Garments Texture Design Class Identification Using Deep Convolutional Neural Network

Abstract

Automatic garments design class identification 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 methods, based on Hand-Engineered feature coding exist for identifying garments design classes. But, most of the time, those methods do not help to achieve better results. 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 (images, sound, and text) more accurately. In this paper, we have applied deep CNN for identifying garments design classes. To evaluate the performances, we used two well-known CNN models AlexNet and VGGNet on two different datasets. We also propose a new CNN model based on AlexNet and found better results than existing state-of-the-art by a significant margin.

Personalized Clothing Prediction Algorithm Based on Multi-modal Feature Fusion

“…This study proposes a CNN model for identifying categories of clothing design, enhancing classification accuracy by effectively learning image attributes [5]. The model surpasses the performance of traditional hand-designed feature coding methods and existing CNN models in category recognition of clothing design.…”

Efficient Object Detection and Intelligent Information Display Using YOLOv4-Tiny

“…Target detection methods that leverage deep learning have greatly advanced with the introduction of models such as recursive convolutional neural networks (R-CNNs) [1][2], Fast R-CNN [3], Faster R-CNN [4], Mask R-CNN [5], single shot detector (SSD) [6], and you only look once (YOLO) [7]. Mask R-CNN proposes a region of interest (ROI) align technology to address the problem that the bounding box positioning of Faster R-CNN's RoI pooling is not accurate enough.…”