New software and hardware technologies, they are becoming increasingly incorporated into our daily lives. Digital images are widely used to access various places. For example with fingerprints, company employees register their arrival/departure, digital cameras can recognize: people, license plates, crops, etc. These applications are now a reality thanks to advances in computer vision, one of the branches of artificial intelligence that has experienced significant growth in recent years. It studies how to automatically process, analyze, interpret, and recognize images. Many research results on digital image processing, have demonstrated the benefits of color spaces for human skin recognition. In this research, skin recognition is performed using the following color spaces: RGB, I1I2I3, YCrCb, HSI y TSL; from which a combination of the channels of each color space is made and the optimal color space for human skin recognition is obtained; as well as the most appropriate combination of channels. Finally, a set of images is shown with the recognition percentages, the color space used and the channel combinations used. The RA-PIEL (Automatic Skin Recognition) software was developed, which is an image analysis application intended for the analysis of images of human beings for the purpose of recognizing human skin.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Human Skin Recognition Comparing Five Color Spaces to Choose the Optimal One, Implementing Computer Vision Techniques

  • José Luis Hernández-Hernández,
  • Mercedes Hernández-De-La-Cruz,
  • Yanet Evangelista Alcocer,
  • María Zavala Hurtado,
  • Sergio Ricardo Zagal Barrera,
  • Mario Hernández-Hernández

摘要

New software and hardware technologies, they are becoming increasingly incorporated into our daily lives. Digital images are widely used to access various places. For example with fingerprints, company employees register their arrival/departure, digital cameras can recognize: people, license plates, crops, etc. These applications are now a reality thanks to advances in computer vision, one of the branches of artificial intelligence that has experienced significant growth in recent years. It studies how to automatically process, analyze, interpret, and recognize images. Many research results on digital image processing, have demonstrated the benefits of color spaces for human skin recognition. In this research, skin recognition is performed using the following color spaces: RGB, I1I2I3, YCrCb, HSI y TSL; from which a combination of the channels of each color space is made and the optimal color space for human skin recognition is obtained; as well as the most appropriate combination of channels. Finally, a set of images is shown with the recognition percentages, the color space used and the channel combinations used. The RA-PIEL (Automatic Skin Recognition) software was developed, which is an image analysis application intended for the analysis of images of human beings for the purpose of recognizing human skin.