基于智能优化图像处理的硬币金额检测  

Coin amount detection based on intelligent optimization image processing

作　　者：王敏 李晟 吴佳 孙硕 王康 WANG Min;LI Sheng;WU Jia;SUN Shuo;WANG Kang(School of Electronic and Information Engineering,Nanjing University of Information Science&Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,南京210044

出　　处：《信息技术》2024年第6期42-46,53,共6页Information Technology

基　　金：国家自然科学基金(41775165,41775039);南京信息工程大学引进人才科研启动专项经费资助(2021r034)。

摘　　要：硬币检测对于银行部门大额硬币流通、自助机交易、假币鉴别等具有实用意义。针对目前光电传感器硬币检测效果不理想的问题,提出了一种基于智能优化图像处理的硬币金额检测方法。首先利用颜色特征和智能优化Otsu图像分割对五角硬币特征区域进行提取并计数,再依次利用图像预处理、边缘检测、形态学处理和Hough圆检测等环节检测各硬币的半径信息,通过对半径进行比较可识别出硬币的种类及面额,最后利用App Designer设计了硬币自动识别系统。实验结果表明,该方法具有效果好、速度快、易于实现等优点,能够满足工程化需要。Coin amount detection has practical significance for the circulation of large coins,self-service machine transactions,counterfeit currency identification and so on.Based on this problem that the coin detection effect of photoelectric sensor is not ideal at present,a coin amount detection method based on intelligent optimization image processing is proposed.Firstly,the color feature and intelligently optimized Otsu image segmentation are used to extract and count the characteristic area of pentagonal coins,and then the radius information of each coin is detected by image preprocessing,edge detection,morphological processing and Hough circle detection.By comparing the radius,the type and denomination of coins can be identified.Finally,the automatic coin recognition system is designed by app designer.The experiment results show that this method has the advantages of ideal effect,fast speed and easy implementation,which can meet the needs of engineering.

关 键 词：硬币识别 图像预处理 智能优化 粒子群算法 Otsu图像分割 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]