基于Faster R-CNN改进的数粒机系统

胡安翔; 李振华

引用本文:

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 3105次下载 2055次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于Faster R-CNN改进的数粒机系统
胡安翔, 李振华
山东大学控制科学与工程学院，济南 250061

摘要:

目的解决目前数粒机只能计数不能同时分拣残损药粒的问题。方法设计以Faster R-CNN深度神经网络为核心的药粒数粒机系统。在原有的数粒机基础之上，更换CCD线阵相机为面阵相机，以满足图像采集的需求，进一步使用图像分割和多线程技术加快图像处理速度。最终通过训练好的Faster R-CNN网络检测出目标并分拣。结果经过测试集的验证，正常药粒识别率达到了95.47%，残损药粒识别率达到了97.94%，单幅图像处理达到了65 ms的实时速度。结论该方法在传统的计数基础上很好地融合了先进的深度学习技术，实现了目标的自动分拣。

关键词: 数粒机面阵相机 Faster R-CNN 药粒分拣

DOI：10.19554/j.cnki.1001-3563.2018.09.025

分类号:TB486；TP391

基金项目:

Improved Capsule Counting Machine Based on Faster R-CNN

HU An-xiang, LI Zhen-hua

School of Control Science and Engineering, Shandong University, Jinan 250061, China

Abstract:

The work aims to solve the problem that the current capsule counting machine can only count capsules and cannot sort damaged capsules at the same time. A capsule counting machine with the Faster R-CNN deep neural network as the core was designed. On the basis of the original capsule counting machine, the CCD line-array camera was replaced by area-array camera to meet the demand of image acquisition, and the image segmentation and multi-thread technology were further used to speed up the image processing speed. Finally, the target was detected and sorted through the well trained Faster R-CNN network. After verification of the test set, the identification rate of normal capsule reached 95.47%, the identification rate of damaged capsule reached 97.94%, and the single image processing reached the real-time speed of 65 ms. The proposed method properly combines the advanced in-depth learning technology based on the traditional counting and realizes the automatic sorting of the target.

Key words: capsule counting machine area-array camera Faster R-CNN capsule sorting