LNCS Homepage
ContentsAuthor IndexSearch

A Human vs. Machine Challenge in Fashion Color Classification

Costantino Grana, Daniele Borghesani, and Rita Cucchiara

Università degli Studi di Modena e Reggio Emilia, Facoltà di Ingegneria “Enzo Ferrari”, Italy

Abstract. For this demo, we present a set of stark applications designed to evaluate the performance of a color similarity retrieval system against human operators performance in the same tasks. The proposed series of tests give some interesting insights about the perception of color classes and the reliability of manual annotation in the fashion context.

Keywords: Human-Machine Interaction, Image Retrieval, Color Analysis, Evaluation

LNCS 7585, p. 631 ff.

Full article in PDF | BibTeX


lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012