Texture image identification method and texture image identification device

Abstract

The invention discloses a texture image identification method which includes the following steps: preprocessing a texture image and extracting a character area; performing coordinate-system conversion on the character area and calculating a projection histogram; performing Fourier transformation on the projection histogram so as to obtain the characteristic vector of the texture image; and executing the above-mentioned steps on a to-be-identified texture image and a standard texture image so that the characteristic vector of the to-be-identified texture image and the characteristic vector of the standard texture image are obtained and calculating the similarity between the characteristic vector of the to-be-identified texture image and the characteristic vector of the standard texture image and judging whether the to-be-identified texture image is a standard texture image according to a similarity threshold. The invention also discloses a texture image identification device. The texture image identification method and identification device are great in identification effect of dynamic objects, high in interference resistance, low in identification missing rate, particularly low in error identification rate, simple in calculation, great in instantaneity and capable of satisfying real-time target detecting tasks under a dynamic scene.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and in particular relates to a texture image recognition method and a texture image recognition device, which can be extended and applied to character recognition and other target recognition tasks with obvious texture features. Background technique [0002] The detection and recognition of texture targets is an important content in target detection. When the camera is still and the target is still, there are no various interferences, rotations, and blurring situations, and the task of target detection is relatively easy. Commonly used detection methods include frame difference method, corner point matching method, etc.; when there is relative motion between the camera and the detection target and the motion cannot be estimated, there will be target disappearance, target rotation, affine change, image blur and many other disturbances. For example, on motion platforms such ...

AI Technical Summary

Problems solved by technology

Commonly used methods such as corner detection, SIFT (Scale-invariant feature transform, scale-invariant feature transformation) feature matching, ORB (ORiented Brief) descriptor, Hu moment and Zernike recognition have defects in highly dynamic symbol recognition, and will lead to misidentification and missed identification

Images