Automatic Cloth Pattern and Color Recognition for Visually Impaired People Using SVM Algorithm

Abstract

This paper highlights the importance of human clothing, especially for visually impaired people. Choosing clothes with different colors is a challenging task for color blind people. Automatic clothing pattern recognition can bring the much needed independence in their lives. But, this is also a challenging research problem due to rotation, scaling, illumination, and especially large intra-class pattern variations. In this paper, we propose a camera based system that recognizes clothing patterns in four main categories (plaid, striped, pattern-less, and irregular) and identifies 16 clothing colors using the support vector machine algorithm. The features and texture of an image can be extracted by the three descriptors. The Radon Signature descriptor is to extract statistical properties, the wavelet subbands are used to extract global features of clothing patterns. This gets combined with local features that are obtained from scale invariance feature transform to recognize complex clothing patterns. To evaluate the effectiveness of the proposed approach, we used the CCNY Clothing Pattern dataset. The proposed method provides an effective method for visually impaired people that they can identify the pattern and respective colors easily without any help.