Eye Detection using Helmholtz Principle

Ahmed Et Al

doi:10.21123/bsj.2019.16.4(suppl.).1087

Abstract

Eye Detection is used in many applications like pattern recognition, biometric, surveillance system and many other systems. In this paper, a new method is presented to detect and extract the overall shape of one eye from image depending on two principles Helmholtz & Gestalt. According to the principle of perception by Helmholz, any observed geometric shape is perceptually "meaningful" if its repetition number is very small in image with random distribution. To achieve this goal, Gestalt Principle states that humans see things either through grouping its similar elements or recognize patterns. In general, according to Gestalt Principle, humans see things through general description of these things. This paper utilizes these two principles to recognize and extract eye part from image. Java programming language and OpenCV library for image processing are used for this purpose. Good results are obtained from this proposed method, where 88.89% was obtained as a detection rate taking into account that the average execution time is about 0.23 in seconds.

Highlights

Eye detection is an important step in various human-computer interaction applications [1]
Eye detection is an essential step in many applications like: face detection/recognition, face expression analysis, gaze estimation, human interactions, pose estimation, biometric systems, character animation and surveillance systems [2, 3]
Eye detection methods can be divided into four major categories, Shape-based, Appearance-based, structural-based, and Context-based approaches

Summary

Introduction

Eye detection is an important step in various human-computer interaction applications [1]. This method is based on two essential steps: in the first step, the skin is detected, the image is binarily divided into skin and non-skin regions, blurring and morphological operations applied to eliminate noise, and contours are extracted.

Results

Conclusion