A CNN Based Approach for Garments Texture Design Classification

Advances in Technology Innovation

Md. Nurul Ahad Tawhid¹  Emon Kumar Dey¹  B. M. Mainul Hossain¹  S.M. Sofiqul Islam¹ 

[1] Institute of Information Technology, University of Dhaka, Bangladesh;

关键词: CNN;    Deep Learning;    AlexNet;    VGGNet;    Texture De-scriptor;    Garment Categories;    Garment Trend Identifica-tion;    Design Classification for Garments;   

DOI  :  

来源: DOAJ

【 摘 要 】

Identifying garments texture design automatically for recommending the fashion trends is important nowadays because of the rapid growth of online shopping. By learning the properties of images efficiently, a machine can give better accuracy of classification. Several Hand-Engineered feature coding exists for identifying garments design classes. Recently, Deep Convolutional Neural Networks (CNNs) have shown better performances for different object recognition. Deep CNN uses multiple levels of representation and abstraction that helps a machine to understand the types of data more accurately. In this paper, a CNN model for identifying garments design classes has been proposed. Experimental results on two different datasets show better results than existing two well-known CNN models (AlexNet and VGGNet) and some state-of-the-art Hand-Engineered feature extraction methods.

【 授权许可】

Unknown