View and Illumination Invariant Object Classification Based on 3D Color Histogram Using Convolutional Neural Networks

Ijjina, E P and C, Krishna Mohan (2015) View and Illumination Invariant Object Classification Based on 3D Color Histogram Using Convolutional Neural Networks. In: Computer Vision - ACCV 2014 Workshops: Singapore, Singapore, November 1-2, 2014, Revised Selected Papers, Part I. Lecture Notes in Computer Science (9008). Springer International Publishing, Switzerland, pp. 316-327. ISBN 978-3-319-16628-5

Preview

Text (Author version pre-print)
w3-p5.pdf - Accepted Version
Download (341kB) | Preview

Abstract

Object classification is an important step in visual recognition and semantic analysis of visual content. In this paper, we propose a method for classification of objects that is invariant to illumination color, illumination direction and viewpoint based on 3D color histogram. A 3D color histogram of an image is represented as a 2D image, to capture the color composition while preserving the neighborhood information of color bins, to realize the necessary visual cues for classification of objects. Also, the ability of convolutional neural network (CNN) to learn invariant visual patterns is exploited for object classification. The efficacy of the proposed method is demonstrated on Amsterdam Library of Object Images (ALOI) dataset captured under various illumination conditions and angles-of-view.

[error in script]

IITH Creators: