MATEC Web Conf.
Volume 246, 20182018 International Symposium on Water System Operations (ISWSO 2018)
|Number of page(s)||7|
|Section||Parallel Session II: Water System Technology|
|Published online||07 December 2018|
A Subblock Partition Of Multi-Layer Pattern Based Image Classification Approach
1 Chongqing Land Resources Housing Surveying and Planning Institute
2 School of Remote Sensing and Information Engineering, Wuhan University, Huangshandadao Road No.64, yubei, Chongqing, China +86 13668093020 Chongqing Land Resources Housing Surveying and Planning Institute Huangshandadao Road No.64, yubei, Chongqing, China, +86 13896829668, Chongqing industrial& commercial school baisha, jiangjin, Chongqing, China, +86 13618381908
Since traditional partition approach may construct very different image representation because of the changed locations of objects in the same image, a subblock partition of multi-layer pattern method for image representation is proposed. The saliency windows straddled by superpixels are utilized to partition the image into multi-layer pattern subblocks. Then all the subblocks are combined to a three order tensor. Comparing to the results of image classification item of Pascal Voc 2007 Challenge，it indicates that the proposed representation method is robust to the varied object locations and achieves better performance than other approaches.
Computing methodologies➝Computer vision • Computing methodologies➝ Machine learning
© The Authors, published by EDP Sciences, 2018
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.