Wen Li

Bio: Wen Li is an academic researcher from Lanzhou University. The author has contributed to research in topics: Iris recognition & Vertex (computer graphics). The author has an hindex of 1, co-authored 2 publications receiving 15 citations.

Accurate Iris Location Based on Region of Interest

Abstract: Iris location is an essential module in iris recognition. Traditional iris location methods involve a large range of search, which is computation wasting and sensitive to noise. And these methods adopt circular template to locate the pupillary boundary. It may not accurately describe the pupillary actual boundary and bring the error for the following feature extraction and recognition. To address these problems, this paper presents an algorithm of accurate iris location based on region of interest for improving the accuracy of iris location. At first, according to the feature of approximate concentric circles of iris inner and outer boundaries, the Region of Interest (ROI) only containing the complete iris information can be automatically extracted from an original iris image by Histograms of Oriented Gradients (HOG) to get the statistical information of direction and gradient of an iris image and then the information is taken into Support Vector Machines (SVM) for training and the SVM decision function is gotten. It can eliminate the sensitive noise and reduce the amount of calculation when reserving the useful information as much as possible. Then the iris inner boundary is located roughly by using minimum average gray method, on the basis of this, the annular region is mapped on the rectangular region for the iris inner boundary accurate detection. At last, the iris outer boundary is confirmed by using the improved J.Daugman circle differential algorithm. Experimental results show that the proposed algorithm can efficiently improve the accuracy of iris location.

An Efficient Contour Tracking and Coding Algorithm Based on Vertex Chain Code

Abstract: Based on analysis of contours of irregular region, and according to the characteristic that massive continuous code and the same specific code combination are usually contained in a region boundary's vertex chain code, a new effective contour tracking algorithm and representation method based on the pixel vertex matrix is proposed. Moreover, we re-encoding the new vertex chain code using a Huffman coding strategy and then select the more compressed result as the output. The results showed that the new method could effectively reduce code stream for contours, hence increase the compression ratio of the image.

Iris location based on regional property and iterative searching

Abstract: Iris recognition is one of common biometric identification technologies, and an important part of iris recognition is iris location, whose precision directly affects the accuracy of iris recognition. Fitting the inner and outer edge of iris as an approximate circle is a common iris location method, which thereby can lead to fitting errors between the location result and the actual edge. In order to solve this problem, the paper proposes an iris location algorithm based on regional property and iterative searching. The pupil area is extracted using the regional attribute of the iris image, and the iris inner edge is fitted exactly by iterating, comparing and sorting the pupil edge points; then the outer edge location is completed in an iterative searching method on the basis of the extracted pupil centre and radius. The results of the experiment show that in this algorithm, more accurate iris inner edge location can be achieved and a range of comprehensive advantages of faster location speed and higher location accuracy are.

A new effective algorithm for iris location

Abstract: Iris location is an essential step and an important part in an iris recognition system. However, traditional iris location methods often involve a large space of search, which is calculation wasting and sensitive to noise. And these methods adopt circular orientation to locate the pupillary boundary; it may lead to inaccurate location result and influence the subsequent feature extraction and recognition. To address these problems, this paper presents a precise iris location algorithm based on Vector Field Convolution (VFC, an improved Snake model) to improve the accuracy of iris location. Firstly, obtaining the iris area completely include the inside and outside boundary from an original iris image, then using minimum average grey value method to determine initialization contour of VFC model automatically, so as to locate an iris inner boundary precisely under the internal and external force of active contour. At last, we adopt the improved Daugman algorithm to locate the iris outer boundary that relatively contains little texture information. Experimental results show that the location accuracy of this method is higher, the iris inner edge location is much closer to the real boundary, the result of location have been improved significantly.

Edge based selective encryption scheme for biometric data using chaotic theory

Abstract: Security of biometric data plays a major concern due to extensive use of biometric systems in many applications. This paper proposes an efficient method for encryption of iris images using edge based encryption algorithm based on chaotic theory. In this proposed technique, the iris image is segmented into significant and non significant blocks to find region of interest (ROI) i.e. to localize iris from complete eye image from which features are extracted to generate biometric template. Selective encryption is used to encrypt the region of interest and it reduces the computational overhead and processing time as compared to full encryption techniques. The experimental results prove that edge based selective encryption significantly reduces the time of encryption of iris images as compared to full encryption method without any compromise in performance. Performance of proposed algorithm has been experimentally analyzed using key sensitivity analysis and the results prove that the encryption algorithm has high key sensitivity and the algorithm is lossless in nature.

Identification of Heart Disease With Iridology Using Backpropagation Neural Network

Abstract: Heart is an organ which function is to pump blood throughout the whole body. Because of it’s never-ending work, heart is prone to have problems. Which is why a simpler and more efficient method to identify and recognize heart complication is needed. By using iridology, heart complication can be recognized through the iris. This research was done to create a system which can recognize a problem that is happening on the heart by observing the iris. The system will feature extraction by using two methods, Principal Component Analysis (PCA) and Gray Level Co-occurrence Matrix (GLCM), these are done to identify the effects of feature extraction method against the success rate and classification using Backpropagation Neural Network. The result showed that the success rate of using PCA produced 90% and using GLCM was 77.5%.

A new approach for iris localization based on an improved level set method

Abstract: In iris recognition systems, iris localization is a critical step which affects the further results definitively. Most of the traditional localization methods were time consuming and sensitive to noises. To solve the problems, we propose an algorithm which adopts a momentum based level set method to locate the pupil boundary. This method hasan advantage of decreasing the effect of local optima solutions and poor convergence dramatically, thus it could accurately describes the pupil boundary and decrease the influences of error parts. Experiment results show the iris localization under this method has a higher accuracy, and the inner iris boundary is much closer to the real one, localization results have been improved significantly.