A Subblock Partition Of Multi-Layer Pattern Based Image Classification Approach

摘要：

　　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.

作者: LV Xuan MA Zezhong LIU Qing

作者单位: Chongqing Land Resources Housing Surveying and Planning Institute;School of Remote Sensing and Infor Chongqing Land Resources Housing Surveying and Planning Institute Huangshandadao Road No.64, yubei, Chongqing industrial& commercial school baisha, jiangjin, Chongqing, China

会议类型: 国际会议

会议名称: 2018 International Symposium on Water System Operations(ISWRSO 2018)(2018年水资源系统及调度国际研讨会)

会议地点: 北京

会议语种:英文

页码: 1-7

在线出版日期: 2018-10-12（万方平台首次上网日期，不代表论文的发表时间）