基于区域特征的果实识别技术  

Technology of Discriminating Fruit Based on Region Feature

作　　者：李印清[1] 郑小东[1] 王晓洁[2] 

机构地区：[1]郑州航空工业管理学院计算机科学与应用系,郑州450015 [2]郑州大学机械工程学院,郑州450002

出　　处：《河南科学》2008年第3期339-342,共4页Henan Science

基　　金：国家自然科学基金项目(60075006)

摘　　要：以番茄作为研究对象,提出基于区域特征的果实识别技术.识别过程包括灰度变换、区域边缘锐化、区域分割、细化处理等步骤.对70幅图像进行的实验表明,其正确识别率为74.3%.如将该技术应用到类似果实的识别领域,仅需对灰度变换公式进行适当的调整.A new technology of discriminating fruit on trees is presented based on region feature, in which tomato is set as study subject. The discriminating process includes gray transformation, region edge enhancement, region segmentation et al. Seventy images are tested and 74.3 percent images are correctly technology is applied to the similar fruits discrimination, all need to do is to adjust the formula.

关 键 词：图像识别 区域特征 番茄 果实 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]