publication . Other literature type . Conference object . 2008

Beyond sliding windows: Object localization by efficient subwindow search

Christoph H. Lampert; Matthew B. Blaschko; Thomas Hofmann;
  • Published: 01 Jun 2008
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch-and-bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages. It converges to a globally optimal solution typically in sublinear time. We show how our method is ap...
free text keywords: Speedup, Implicit Shape Model, Sliding window protocol, Computer vision, Contextual image classification, Artificial intelligence, business.industry, business, Classifier (linguistics), Computer science, Pattern recognition, Object detection, Support vector machine, Cognitive neuroscience of visual object recognition
Related Organizations
Download fromView all 3 versions
Conference object . 2008
Provider: MPG.PuRe
Other literature type . 2008
Provider: Datacite
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue