Point-context descriptor based region search for logo recognition
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Beyond bounding-boxes: learning object shape by model-driven grouping
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
On the use of regions for semantic image segmentation
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Arbitrary-Shape object localization using adaptive image grids
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Object class detection: A survey
ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
We propose a branch-and-cut strategy for efficient region-based object detection. Given an oversegmented image, our method determines the subset of spatially contiguous regions whose collective features will maximize a classifier's score. We formulate the objective as an instance of the prize-collecting Steiner tree problem, and show that for a family of additive classifiers this enables fast search for the optimal object region via a branch-and-cut algorithm. Unlike existing branch-and-bounddetection methods designed for bounding boxes, our approach allows scoring of irregular shapes - which is especially critical for objects that do not conform to a rectangular window. We provide results on three challenging object detection datasets, and demonstrate the advantage of rapidly seeking best-scoring regions rather than subwindow rectangles.