系统仿真学报 ›› 2015, Vol. 27 ›› Issue (10): 2483-2488.

• 虚拟现实与可视化 • 上一篇    下一篇

用于手势识别系统的肤色图像后处理方法研究

王任大1, 尹勇1, 邢胜伟2   

  1. 1.大连海事大学航海动态仿真和控制实验室,大连 116026;
    2.大连海事大学航海学院,大连 116026
  • 收稿日期:2015-06-14 修回日期:2015-07-30 出版日期:2015-10-08 发布日期:2020-08-07
  • 作者简介:王任大(1984-),男,辽宁沈阳人,博士,讲师,研究方向为航海动态仿真与控制;尹勇(1969-),男,湖北十堰人,博士,教授,博导,研究方向为航海动态仿真与控制;邢胜伟(1982-),男,河北邯郸人,博士,讲师,研究方向为智能运输系统的理论与技术。
  • 基金资助:
    863课题(2015AA016404)

Research on Skin Color Image Post-processing Methods for Gesture Recognition System

Wang Renda1, Yin Yong1, Xing Shengwei2   

  1. 1. Key Laboratory of Marine Dynamic Simulation & Control for Ministry of Communications, Dalian Maritime University, Dalian 116026, China;
    2. Navigation College, Dalian Maritime University, Dalian 116026, China
  • Received:2015-06-14 Revised:2015-07-30 Online:2015-10-08 Published:2020-08-07

摘要: 提出了一种适用于基于视觉的手势识别系统的肤色区域图像后处理方法。针对手势识别系统中人脸与人手经常同时在图像帧中出现的问题,对基于Haar-like模板的AdaBoost人脸检测器的训练流程和组合方案进行了研究,并提出了一种融合肤色信息的人脸区域快速剔除方法。针对肤色区域图像中的噪声干扰问题,提出了椒盐噪声抑制和类肤色区域剔除方法。测试结果表明,上述方法能够在基本保持检测率不变的前提下大幅度提升人脸检测速度,且能够使后续手姿识别步骤的识别正确率得到显著的提升。

关键词: 手势识别, 皮肤检测, 人脸检测, 噪声抑制

Abstract: Skin color region image post-processing methods suitable for gesture recognition system based on computer vision was proposed. To solve the problem of face and hand often occur simultaneously in the image frame, the training process and grouping strategy of AdaBoost face detector based on Haar-like template were studied, and a rapid culling method of face region based on fusion of color information was proposed. To reduce the influence of noise in skin color region image, impulse noise suppression and skin-like region rejection was proposed. The test results have shown that the proposed methods can greatly speed up the face detection process under the premise of detection accuracy almost remaining unchanged, and significantly improve the accuracy of subsequent hand posture recognition steps.

Key words: gesture recognition, skin detection, face detection, noise suppression

中图分类号: