Zuraini Othman

Preliminary study on iris recognition system: Tissues of body organs in iridology

Iris recognition gives many advantages to those who practice iridology in order to detect symptom in patients iris. In iridology, there are many factors in it iris analysis have to be considered due to complex iriss structure. Practitioners have to measure color of iris, its density, sign on iris image and the location of body organ in iris image as stated in iridology chart. Currently, iris diagnosis systems have certain weaknesses. This paper proposed an approach to discover those problems. An accurate iris image will be obtained by using new segmentation technique in iris recognition which called water flow method. This research expected to fulfill all the iridology practitioners need in order to diagnose patient health.

A statistical approach of multiple resolution levels for canny edge detection

Vision processing needs effective feature detectors to estimate the structure and properties of objects in an image. The best known is Canny edge detection that combine a Gaussian low pass filter for noise reduction and non-maximal suppression and hysteresis threshold for edge localization. A possible problem of this approach is that the threshold values. Applying a single fixed threshold to gradient maxima is not an optimal choice. Thus, Canny uses two thresholds values namely Tlow and Thigh to reduce the number of false positive of pixels that represent significant contours in the image. However, by introducing two fixed threshold values are also not an optimal choice due to high variations in images. In this paper we introduce a method that computes the threshold values from the foreground and background image pixels. According to this method, an image is divided into several blocks using at multiple resolution levels. After that, a sampling approach is used on global and local regions to get the optimal thresholds by selecting the highest between class variance values. We have performed experiments on 200 images from the Berkeley dataset. The results show that the proposed method outperforms Canny that uses two fixed threshold values.

An Adaptive Threshold Based on Multiple Resolution Levels for Canny Edge Detection

Machine vision requires detectors to obtain the characteristics and the nature of the object in the image. The Canny edge detection method is the most recognisable technique that combines a low-pass Gaussian filter to reduce noise and oppression instead of the maximum threshold and hysteresis for localisation advantages. One of the problems encountered in the Canny approach is in the selection of a threshold value. Using a single fixed threshold value for the maximum gradient is not the optimal choice. Therefore, the Canny approach uses two threshold values, a high threshold and a low threshold to reduce the number of false positive pixels, representing the contours in the image significantly. However, using two fixed threshold values is also not the best option because of the high variation in the image. Although adaptive thresholds have been introduced, they are only used for specific types of images. In this paper, we introduce a method that computes the threshold values from the foreground and background image pixels from global and local image analysis. According to this method, an image is divided into several blocks using multiple resolution levels. After that, a modification sampling approach is used on global and local regions to get the optimal thresholds by selecting the highest between the class variance values. Experiments have been done on four different types of dataset images which are Berkeley, DRIVE, Persian and CASIA V2 datasets. The results show that the proposed method outperforms the Canny method and other adaptive methods.