Translator Disclaimer
22 March 2019 A performance improvement of Mask R-CNN using region proposal expansion
Author Affiliations +
Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019; 1104929 (2019) https://doi.org/10.1117/12.2521383
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore
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.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Naoki Degawa, Xin Lu, and Akio Kimura "A performance improvement of Mask R-CNN using region proposal expansion", Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 1104929 (22 March 2019); https://doi.org/10.1117/12.2521383
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
Back to Top