Iris recognition is the mean of biometric identification using very large amount of iris database taken without contact to the human body. Basically three main methods are available to process iris data, out of which in this paper, an iris image synthesis method based on Principal Component Analysis (PCA), Independent component analysis (ICA) and Daugman's rubber sheet model& hybrid model is proposed. Iris Recognition is a most secure biometric authentication that uses pattern-recognition techniques. The video based iris recognition system is used to locate eye and iris, to evaluate degree of occlusion by eyelids, determine the centre & boundary of pupil and outer edge of iris. The measured features are encoded into 512-byte iris code which is further enrolled for identification. Here we compared different techniques i.e. ICA, PCA, Daugman's rubber sheet model & hybrid model which is combination of all above three along with RFID system. Out of 400 degrees of freedom (measurable variables), 200 features are compared to create the code which can be compared to an entire database in milliseconds. After using lot many algorithms for iris recognition we found that existing system shows, Daugman's rubber sheet model is better. The comparative study of the various algorithms proposed above shows some interesting results which is the achievement of the practical study on iris recognition.

This paper proposes a real time visual surveillance system for human detection this interest needs in many applications where human entry is restricted. In order to develop a real time system initially wavelet transform based multiple features obtained from three layers of each image sample which forms training input to the SVM classifier. Finally, we used trained recognizer to identify whether there is somebody broken into object region. If there is, the automatic warning device gives the alarm, which guarantees a real-time surveillance.

No abstract

Automatic human detection is an important application where security is the main concern. As human detection problem involves classification of two objects as humans and others, a human detection using intelligent video surveillance system is presented using support vector machine to detect human in surveillance field. In this paper, in order to improve the efficiency of the machine learning 2D Wavelet transform based features are used. It consists of wavelet statistical features and wavelet co-occurrence features which are obtained from red, green and blue layers of sample images. The sample images are obtained through the video which forms training input to SVM. The experimental results demonstrate that the proposed system achieves good success rate for wavelet co-occurrence features.

No abstract