A NEW MODEL OF ADAPTIVE CONTAINER IMAGE PREPROCESSING

摘要

The preprocessing of container image is the key to the whole container code intelligent identification system, and the result of treatment directly affects the accuracy of the code area positioning, the character segmentation and recognition. Based on some features of container images such as the color, the gradient and the connected domain we proposed a novel and adaptive container image preprocessing model. In traditional methods, there are many parameters should be optimized, and multi-parameter optimization is a difficult point. Yet, our model not only solve the problem skillfully, but also can remove a large number the background color of container image adaptively when the color difference of background and target is small. Therefore, our model can better on container area segmentation, character segmentation and recognition. A lot of experimental results showed that the proposed model can effectively extract the more effect.