Deep Learning: A Study of Pattern Recognition for Personalized Clothing

Abstract

Objectives: This article aims to enhance the efficiency of clothing recognition and retrieval by implementing deep learning algorithms for personalized clothing pattern recognition. Methods: Based on the you only look once version 4 (YOLOv4) algorithm in deep learning, the CSPDarknet-53 in the original algorithm was replaced by GhostNet, and the original Leaky ReLU activation function was replaced by FMish. Then, an improved YOLOv4 algorithm was obtained. Experiments were carried out on the personalized clothing pattern set, the Fashion Mnist dataset, and the DeepFashion dataset to compare and analyze different algorithms. Findings: When replacing CSPDarknet-53 with GhostNet and the Leaky ReLU activation function with FMish, the optimized YOLOv4 algorithm performed significantly better, verifying the reliability of the YOLOv4 improvement. The optimized algorithm achieved an F1 value of 94.22% and a mAP of 95.41% on different datasets, and 39.51% and 49.56% on the DeepFashion dataset, respectively, outperforming other deep learning methods such as the faster-recurrent convolutional neural network. Furthermore, the floating-point operations per second of the optimized YOLOv4 algorithm were 8.72 G, showing a reduction of 49.71% compared to the traditional algorithm. This suggested that it had low complexity and calculation amounts. Novelty: The optimized YOLOv4 algorithm performs excellently in recognizing personalized clothing patterns, which can provide a new and reliable approach for recognition and retrieval in the field of clothing. Doi: 10.28991/HIJ-2023-04-03-03 Full Text: PDF