Research on the Image Semantic Understanding Pattern based on the Sparse Coding and Wavelet Theory

DOI

10.2991/emcs-17.2017.229How to use a DOI?

Keywords

Image Processing; Semantic Understanding; Sparse Coding; Wavelet Theory

Abstract

In this paper, we conduct research on the image semantic understanding pattern based on the sparse coding and wavelet theory. From the perspective of image understanding, according to the different weights of spatial information to give false points pixels, make the false points of pixels in different positions have different importance. Was introduced to the weighted formula of relative distance, foreground and background search distance, in order to obtain evaluation algorithm for image segmentation is scaling invariance conclusion in order to overcome large ratio of segmentation quality evaluation distortion phenomenon, put forward a kind of distortion of punishment, improve the effectiveness of the evaluation algorithm and global. Through applying the algorithm into primary application scenarios, we could test the effectiveness and robustness.

Copyright

© 2017, 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  - Wenzhun Huang
AU  - Baohui Zhao
PY  - 2017/03
DA  - 2017/03
TI  - Research on the Image Semantic Understanding Pattern based on the Sparse Coding and Wavelet Theory
BT  - Proceedings of the 2017 7th International Conference on Education, Management, Computer and Society (EMCS 2017)
PB  - Atlantis Press
SP  - 1193
EP  - 1197
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcs-17.2017.229
DO  - 10.2991/emcs-17.2017.229
ID  - Huang2017/03
ER  -