您的位置:首页 > 运维架构

OpenCV学习——眼部识别算法实现

2013-10-31 15:41 381 查看
http://blog.csdn.net/gnuhpc/article/details/4362233

论文下载地址:
http://www.cs.bu.edu/techreports/pdf/2005-012-blink-detection.pdf
程序介绍:

This system is the enhancement of my previous Eye Tracking system, where this system

automatically locate the user's eye by detecting eye blinks. Motion analysis

techniques are used in this stage, followed by online creation of the open eye template.

The open eye template is used to locate the user's eye in the subsequent frames with

template matching. Blink detection is performed using motion analysis techniques.

Since the operation requires extensive amount of computation, the search region is

restricted in a small search window around the user's eye. This method will drastically

reduces the computation needed thus making the system running smoothly in real time.

Author: Nashruddin Amin <me@nashruddin.com>

License: GPL

Website: http://nashruddin.com
See the complete tutorial at:
http://nashruddin.com/Real_Time_Eye_Tracking_and_Blink_Detection
Requirement

===========

This package requires the OpenCV library, freely available at:
http://sourceforge.net/projects/opencvlibrary
Compiling

=========

Compile as usual. See the OpenCV wiki (http://opencv.willowgarage.com) for info on how

to use various IDE with OpenCV.

Usage

=====

1. Run the program.

2. Blink your eyes. You will see 2 rectangles. The green rectangle labels

the object being tracked (your eye) and the red rectangle is the search window.

3. Move your head to see the eye tracking.

4. If you blink, the program will display the text 'blink!' in the window.

5. Press 'r' to repeat eye detection.

6. Press 'q' to quit.

Contact the author

==================

Feel free to contact me@nashruddin.com.

源程序:
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: