A Novel Method Used in Automatic Eye Localization System
Abstract:Human eyes play an important role in face analysis and they are considered the most salient and stable among all other facial features. In this paper, after analyzing the traditional gray projection methods, a new approach based on region projection function (RPF) is proposed, which taking into account the two-dimensional characteristics in the process of gray projection. Based on this algorithm, the automatic eye detection and location system is designed. Firstly, AdaBoost algorithm is used to detect the facial region, and the rough eye window can be obtained approximately. Then, the eye image is divided into several non-overlapping regions and the candidate region of pupil is obtained by horizontal projection and vertical projection. Finally, the pupil center is located precisely by boundary tracking with the use of the gray characteristics. A criterion is adopted to evaluate the accuracy of human eye location, and the algorithm is tested on the Caltech facial database and JAFFE database. By the Experiments analysis, it showed that the proposed method is working well in the eye localization system and had better performance than traditional projection methods.
Document Type: Research Article
Publication date: 2011-10-01
More about this publication?
- The growing interest and activity in the field of sensor technologies requires a forum for rapid dissemination of important results: Sensor Letters is that forum. Sensor Letters offers scientists, engineers and medical experts timely, peer-reviewed research on sensor science and technology of the highest quality. Sensor Letters publish original rapid communications, full papers and timely state-of-the-art reviews encompassing the fundamental and applied research on sensor science and technology in all fields of science, engineering, and medicine. Highest priority will be given to short communications reporting important new scientific and technological findings.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites