Image analysis with Python

1. matplotlib ( is a python 2D plotting library )

 - site (api)

http://matplotlib.org/api/pyplot_api.html

2. opencv (is an open source computer vision and machine learning software library.)

 - site (api)

http://opencv.org/

 - template matching

http://docs.opencv.org/doc/tutorials/imgproc/histograms/template_matching/template_matching.html#which-are-the-matching-methods-available-in-opencv

3. NumPy (is the fundamental package for scientific computing with Python.)
http://www.numpy.org/

4. sample code

# personal issue

import matplotlib

matplotlib.use('TkAgg')

# begin

import cv2

import numpy as np

from matplotlib import pyplot as plt

pic = '/home/fox/park.JPG'

compare_pic = '/home/fox/car.JPG'

img_rgb = cv2.imread(pic)

img_gray = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)

template = cv2.imread(compare_pic,0)

w, h = template.shape[::-1]

res = cv2.matchTemplate(img_gray,template,cv2.TM_CCOEFF_NORMED)

threshold = 0.7   # wanna find a best matching image => np.amax(res)

loc = np.where( res >= threshold)

for pt in zip(*loc[::-1]):

   cv2.rectangle(img_rgb, pt, (pt[0] + w, pt[1] + h), (0,0,255), 2)

cv2.imwrite('/home/fox/res3.png',img_rgb)

plt.subplot(121),plt.imshow(res,cmap = 'gray')

plt.title('Matching Result'), plt.xticks([]), plt.yticks([])

plt.subplot(122),plt.imshow(img_rgb,cmap = 'gray')

plt.title('Detected Point'), plt.xticks([]), plt.yticks([])

plt.show()

up to bottom
 - car.JPG , park.JPG, best_one.JPG, density_0.6.JPG