Target corner extraction method of complex scene image based on feature extraction

The invention discloses a target corner extraction method of a complex scene image based on feature extraction. The method comprises the following steps: graying an image; binarizing the image on thebasis; the influence of global binarization on the local property is avoided; the binarization accuracy is improved; all possible angular points are detected by using a Harris angular point detectionmethod; the method comprises the following steps: extracting corresponding features including a domain matrix calculation result, neighborhood binarization black and white pixel change features and the like for each corner, performing feature analysis on a large number of features on the basis to determine the features of a target corner, and finally, filtering out candidate corners which do not meet requirements by utilizing related parameters obtained by analysis. According to the scheme, the candidate angular points which do not meet the requirements can be accurately filtered, the target angular points are extracte