Image classification method based on histogram and polar coordinate change

The invention discloses an image classification method based on histogram and polar coordinate change. The method comprises the following steps: S1, establishing a plurality of types of standard histograms corresponding to image classification; S2, performing statistical analysis on values of all pixel points in the to-be-classified image, drawing statistical histograms of different pixel values,and recording the statistical histograms as pd; S3, performing polar coordinate transformation on each pixel point in the to-be-classified image, namely S4, rounding r and theta by using a nearest neighbor interpolation method to obtain pixel values corresponding to the rounded r and theta; S5, performing statistical analysis on the values of all the pixel points in the polar coordinate image, drawing statistical histograms of different pixel values, and recording the statistical histograms as pp; and S5, analyzing the two histograms pd and pp, comparing the two histograms pd and pp with different types of standard hi