###
计算机系统应用:2020,29(4):254-259
本文二维码信息
码上扫一扫!
级联层叠金字塔网络模型的服装关键点检测
李维乾1,2,3, 张紫云1,2,3, 王海4, 张艺1,2,3
(1.西安工程大学 计算机科学学院, 西安 710048;2.陕西省服装设计智能化重点实验室, 西安 710048;3.新型网络智能信息服务国家地方联合工程研究中心, 西安 710048;4.西北大学 信息科学与技术学院, 西安 710127)
Cascaded Stacked Pyramid Network Model for Key Point Detection of Clothing
(1.School of Computer Science, Xi'an Polytechnic University, Xi'an 710048, China;2.Shaanxi Key Laboratory of Clothing Intelligence, Xi'an 710048, China;3.State and Local Joint Engineering Research Center for Advanced Networking and Intelligent Information Services, Xi'an 710048, China;4.School of Information Science and Technology, Northwest University, Xi'an 710127, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 155次   下载 187
投稿时间:2019-09-07    修订日期:2019-10-08
中文摘要: 服装关键点的检测对服饰分类、推荐和检索效果具有重要的作用,然而实际服装数据库中存在大量形变及背景复杂的服饰图片,导致现有服装分类模型的识别率和服装推荐、检索的效果较差.为此,本文提出了一种级联层叠金字塔网络模型CSPN (Cascaded Stacked Pyramid Network),将目标检测方法与回归方法相结合,首先采用Faster R-CNN结构对服装目标区域进行识别,然后基于ResNet-101结构生成的多层级特征图,构建级联金字塔网络,融合服饰图像的多尺度高低层信息,解决图片形变及复杂背景下服装关键点识别准确度不高等问题.实验结果表明,CSPN模型在DeepFashion数据集上较其他三种模型对服装关键点具有较高识别度.
Abstract:The detection of key points of clothing plays an important role in the classification, recommendation, and retrieval of clothing. However, there are a large number of clothing pictures with deformation and complex background in the clothing database, which leads to the poor recognition rate of the existing clothing classification model and the effect of clothing recommendation and retrieval. For this reason, this study proposes a model called Cascaded Stacked Pyramid Network (CSPN) which combines the target detection method with the regression method. First, the costume target area is identified by the Faster R-CNN, and then the Cascaded Pyramid Network (CPN) is constructed based on the multi-level feature map generated by ResNet-101 structure. This model integrates the multi-scale and different-layer clothing image feature, and solves low image recognition accuracy about clothing key points of the deformation and complex background image. Experimental results show that the CSPN model has higher recognition rate on the key points of clothing than the other three models in the DeepFashion dataset.
文章编号:7376     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61572401,61672426,61701400);西安工程大学博士科研启动基金(BS1330)
引用文本:
李维乾,张紫云,王海,张艺.级联层叠金字塔网络模型的服装关键点检测.计算机系统应用,2020,29(4):254-259
LI Wei-Qian,ZHANG Zi-Yun,WANG Hai,ZHANG Yi.Cascaded Stacked Pyramid Network Model for Key Point Detection of Clothing.COMPUTER SYSTEMS APPLICATIONS,2020,29(4):254-259

用微信扫一扫

用微信扫一扫