###
计算机系统应用:2018,27(10):226-231
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于迁移学习的商品图像检测方法
胡正委, 朱明
(中国科学技术大学 信息科学技术学院, 合肥 230031)
Product Image Detection Based on Transfer Learning
HU Zheng-Wei, ZHU Ming
(School of Information Science and Technology, University of Science and Technology of China, Hefei 230031, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 69次   下载 77
投稿时间:2018-03-15    修订日期:2018-04-18
中文摘要: 近年来,对象识别方法被应用到多个领域.如人脸检测,车辆检测.然而模型训练所需要的边框标定需要很大的工作量.本文通过基于迁移学习的方法,将物体检测任务迁移到商品检测,且不需要边框标定.本文在分类层和边框回归层之间建立关系层,来学习两种任务之间的关联.本文建立了一个商品数据集,并提出了一种深度学习训练方法,解决了可旋转物体的检测问题.基于Faster RCNN框架,本文提出一种候选选择方法,可以在边框标定情况下训练商品分类.本文提出的商品检测方法不需要边框标定,而且很容易训练并应用到其它数据集.
Abstract:In recent years, object detection is transferred to other fields, for example, face and vehicle detection. However, the bounding-box labeling is a huge resources cost work. This study solves the problem that transfer object detection task to other domain dataset without bounding-box label. A relationship layer is built to learn the relationship between classification and regression task. In addition, we construct a product dataset, on which rotatable object detection is solved using our training method. A proposal selecting method is proposed for training classification based on faster RCNN framework without bounding-box label. We propose a object detection method without bounding-box annotation. The method is easy to transfer to other datasets and training.
文章编号:     中图分类号:    文献标志码:
基金项目:中科院先导专项课题(XDA06011203)
引用文本:
胡正委,朱明.基于迁移学习的商品图像检测方法.计算机系统应用,2018,27(10):226-231
HU Zheng-Wei,ZHU Ming.Product Image Detection Based on Transfer Learning.COMPUTER SYSTEMS APPLICATIONS,2018,27(10):226-231

用微信扫一扫

用微信扫一扫