A shape reconstructability measure of object part importance with applications to object detection and localization

DOI10.1007/S11263-014-0705-9MaRDI QIDQ903522zbMATH OpenOpenAlexFDO

Authors Ge Guo, Tingting Jiang, Alan Yuille, Fang Fang, Wen Gao, Yizhou Wang

Publication date 6 January 2016

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11263-014-0705-9

zbMATH Keywords

shape reconstructionobject recognition and detectionpart importanceshape part

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Recommendations

• Inference and learning with hierarchical shape models
• Object detection by global contour shape
• Detection and recognition of contour parts based on shape similarity
• Partially occluded object recognition using statistical models
• The largest convex patches: A boundary-based method for obtaining object parts

Cites work

• A new point matching algorithm for non-rigid registration
• An introduction to support vector machines and other kernel-based learning methods.
• Computer Vision - ECCV 2004
• Computer Vision - ECCV 2004
• Euler spiral for shape completion
• Shape-based object detection via boundary structure segmentation

Cited in

(1)

• Local reliability weighting explains identification of partially masked objects in natural images

Describes a project that uses

Uses Software

• PASCAL VOC

This page was built for publication: A shape reconstructability measure of object part importance with applications to object detection and localization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q903522)