Year: 2015
Journal of Fiber Bioengineering and Informatics, Vol. 8 (2015), Iss. 3 : pp. 501–511
Abstract
Color is one of the most powerful and important types of visual information. Color information of images plays an important role in human body contour extraction process. In most of the current human body contour extraction systems, color images are converted into gray images first and then human body contours are extracted from these gray images. In this process, a large mount of color information is lost and the extraction results are inaccurate. Besides, strict requirements are put forward about objective conditions when taking pictures in these systems, such as background, dress, pixel of cameras, light and so on. In order to solve these problems, HSV color model in line with human visual habits was adopted to extract human body contours in this paper. Human body contours were directly extracted from color images by analyzing and changing H, S and V values. MATLAB software was used to write a human body contour extraction program. Results of experiments show that the accuracy of extraction is improved. The requirements about the background, dress, pixel, light and other factors are reduced through adopting HSV color space. Automatic human body contour extraction under complex conditions is realized in this paper, which can lay a foundation for the development of remote automatic human body measurement systems. Research results of this paper provide a reliable basis for the development of apparel electronic-commerce and personalized customization.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.3993/jfbim00148
Journal of Fiber Bioengineering and Informatics, Vol. 8 (2015), Iss. 3 : pp. 501–511
Published online: 2015-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 11
Keywords: Color Information