基于图像特征匹配的商品识别算法

基于条形码的结帐系统存在操作繁琐等一些问题，为了解决零售业结账服务中排队的难题，提出一种以SURF(Speeded Up Robust Features)特征匹配为主，主颜色特征数字编码分类、形状特征数字编码分类为辅的商品快速识别算法。基于特征的方法具有压缩信息量、精度高等优点，成为目前研究的热点。但是传统图像特征识别算法，存在特征维度多、计算量大、运行速度慢等缺点，限制了其应用。本文将其中的主颜色和形状特征进行数字编码分类，之后利用高效识别算法SURF进行准确识别，很好地克服了以上缺点。实验表明，本文算法运行速度快，识别性能好，为零售业的结账服务提供了便利。

Objection Recognition Algorithm Based on Image Feature Matching

Abstract： Some complicated problems are existed in checkout system based on bar code. In order to solve the queuing problem, a fast objection recognition system based on image feature matching is proposed. In this new system, features are combined with SURF（ Speeded Up Robust Features） feature matching, main color feature digital coding classification, and shape feature digital coding classification. The method based on characteristics can compress the amount of information, has the advantages of high precision, and it becomes a research hotspot. But the traditional image feature recognition algorithm has the disadvantages of large feature dimensions, huge calculation, and slow shortcomings, limiting its application. In this paper, main color and shape fea- tures are used as digital coding classification firstly, and then SURF identification is used to get precise classification, in order to overcome the above disadvantages. It is showed by the experiment, our system has fast speed and good recognition performance, and provides a convenient for the retail checkout service.