Among the various biometrics technologies, iris recognition is the most reliable and accurate biometric identification system available. In this paper a novel framework for recognizing and identifying iris is been proposed. Iroimages are pre-processed to remove noise using median filtering on different image planes separately. GLCM and Gabor wavelet texture features have been used to identify the Iris and classification tree approach is used to classify them. The results are improved by the use of combined GLCM and Gabor features. Speed vector machine (SVM) is used for classification. This is an intelligent system which has the ability to identify retina from photographs of their iris and it provides accurate results in less time. The real time database is prepared for the experimental use. The database contains various iris with various shapes, colours and size. Experiment is carried out with the different Iris of different classes and tested. Iris recognition by using blood vessel segmentation

ABSTRACT:This paper presents a detailed study and comparison of different clustering based image segmentation algorithms. The traditional clustering algorithms are the hard clustering algorithm and the soft clustering algorithm. We have compared the hard k-means algorithm with the soft fuzzy c-means (FCM) algorithm. To overcome the limitations of conventional FCM we have also studied Kernel fuzzy c-means (KFCM) algorithm in detail. The K-means algorithm is sensitive to noise and outliers so, an extension of K-means called as Fuzzy c-means (FCM) are introduced. FCM allows data points to belong to more than one cluster where each data point has a degree of membership of belonging to each cluster. The KFCM uses a mapping function and gives better performance than FCM in case of noise corrupted images.

Gesture recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost importance in designing an intelligent and efficient human-computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation to virtual reality. In this paper, we provide a survey on gesture recognition with particular emphasis on hand gestures and facial expressions. Applications involving wavelet transform and principal component analysis for face and hand gesture recognition on digital images.

In this paper Neural Networks have been implemented for categorizing the beats in an ECG into normal and abnormal. This paper intends towards the enabling of automatic detection and classification of various Arrhythmia types. The MIT-BIH Arrhythmia database has been implemented. This database is referred for classify the ECG image in to Standard Arrhythmia CU Ventricular Tachyarrhythmia, Supraventricular Arrhythmia and Ventricular Tachyarrhythmia. During the process, the scanned ECG images have been preprocessed to remove noise. After cropping the ROI, the Dijikstraw's shortest path algorithm is employed for detection and digitization of ECG signal. A wide Variety of Harris corner features are drawn out from the digitized ECG signal. Using these features ECG signals are classified into different categories. The real time scanned ECG images are also used for disclosure and classification of ECG images. The dataset is divided as training and testing sub-data. The accuracy and abilities of investigating the concepts of ECG arrhythmia detection is explained with practical and comparisons with various network models have been implemented.

No abstract