papers AI Learner
The Github is limit! Click to go to the new site.

Delegating Custom Object Detection Tasks to a Universal Classification System

2013-12-19
Andrew Gleibman

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1401.6126

PDF

https://arxiv.org/pdf/1401.6126


Similar Posts

Comments