基于深度学习的服装图像语义分析与检索推荐  

Image semantic analysis and retrieval recommendation for clothing based on deep learning

作　　者：徐慧 白美丽 万韬阮[2] 薛涛 汤汶 XU Hui;BAI Meili;WAN Taoruan;XUE Tao;TANG Wen(School of Computer Science/Shaanxi Key Laboratory of Clothing Intelligence,Xi’an Polytechnic University,Xi’an 710048,China;Faculty of Engineering and Informatics,University of Bradford,Bradford,BD71DP,United Kingdom;Faculty of Science and Technology,Bournemouth University,Poole BH125BB,United Kingdom)

机构地区：[1]西安工程大学计算机科学学院/陕西省服装设计智能化重点实验室,陕西西安710048 [2]布拉德福德大学工程与信息学院,英国布拉德福德BD71DP [3]伯恩茅斯大学科学与工程技术学院,英国伯恩茅斯BH125BB

出　　处：《纺织高校基础科学学报》2020年第3期64-72,共9页Basic Sciences Journal of Textile Universities

基　　金：陕西省技术创新引导专项计划项目(2020CGXNG-012)。

摘　　要：针对服装检测推荐方法中的服装图像分割算法分割精度不高且存在多尺度特征融合不佳的问题,提出一种基于注意力机制和多尺度特征融合的深度卷积网络服装特征提取分析检索与推荐方法。该方法以图像语义分割算法为基础,从服装图像中提取高级语义信息,通过哈希函数对提取的特征进行编码,并引入ASPP对图像进行多尺度特征提取,然后使用注意力模型对提取到的特征进行融合并构建索引库,最终实现语义相似性服装推荐的功能。实验表明:本方法可以有效提高分割准确度,解决多尺度特征提取的问题,能够成功提取图像中的高层次语义特征,具有较高的分割准确率,在很大程度上提高了服装相似性语义推荐的效率。Aiming at the problems of low segmentation accuracy and poor multi-scale feature fusion of clothing image segmentation algorithm in clothing detection and recommendation method,a deep convolution network clothing feature extraction analysis retrieval and recommendation method based on attention mechanism and multi-scale feature fusion is proposed.Based on the image semantic segmentation algorithm,this method extracts high-level semantic information from clothing images,encodes the extracted features by hash function,and extracts multi-scale features of the image by introducing ASPP,and then merges the extracted features with attention model to build an index database,and finally the function of clothing recommendation with semantic similarity is realized.The experimental results show that this method can effectively improve the segmentation accuracy,solve the problem of multi-scale feature extraction,successfully extract the high-level semantic features in the image,with high segmentation accuracy,and greatly improve the efficiency of semantic recommendation of clothing similarity.

关 键 词：深度卷积神经网络 多尺度特征融合 服装语义分割 服装多尺度特征提取 服装检索 服装推荐 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]