Details

Autor(en) / Beteiligte

• Lv, Xuan
• Ma, Zezhong
• Liu, Qing
• Li, H.
• Lei, X.
• Cai, S.
• Yu, Y.

Titel

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

Ist Teil von

• MATEC Web of Conferences, 2018-01, Vol.246, p.3043

Ort / Verlag

Les Ulis: EDP Sciences

Erscheinungsjahr

2018

Link zum Volltext

Quelle

EZB Free E-Journals

Beschreibungen/Notizen

• 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