Share Email Print

Proceedings Paper

A performance improvement of Mask R-CNN using region proposal expansion
Author(s): Naoki Degawa; Xin Lu; Akio Kimura
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

It is difficult for the conventional Mask Regions with Convolutional Neural Network (Mask R-CNN)1 to distinguish different objects with similar features of the shape. In this paper, we improve the object classification performance of Mask R-CNN by expanding the region proposal appropriately and using it for learning. The results of experimental evaluations using our modified 300-W dataset2 show that the mAP of our proposed method is improved from 0.631 to 0.701, compared with the original Mask R-CNN.

Paper Details

Date Published: 22 March 2019
PDF: 6 pages
Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 1104929 (22 March 2019); doi: 10.1117/12.2521383
Show Author Affiliations
Naoki Degawa, Iwate Univ. (Japan)
Xin Lu, Iwate Univ. (Japan)
Akio Kimura, Iwate Univ. (Japan)

Published in SPIE Proceedings Vol. 11049:
International Workshop on Advanced Image Technology (IWAIT) 2019
Qian Kemao; Kazuya Hayase; Phooi Yee Lau; Wen-Nung Lie; Yung-Lyul Lee; Sanun Srisuk; Lu Yu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?