Opencv learning note 4 -- bank card number recognition

Early step

Import toolkit

from imutils import contours
import numpy as np
import argparse
import cv2
import myutils
import matplotlib.pyplot as plt#Matplotlib yes RGB

Specify the type of credit card

#  Specify the type of credit card （ According to the first digit of the card number ）
FIRST_NUMBER = {
    
	"3": "American Express",
	"4": "Visa",
	"5": "MasterCard",
	"6": "Discover Card"
}

Define the drawing function

#  Graphic display 
def cv_show(name,img):
    b,g,r = cv2.split(img)
    img_rgb = cv2.merge((r,g,b))
    plt.imshow(img_rgb)
    plt.show()
def cv_show1(name,img):
    plt.imshow(img)
    plt.show()
    cv2.imshow(name,img)
    cv2.waitKey()
    cv2.destroyAllWindows()

Read in the data

#  Read a template image 
img = cv2.imread("./ocr_a_reference.png")
cv_show('img',img)

#  grayscale 
ref = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv_show1('ref',ref)

#  Binary image 
ref = cv2.threshold(ref, 10, 255, cv2.THRESH_BINARY_INV)[1]
cv_show1('ref',ref)

Template handling

Calculate the contour

#cv2.findContours() The parameters accepted by the function are binary graphs , Black and white （ It's not grayscale ）,cv2.RETR_EXTERNAL Only the outer contour is detected ,cv2.CHAIN_APPROX_SIMPLE Keep only the end coordinates
# Back to list Each element in is an outline in the image

ref_, refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

cv2.drawContours(img,refCnts,-1,(0,0,255),3) 
cv_show1('img',img)

print (np.array(refCnts).shape)
refCnts = myutils.sort_contours(refCnts, method="left-to-right")[0] # Sort , From left to right , From top to bottom 
digits = {
    }

(10,)


d:\Miniconda3\envs\learnCV\lib\site-packages\ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
  """Entry point for launching an IPython kernel.

#  Traverse every contour 
for (i, c) in enumerate(refCnts):
	#  Calculate the circumscribed rectangle and resize To the right size 
	(x, y, w, h) = cv2.boundingRect(c)
	roi = ref[y:y + h, x:x + w]
	roi = cv2.resize(roi, (57, 88))

	#  Each number corresponds to each template 
	digits[i] = roi

#  Initialize convolution kernel 
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))

Card processing

# Read input image , Preprocessing 
image = cv2.imread("./images/credit_card_01.png")
cv_show('image',image)
image = myutils.resize(image, width=300)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv_show1('gray',gray)

# Hat operation , Highlight brighter areas 
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel) 
cv_show1('tophat',tophat) 
#  Calculation x Directional image gradient 
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, #ksize=-1 Equivalent to using 3*3 Of 
	ksize=-1)

gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")

print (np.array(gradX).shape)
cv_show1('gradX',gradX)

(189, 300)

# By closing （ Inflate first , Corrode again ） Put the numbers together 
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel) 
cv_show1('gradX',gradX)

[ Failed to transfer the external chain picture , The origin station may have anti-theft chain mechanism , It is suggested to save the pictures and upload them directly (img-8AcGUyGC-1656380868739)(https://gitcode.net/weixin_41756645/csdnimage/-/raw/master/ocr_match_files/ocr_match_19_0.png)]

#THRESH_OTSU Will automatically find the right threshold , Suitable for bimodal , The threshold parameter needs to be set to 0
thresh = cv2.threshold(gradX, 0, 255,
	cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1] 
cv_show1('thresh',thresh)

# Another close operation 

thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel) # Another close operation 
cv_show1('thresh',thresh)

#  Calculate the contour 

thresh_, threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
	cv2.CHAIN_APPROX_SIMPLE)

cnts = threshCnts
cur_img = image.copy()
cv2.drawContours(cur_img,cnts,-1,(0,0,255),3) 
cv_show('img',cur_img)
locs = []

#  Traverse the outline 
for (i, c) in enumerate(cnts):
	#  Calculate rectangle 
	(x, y, w, h) = cv2.boundingRect(c)
	ar = w / float(h)

	#  Choose the right area , According to the actual task , It's basically a set of four numbers 
	if ar > 2.5 and ar < 4.0:

		if (w > 40 and w < 55) and (h > 10 and h < 20):
			# The right ones stay 
			locs.append((x, y, w, h))

#  Sort the matching contours from left to right 
locs = sorted(locs, key=lambda x:x[0])
output = []

#  Go through the numbers in each profile 
for (i, (gX, gY, gW, gH)) in enumerate(locs):
	# initialize the list of group digits
	groupOutput = []

	#  Extract each group from the coordinates 
	group = gray[gY - 5:gY + gH + 5, gX - 5:gX + gW + 5]
	cv_show1('group',group)
	#  Preprocessing 
	group = cv2.threshold(group, 0, 255,
		cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
	cv_show1('group',group)
	#  Calculate the outline of each group 
	group_,digitCnts,hierarchy = cv2.findContours(group.copy(), cv2.RETR_EXTERNAL,
		cv2.CHAIN_APPROX_SIMPLE)
	digitCnts = contours.sort_contours(digitCnts,
		method="left-to-right")[0]

	#  Calculate each value in each group 
	for c in digitCnts:
		#  Find the outline of the current value ,resize To the right size 
		(x, y, w, h) = cv2.boundingRect(c)
		roi = group[y:y + h, x:x + w]
		roi = cv2.resize(roi, (57, 88))
		cv_show1('roi',roi)

		#  Calculate the match score 
		scores = []

		#  Calculate each score in the template 
		for (digit, digitROI) in digits.items():
			#  Template matching 
			result = cv2.matchTemplate(roi, digitROI,
				cv2.TM_CCOEFF)
			(_, score, _, _) = cv2.minMaxLoc(result)
			scores.append(score)

		#  Get the most appropriate number 
		groupOutput.append(str(np.argmax(scores)))

	#  Draw out 
	cv2.rectangle(image, (gX - 5, gY - 5),
		(gX + gW + 5, gY + gH + 5), (0, 0, 255), 1)
	cv2.putText(image, "".join(groupOutput), (gX, gY - 15),
		cv2.FONT_HERSHEY_SIMPLEX, 0.65, (0, 0, 255), 2)

	#  Get the results 
	output.extend(groupOutput)

#  Print the results 
print("Credit Card Type: {}".format(FIRST_NUMBER[output[0]]))
print("Credit Card #: {}".format("".join(output)))
cv_show("Image", image)
#cv2.waitKey(0)

Credit Card Type: Visa
Credit Card #: 4000123456789010

Reference resources

1.【2021B Stand at the best OpenCV Course recommended 】OpenCV From introduction to practice The whole course （ Attached course courseware materials + Courseware notes ）