Flake-type medium identification method and identification device

Abstract

The invention relates to a flake-type medium identification method and an identification device. The method includes the first step of collecting image information, the second step of choosing the image information of a to-be-identified object in a dividing mode from the collected image information, the third step of reconstructing image data of a characteristic area, and extracting characteristics on the reconstructed image data to form characteristic vectors, and the fourth step of sending the characteristic vectors to classifiers which are well trained through standard data to obtain identification results. The method reconstructs images according to prior information of the characteristic area, improves image quality, is beneficial for improvement of the accuracy rate of identification, reduces consumption of storage space due to the fact that only reconstruction needs extraction of the characteristic image area, saves large amount of storage space and time, improves the resource utilization rate, effectively improves the accuracy rate of the identification, and achieves a good balance between resources and efficiency.

Description

technical field [0001] The invention relates to a pattern recognition technology based on image information, in particular to a method and device for recognizing thin sheet media based on image information. Background technique [0002] In the field of image-based pattern recognition, the first thing to do is to use the sensor to collect the recognized image. If the image resolution is insufficient, the accuracy of the recognition result will be greatly reduced, especially between easily confused recognition objects, such as characters in character recognition. "O" and "D", although the computer technology is changing with each passing day, but considering the cost, they will not choose a very high-end hardware platform, just to meet the actual needs. In this case, in the actual production process, due to the differences in hardware If the differences between objects and the diversity of the recognition space, there will be more confusing object recognition errors. [0003]...

AI Technical Summary

Problems solved by technology

However, in the actual collected signals, the amount of useful signal data is much greater than the amount of noise data. At this time, to reconstruct all the collected signals, the amount of data processing is huge, and the processing speed of the algorithm is slow. Improve recognition accuracy, but not ideal in most cases

Images