人脸检测中一种简单有效的合并重合窗口方法 |
| |
引用本文: | 闫胜业,山世光,陈熙霖. 人脸检测中一种简单有效的合并重合窗口方法[J]. 数字社区&智能家居, 2009, 0(19) |
| |
作者姓名: | 闫胜业 山世光 陈熙霖 |
| |
作者单位: | 中国科学院计算技术研究所数字媒体中心;中国科学院研究生院; |
| |
基金项目: | 国家自然科学基金(60332010&60473043)) |
| |
摘 要: | 在当前主流的基于统计学习和穷举搜索窗口的人脸检测技术中,使用分类器对每个候选窗口进行分类判决之后,会留下多个重合的人脸候选窗口。为了将多个重合窗口合并为一个,提出一种使用矩形环对一个真实人脸的多个具有重合性质的分类器响应候选窗口进行重合范围限定,并合并多个窗口的策略。提出的矩形环合并窗框方法具有简单、易编程的特点,实验表明了该文方法的有效性。
|
关 键 词: | 人脸检测 学习 重合 子窗口 穷举 搜索 |
A Simple and Efficient Method to Remove Overlaps for Face Detection |
| |
Abstract: | In the most popular face detection methods which are based on statistical learning and brute-in-force search,after the search of each candidate sub-window,the surviving sub-windows for one real face are always overlapped each other.A rectangle loop is proposed to limit the overlap extent and used for removing multiple overlapped sub-windows.The proposed method is simple and easy for pro-gramming.The experimental results show its efficiency. |
| |
Keywords: | face detection learning overlap sub-window brute-in-force search |
本文献已被 CNKI 等数据库收录! |