| Title: | OS4-2 Error Backpropagation Neural Network Based Image Identification for a Foot Massage Machine and Its Mechanism Design |
|---|---|
| Publication: | ICAROB2023 |
| Volume: | 28 |
| Pages: | 107-111 |
| ISSN: | 2188-7829 |
| DOI: | 10.5954/ICAROB.2023.OS4-2 |
| Author(s): | Chun-Chieh Wang |
| Publication Date: | February 9, 2023 |
| Keywords: | Error backpropagation neural network (EBNN), Foot massage machines, Image identification |
| Abstract: | In the past twenty years, many companies have developed different styles of foot massage machines. At present, the common massage products on the market include roller type and pressing type. However, it is very difficult to accurately stimulate all acupuncture points for different sizes of feet. Besides, the massage roller cannot be controlled independently. Therefore, a novel computer vision technology is proposed to identify the foot acupuncture points by error backpropagation neural network (EBNN) in this paper. First, we use cameras to capture the sole of users' soles and execute image preprocessing procedures to segment the region of interest (ROI) of soles. We map foot acupuncture points to foot images to obtain reference massage positions. Second, the YCbCr color space is used to separate the brightness to complete the segmentation of the foot image in the skin detection. Moreover, EBNN is used to train users' soles-image sets to improve the success rate of image segmentation. Finally, to improve the rate of image recognition and user convenience, a foot massage machine was redesigned. Experimental results validate the superiority and practicality of the proposed image identification method for foot massage machines. |
| PDF File: | https://alife-robotics.co.jp/members2023/icarob/data/html/data/OS/OS4/OS4-2.pdf |
| Copyright: | © The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/ |
(c)2008 Copyright The Regents of ALife Robotics Corporation Ltd. All Rights Reserved.