The motivation was to create an object tracking application to interact with the computer, and develop a virtual human computer interaction device. In this study, a color pointer has been used for the object recognition and tracking. Left and the right click events of the mouse have been achieved by detecting the number of pointers on the image.

Back to Top

Abstract

Voice Activated Calculator
In the era of human machine interface, speech recognition is being looked upon as highly fascinating field to achieve human computer interaction. Several applications of speech recognition have emerged over the past years including voice dialing, voice query recognition for call routing and simple data entry. Speech recognition is the process of automatic determination of linguistic information conveyed by human speech using a computer and reconstructing the text of a spoken sentence from the continuous acoustic signal, overcoming the associated noise induced disturbances. The aim of this project is to present an overview of the application of speech recognition system for mathematical computing using a basic computer without any additional hardware. The system developed would be able to take voice inputs from the user, match it with the database to recognize the digits, perform the required mathematical operation and display the output. This technology would make the calculation process easier for the user by supporting the concept of multitasking as well as eliminating human errors due to mistyping.

Back to Top

Abstract

Speech Recognition
This project presents a fast and accurate automatic voice recognition algorithm. We use Mel frequency Cepstral Coefficient(MFCC) to extract the features from voice and Vector quantization technique to identify the speaker, this technique is usually used in data compression, it allows to model a probability functions by the distribution of different vectors, the results that we achieve were 100% of precision with a database of 10 speakers.

Back to Top

Abstract

Facial Expression Recognition
Automatic recognition of people is a challenging problem which has received much attention during recent years due to its many applications in different fields. Face recognition is one of those challenging problems and up to date, there is no technique that provides a robust solution to all situations. This project presents a new technique for human face recognition. This technique uses an image-based approach towards artificial intelligence by removing redundant data from face images through image compression using the two-dimensional discrete cosine transform (2D-DCT). The DCT extracts features from face images based on skin color. Feature vectors are constructed by computing DCT coefficients. A self-organizing map (SOM) using an unsupervised learning technique is used to classify DCT-based feature vectors into groups to identify if the subject in the input image is “present” or “not present” in the image database. Face recognition with SOM is carried out by classifying intensity values of grayscale pixels into different groups. Evaluation was performed in MATLAB using an image database of 25 face images, containing five subjects and each subject having 5 images with different facial expressions. After training for approximately 850 epochs the system achieved a recognition rate of 81.36% for 10 consecutive trials. The main advantage of this technique is its high-speed processing capability and low computational requirements, in terms of both speed and memory utilization.

Back to Top

Abstract

View-Invariant Action Recognition Based On Artificial Neural Networks
In this project, a novel view invariant action recognition method based on neural network representation and recognition is proposed. The novel representation of action videos is based on learning spatially related human body posture prototypes using self-organizing maps. Fuzzy distances from human body posture prototypes are used to produce a time invariant action representation. Multilayer perceptions are used for action classification. The algorithm is trained using data from a multi-camera setup. An arbitrary number of cameras can be used in order to recognize actions using a Bayesian framework. The proposed method can also be applied to videos depicting interactions between humans, without any modification. The use of information captured from different viewing angles leads to high classification performance. The proposed method is the first one that has been tested in challenging experimental setups, a fact that denotes its effectiveness to deal with most of the open issues in action recognition.

Back to Top

Abstract

Efficient Defect Detection Algorithm For Gray Level Digital Images Using Gabor Wavelet Filter And Gaussian Filter
The Automated visual inspection systems are utilized effectively to identify the defects in various digital images in industries. In our research work we have used Gabor filter and Gaussian filter to eliminate the texture elements in the digital image by isolating the defected area. Then a fast searching algorithm which uses feature extraction parameters is deployed to identify the defected pixels and to effectively segment it. The proposed technique is suitable for texture and non-texture images. Thus the Algorithm is used to identify the defects in the digital texture image using non texture methods.

Back to Top

Abstract

Hand Vein Biometric Verification Prototype
This project presents a hand vein authentication system using fast spatial correlation of hand vein patterns. In order to evaluate the system performance, a prototype was designed and a dataset of 50 persons of different ages above 16 and of different gender, each has 10 images per person was acquired at different intervals, 5 images for left hand and 5 images for right hand. In verification testing analysis, we used 3 images to represent the templates and 2 images for testing. Each of the 2 images is matched with the existing 3 templates. FAR of 0.02% and FRR of 3.00 % were reported at threshold 80. The system efficiency at this threshold was found to be 99.95%. The system can operate at a 97% genuine acceptance rate and 99.98 % genuine reject rate, at corresponding threshold of 80. The EER was reported as 0.25 % at threshold 77. We verified that no similarity exists between right and left hand vein patterns for the same person over the acquired dataset sample. Finally, this distinct 100 hand vein patterns dataset sample can be accessed by researchers and students upon request for testing other methods of hand veins matching.

Back to Top

Abstract

Data Hiding In Medical Images
The security of medical records is an important issue related to privacy and safety during storage and communication. Human errors in hospitals and medical centers are closed related with mishandling of medical records. Cryptography and Steganography can offer not only information security but also secure association of multimedia records. Embodying a part of Cryptography, the art and science of writing hidden messages in such a way that no one, apart from the sender and intended recipient, suspects the existence of the message, a form of security through obscurity is defined as Steganography. In digital Steganography, electronic communications may include Steganography coding inside of a transport layer, such as a document file, image file, program or protocols. Media files are ideal for Steganography transmission because of their large size. One of the digital Steganography techniques includes concealing messages within lowest bits of images or media files. The robustness of the encoding depends upon the technique used to encode the stego-data. The main objective of making Steganography encoding difficult to detect is to ensure that the changes to the cover image by the injection of the embedded image is negligible. Technical advancements which have gained significance in the context of data embedding in video and audio signals can be extended to telemedicine. Data embedding with medical images will have applications such as compact storage, efficient transmission and confidentiality of patient records. This will help the data to remain intact across varying data file formats. Current standards for medical image data exchange like DICOM provide a set of methods that could be used to implement security policies regarding the interchange of data objects through networks. However, the diffusion of such systems is not very large, so that in some applications a medical image could be distributed to a non-standard system, with the risk that a format conversion could result in a wrong link between image and patient data. Hence, in order to maintain the integrity of the image as well as the data this project uses Arithmetic coding along with cryptography to incorporate the data in a medical image.

Back to Top

Abstract

Satellite Image Resolution Enhancement
Since the computer technology continues to grow up, the importance of human computer interaction is enormously increasing. Nowadays most of the mobile devices are using a touch screen technology. However, this technology is still not cheap enough to be used in desktop systems. Creating a virtual human computer interaction device such as mouse or keyboard using a webcam and computer vision techniques can be an alternative way for the touch screen. In this study, finger tracking based a virtual mouse application has been designed and implemented using a regular webcam. The motivation was to create an object tracking application to interact with the computer, and develop a virtual human computer interaction device.In this study, a color pointer has been used for the object recognition and tracking. Left and the right click events of the mouse have been achieved by detecting the number of pointers on the image

Back to Top

Abstract

Satellite Image Resolution Enhancement
Resolution of an image has been always an important issue in many image- and video-processing applications, such as video resolution enhancement, feature extraction and satellite image resolution enhancement. Interpolation in image processing is a method to increase the number of pixels in a digital image. Interpolation has been widely used in many image processing applications, such as facial reconstruction multiple description coding and image resolution enhancement .The interpolation-based image resolution enhancement has been used for a long time and many interpolation techniques have been developed to increase the quality of this task. There are three well-known interpolation techniques, namely, nearest neighbor, bilinear, and bicubic. Bicubic interpolation is more sophisticated than the other two techniques and produces smoother edges. Wavelets are also playing a significant role in many image processing applications. The 2-D wavelet decomposition of an image is performed by applying the 1-D discrete wavelet transform (DWT) along the rows of the image first, and then the results are decomposed along the columns. This operation results in four decomposed sub band images referred to low (LL), low-high (LH), high-low (HL), and high-high (HH). The frequency components of those sub bands cover the full frequency spectrum of the original image. In this project, we propose a resolution-enhancement technique using interpolated DWT high-frequency sub band images and the input low-resolution image. Inverse DWT (IDWT) has been applied to combine all these images to generate the final resolution-enhanced image.

Back to Top

Abstract

Color Detection In Real Time Video/Image
Image segmentation, a process of pixel classification, aims to extract or segment objects or regions from the background. It is a critical preprocessing step to the success of image recognition image compression, image visualization, and image retrieval. Pal and Pal .provided a review on various segmentation techniques. It should be noted that there is no single standard approach to segmentation. Many different types of scene parts can serve as the segments on which descriptions are based, and there are many different ways in which one can attempt to extract these parts from the image. Selection of an appropriate segmentation technique depends on the type of images and applications. Image segmentation, a process of pixel classification, aims to extract or segment objects or regions from the background.

Back to Top

Abstract

Basic Image Processing Functionalities
The presented Matlab code demonstrates a set of basic image processing functionalities. Furthermore, it provides a simple Graphical User Interface, also implemented in Matlab, using the GUIDE tool.

Back to Top