Intelligent Image Segmentation and Synthesis

DOI

10.2991/mmme-16.2016.70How to use a DOI?

Keywords

image segmentation; image smoothing; e-commerce

Abstract

With the rapid development of the e-commerce, shopping online has gradually become one of the most im-portant way of shopping in our life. But there are still some problems, such as size, color, quality and other is-sues. We can always find some comments that some clothes have color difference. The consumers shopping online can only see the picture from the Internet, without experiencing the goods in the picture by themselves. So many people often find the goods are different from their expectation after accepting them, which results in returning and other problems. To solve this problem, this study uses the MATLAB language and the knowledge of image segmentation, smoothing and the adjustment of brightness and contrast to design of the application. The function of this application is to automatically identify the central object in the original image, using segmentation method based on the edge to segment the image and cover the segmented objects into the new background. When the image is merged, the edge of the image is smoothed by low-pass filtering to ad-just the brightness and the exposure of the image to achieve the best results. So the image can reflect the ef-fect of the object under different scenarios, which can make consumers see the tie-in result with the goods. The application can be used in virtual try-on, which can combine various kinds of dress online with their own photos. It gives consumers more intuitive understanding of the goods before buying them, so that shopping will get more scientific.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qizhi Xu
PY  - 2016/10
DA  - 2016/10
TI  - Intelligent Image Segmentation and Synthesis
BT  - Proceedings of the 2016 4th International Conference on Mechanical Materials and Manufacturing Engineering
PB  - Atlantis Press
SP  - 309
EP  - 313
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmme-16.2016.70
DO  - 10.2991/mmme-16.2016.70
ID  - Xu2016/10
ER  -