Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model

Haruhiro Fujita; Masatoshi Itagaki; Yew Kwang Hooi; Kenta Ichikawa; Kazutaka Kawano; Ryo Yamamoto

Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model

Computer Vision and Pattern Recognition 2020-10-28 v1

Authors: Haruhiro Fujita , Masatoshi Itagaki , Yew Kwang Hooi , Kenta Ichikawa , Kazutaka Kawano , Ryo Yamamoto

Abstract

Detection performances on bounding box and segmentation mask outputs of Mask R-CNN models are evaluated. There are significant differences in detection performances of bounding boxes and segmentation masks, where the former is constantly superior to the latter. Harmonic values of precisions and recalls of linear cracks, joints, fillings, and shadows are significantly lower in segmentation masks than bounding boxes. Other classes showed similar harmonic values. Discussions are made on different performances of detection metrics of bounding boxes and segmentation masks focusing on detection algorithms of both detectors.

Keywords

object detection instance segmentation mask r-cnn bounding box segmentation mask detection algorithm

Cite

@article{arxiv.2010.13783,
  title  = {Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model},
  author = {Haruhiro Fujita and Masatoshi Itagaki and Yew Kwang Hooi and Kenta Ichikawa and Kazutaka Kawano and Ryo Yamamoto},
  journal= {arXiv preprint arXiv:2010.13783},
  year   = {2020}
}

Comments

8 pages, 9 figures, 4 tables. arXiv admin note: text overlap with arXiv:2010.11464

Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model

Abstract

Keywords

Cite

Comments

Related papers