Iris segmentation is the most contested issue in the iris recognition system, since noise and poor image quality can significantly affect accuracy of iris localization stage. Therefore, very careful attention has to be paid for the segmentation process if only an accurate result is expected. This study presents a new method for precise pupil detection capable of handling the unconstrained bad acquisition conditions especially those related to low contrast or to the non-uniform brightness caused by the position of light sources, specular reflection, eyelashes and eyelids. Contrast stretching (normalization) technique is used for handling the variations in contrast and illumination in an iris image by stretching' the range of intensity values. Next, the local integration is applied on the enhanced image, this process will enhance the contrast level between the existing white and black areas of the image; this will useful to compute the optimal threshold value required to perform a successful image binarization for the purpose of isolation of the pupil region, the seed fill algorithm is used as region growing method to segment the binary image and allocate the pupil as a circular black segment with biggest area, the approximate pupil center is detected then for removing the specular reflection, the pupil is filled with black color using a simple filling method. Finally a circle fitting algorithm is used for precisely allocating the circular pupil region by the fact that richer iris textures are not closer to the pupil boundary. A set of tests was conducted on 2,655 iris images which were downloaded from CASIA V3.0-interval standard dataset; the test results indicated that the proposed method had subjectively 100% accuracy rate with pupil localization, process satisfy the real time constraints even when dealing with images have very different brightness or contrast conditions or they contain eyelashes artifacts.

Iris is regarded as the most reliable and accurate biometric identification system available. In this paper, we propose a novel system for iris recognition composed of image preprocessing including (segmentation, normalization, eyelashes and eyelids detection, enhancement), features extraction and classifier design. Iris feature extraction is based on using second order gradient images operator that will be robust against the variations may occur in iris's contrast or illumination because of lightening differences and camera changes. The low order norms of gradient components are used to establish the feature vector. The experimental results indicated that the efficiency of our proposed method when tested on the CASIA v1 and CASIA v4-Interival image database is promising, it achieves nearly perfect high recognition rate.

Abstract:Content-Based Image Retrieval CBIR system commonly extracts retrieval results respecting to the similarities of the extracted feature of the given image and the candidate images. The proposed system presented a comparative analysis of five types of classifiers which used in CBIR. These classifiers are Multilayer Perceptron (MP), Sequential Minimal Optimization (SMO), Random Forest (RF), Bayes Network (BN) and Iterative Classifier Optimizer (ICO). It has been investigated to find out the best classifier in term of performance and computation to be the suitable for image retrieval. The low level image features which include texture and color are used in the proposed system. The color features involve color-histogram, color-moments and color-autocorrelogram while texture features involve wavelet transform and log Gabor filter. Also the system will include hybrid of texture and color features to get efficient image retrieval. The system was tested using WANG database, and the best average precision achieved was (85.08%) when combining texture and color features and using the (RF) classifier.

No abstract

No abstract