Communications of the ACM

Research highlights

Using the Forest to See the Trees: Exploiting Context For Visual Object Detection and Localization

By A. Torralba, K. P. Murphy, W. T. Freeman
Communications of the ACM, March 2010, Vol. 53 No. 3, Pages 107-114
10.1145/1666420.1666446
Comments

Recognizing objects in images is an active area of research in computer vision. However, most of the algorithms for detecting objects perform an exhaustive search across all locations and scales in the image comparing local image regions with an object model. That approach ignores the semantic structure of scenes and tries to solve the recognition problem by brute force.

The full text of this article is premium content

---

No entries found