Author(s): Xuan Lv; Zezhong Ma; Qing Liu

Linked Author(s):

Keywords: No keywords

Abstract: 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. CCS Concepts Computing methodologies➝Computer vision • Computing methodologies➝ Machine learning

DOI: https://doi.org/10.1051/matecconf/201824603043

Year: 2018