Python Image Processing (9): Hu Moment, python image processing hu

Python Image Processing (9): Hu Moment, python image processing hu

Happy shrimp

Http://blog.csdn.net/lights_joy/

Reprinted, but keep the author information

The geometric moment was proposed by Hu in 1962 and has the characteristics of translation, rotation, and scale immutability. The Calculation of Moment in opencv is completed by the Moments class in C ++:

//! raster image momentsclass CV_EXPORTS_W_MAP Moments{public:    //! the default constructor    Moments();    //! the full constructor    Moments(double m00, double m10, double m01, double m20, double m11,            double m02, double m30, double m21, double m12, double m03 );    //! the conversion from CvMoments    Moments( const CvMoments& moments );    //! the conversion to CvMoments    operator CvMoments() const;    //! spatial moments    CV_PROP_RW double  m00, m10, m01, m20, m11, m02, m30, m21, m12, m03;    //! central moments    CV_PROP_RW double  mu20, mu11, mu02, mu30, mu21, mu12, mu03;    //! central normalized moments    CV_PROP_RW double  nu20, nu11, nu02, nu30, nu21, nu12, nu03;};

It can be seen that it mainly includes space moment, center moment and center normalization moment.

I have never believed in the effect of geometric moment on identification of plant leaves, especially for blocked leaves. However, if you have learned this, try to calculate the Hu Moment in Python.

The image used is the color image separated from the preceding image:

We have obtained their binary images:

We use these two binary images as the input image for moment calculation.

#-*-Coding: UTF-8-*-import cv2import numpy as np # import matplotlib. pyplot as pltdir = 'f: \ projects \ src \ opencv \ images \ cotton \\'; # Hu moments unchanged # Read cotton image cotton = cv2.imread (dir + '39.mask.jpg ') cotton = cotton [:,:, 0] # This is a binary image, only use the first channel cv2.imshow ('cotton ', cotton) # Read weed image weed = cv2.imread (dir + '47.mask.jpg') weed = weed [:,:, 0] # This is a binary image. Only the first channel cv2.imshow ('weed', weed) is used. # Calculate the moment of cotton and the Hu Moment moments = cv2.moments (cotton) hu_moments = cv2.HuMoments (moments) print ('cotton moments: ') print (hu_moments) # Calculate the moment of weeds and Hu Moment moments = cv2.moments (weed) hu_moments = cv2.HuMoments (moments) print ('weed moments: ') print (hu_moments) cv2.waitKey ()

The calculation result is as follows:

The preceding code shows how to use Python to calculate Hu Moment.