摘要
近年来,图像检测方法已经被应用于很多领域.然而,这些方法都需要在目标任务上进行大量边框标注数据的重新训练.本文基于Faster RCNN方法,并对其进行改进,解决了在小数据且无需边框标注的情况下的商品图像检测问题.首先对Faster RCNN的边框回归层进行改进,提出了一种非类别特异性的边框回归层,仅使用公开数据集训练,无需在目标数据集上进行再训练,并将其用于数据预标定与商品检测.然后结合Grabcut与非类别特异性Faster RCNN提出了一种样本增强方法,用来生成包含多个商品的训练图像;并为Faster RCNN添加了重识别层,提高了检测精度.
In recent years, object detection has been applied to many fields. However, retraining using large amount of bounding-box labeled data is needed. This study improves the Faster RCNN method and solves the problem of detecting multi-object in images using few-shot single object training data without bounding-box annotation. We propose a nonclasswise bounding-box regression layer, which is only trained by public dataset and used for product training image labeling and testing image detection. Combined with Grabcut method, a data augmentation method is proposed to generate multi-object product training image. The improved faster RCNN model is re-trained by these images. In addition,a re-identification layer is added to the Faster RCNN architecture and improves the detection performance.
作者
胡正委
朱明
HU Zheng-Wei, ZHU Ming(School of Information Science and Technology, University of Science and Technology of China, Hefei 230031, China)
出处
《计算机系统应用》
2018年第11期128-135,共8页
Computer Systems & Applications
基金
中科院先导专项课题(XDA06011203)~~