计算机与数字工程2019，Vol.47Issue(10)：2556-2560,5.DOI:10.3969/j.issn.1672-9722.2019.10.035
基于图案的多层次跨场景服装检索∗
Pattern-based Multi-level Cross-scene Clothing Retrieval
摘要
Abstract
In the cross-scene clothing image retrieval,the current "searching pattern by pattern" mainly relies on clothing re?gions global feature extraction of garment styles,resulting in low retrieval accuracy. In view of this situation,this paper proposes a pattern-based multi-level cross-scene garment retrieval method. Based on the feature matching in the garment area,the matching degree of the regional patterns in the interior of the garment is taken as the measure of the retrieval result,using the multi-level gar?ment feature description to match the search. In addition,the triplet loss function is used to measure learning,and inputting the im?ages under different background environments into the training network as a positive sample can improve the anti-interference abili?ty of the network model for cross-scene garment retrieving. The experimental results show that the addition of pattern region match?ing and the use of triplet loss function can effectively enhance the feature extraction ability of the network and improve the accuracy of cross-scene clothing retrieval,which is suitable for everyday clothing retrieval.关键词
服装检索/图案区域匹配度/跨场景/度量学习Key words
clothing retrieval/pattern area matching degree/cross-scene/measure learning分类
信息技术与安全科学引用本文复制引用
龚安,周静红,李华昱..基于图案的多层次跨场景服装检索∗[J].计算机与数字工程,2019,47(10):2556-2560,5.基金项目
国家油气重大专项(编号:2017ZX05013-001)资助. （编号:2017ZX05013-001）
