AbstractsComputer Science

Comparison Analysis of Color Constancy Algorithms

by Dian Liu




Institution: Högskolan i Gävle
Department:
Year: 2013
Keywords: Natural Sciences; Computer and Information Science; Computer Science; Naturvetenskap; Data- och informationsvetenskap; Datavetenskap (datalogi)
Record ID: 1327555
Full text PDF: http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-14669


Abstract

Color constancy refers to a stable psychological tendency in perception even the lighting circumstances changed and it plays an important role in many computer vision applications. In this paper, an overview of many frequently used computational color constancy algorithms is presented. Besides, existing algorithms are usually divided into statistical and physics-based and we discuss the characteristic between them, and we also evaluate two main stream hypotheses that usually made before conducting the ill-posed Lambertian Reflectance Model and discuss about their different emphases. What’s more, we perform a comparison analysis in section 3 among three of the most basic algorithms with several well-defined criteria.