Learning Image Components for Object Recognition

Research output: Contribution to journalArticlepeer-review

70 Citations (Scopus)
38 Downloads (Pure)

Abstract

In order to perform object recognition it is necessary to learn representations of the underlying components of images. Such components correspond to objects, object-parts, or features. Non-negative matrix factorisation is a generative model that has been specifically proposed for finding such meaningful representations of image data, through the use of non-negativity constraints on the factors. This article reports on an empirical investigation of the performance of non-negative matrix factorisation algorithms. It is found that such algorithms need to impose additional constraints on the sparseness of the factors in order to successfully deal with occlusion. However, these constraints can themselves result in these algorithms failing to identify image components under certain conditions. In contrast, a recognition model ( a competitive learning neural network algorithm) reliably and accurately learns representations of elementary image features without such constraints.
Original languageEnglish
Article numberN/A
Pages (from-to)793 - 815
Number of pages23
JournalJOURNAL OF MACHINE LEARNING RESEARCH
Volume7
Issue numberN/A
Publication statusPublished - May 2006

Fingerprint

Dive into the research topics of 'Learning Image Components for Object Recognition'. Together they form a unique fingerprint.

Cite this