摘要
在当今信息爆炸的时代中,随着科技在图像认知需求的激增,碎片式的图像已然成为巨大信息量的载体之一,因此如何对图像中目标的方位和类型进行识别就显得极为重要.近年来,机器视觉、目标识别等成为可以解决在大量碎片式的图像数据库中提取信息的人工智能相关的研究方向.基于嵌入式与Python—OpenCV平台,对图像目标识别进行了一系列研究,实现了对视频中的鞋子进行正确识别并能将识别的图像信息进行储存的目的.该研究对于机器视觉和目标识别技术在现实中的应用具有重要的意义.
In today＇s information explosion era,with the increase of technology applied in image cognition,fragmented images have become one of the carriers of huge information. So how to identify the orientation and type of objects in the image is extremely important. In recent years,machine vision and target recognition have become the research directions related to artificial intelligence that can extract information in a large number of fragmented image databases. Based on the embedded and Python-OpenCV platform,this paper studies a series of research on image target recognition,which realizes the purpose of correctly identifying the shoes in the video and storing the recognized image information. This research has important practical significance for the application of machine vision and target recognition technology in reality.
作者
邵彩幸
于越
段琼
刘明志
SHAO Cai-xing;YU Yue;Duan Qiong;LIU Ming-zhi(School of Computer Science and Technology,Southwest Minzu University,Chengdu 610041,P.R.C.;Key Laboratory for Computer Systems of State Ethnic Affairs Commission,Southwest Minzu University,Chengdu 610041,P.R.C.)
出处
《西南民族大学学报（自然科学版）》
CAS
2018年第5期502-506,共5页
Journal of Southwest Minzu University(Natural Science Edition)
基金
四川省科技厅应用基础项目(2017JY0230)
中央高校基本科研业务费(2017NZYQN20)
