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 features 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.

Key words: SURF feature, color feature; , shape feature, bar code