English

Delegating Custom Object Detection Tasks to a Universal Classification System

Computer Vision and Pattern Recognition 2014-01-24 v1

Abstract

In this paper, a concept of multipurpose object detection system, recently introduced in our previous work, is clarified. The business aspect of this method is transformation of a classifier into an object detector/locator via an image grid. This is a universal framework for locating objects of interest through classification. The framework standardizes and simplifies implementation of custom systems by doing only a custom analysis of the classification results on the image grid.

Keywords

Cite

@article{arxiv.1401.6126,
  title  = {Delegating Custom Object Detection Tasks to a Universal Classification System},
  author = {Andrew Gleibman},
  journal= {arXiv preprint arXiv:1401.6126},
  year   = {2014}
}

Comments

3 pages, 2 figures, 6 refs. arXiv admin note: substantial text overlap with arXiv:1310.7170

R2 v1 2026-06-22T02:53:32.306Z