crop fields

get_data.py

+from cv2 import cv2
+import random
+
+scale = 0.5
+circles = []
+counter = 0
+counter2 = 0
+point1 = []
+point2 = []
+myPoints = []
+myColor = []
+
+def mousePoints(event,x,y,flags,params):
+    global counter,point1,point2,counter2,circles,myColor
+    if event == cv2.EVENT_LBUTTONDOWN:
+        if counter == 0:
+            point1=int(x//scale),int(y//scale)
+            counter +=1
+            myColor = (random.randint(0,2)*200,random.randint(0,2)*200,random.randint(0,2)*200)
+        elif counter ==1:
+            point2=int(x//scale),int(y//scale)
+            types = input('Enter Type ')
+            name = input('Enter Name ')
+            myPoints.append([point1,point2,types,name])
+            counter=0
+        circles.append([x,y,myColor])
+        counter2 += 1
+
+img = cv2.imread('template.jpg')
+h,w,c  = img.shape
+img = cv2.resize(img, (w//3,h//3), None, scale, scale)
+
+while True:
+    for x,y,color in circles:
+        cv2.circle(img,(x,y),3,color,cv2.FILLED)
+    cv2.imshow("Original Image ", img)
+    cv2.setMouseCallback("Original Image ", mousePoints)
+    if cv2.waitKey(1) & 0xFF == ord('s'):
+        print(myPoints)
+        break
\ No newline at end of file

img_to_text.py

+import numpy as np
+from cv2 import cv2
+import pytesseract
+import os
+
+# Declaring Paths
+pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
+current_path =  os.path.abspath(os.path.join(os.path.dirname(__file__)))
+test_images_path = current_path+"\\Test_images"
+
+per = 25
+scale = 0.5
+
+roi = [[(204, 196), (3304, 364), 'text', 'Validation'], #(x,y) (width+x,height+y)
+       [(154, 668), (2544, 765), 'text', 'Name'], 
+       [(2654, 650), (3400, 758), 'text', 'RegNo'], 
+       [(754, 960), (2380, 1065), 'text', 'Course'], 
+       [(2412, 1370), (3350, 1450),  'text', 'Amount']]
+
+imageT = cv2.imread("template.jpg")
+h,w,c  = imageT.shape
+#imageT = cv2.resize(imageT, (w//6,h//6))
+# text = pytesseract.image_to_string(image)
+
+orb = cv2.ORB_create(1000)
+
+# unique key points/elements to image,  decsripters are the representation of these key points that will be easier for
+#the computer to understand
+kp1, des1 = orb.detectAndCompute(imageT, None)
+
+Image_list = os.listdir(test_images_path)
+print(Image_list)
+
+for j,y in enumerate(Image_list):
+    img = cv2.imread(test_images_path + "\\"+y)
+    h,w,c  = img.shape
+    kp2, des2 = orb.detectAndCompute(img, None)
+    bf = cv2.BFMatcher(cv2.NORM_HAMMING)
+    matches = bf.match(des2,des1)
+    matches.sort(key= lambda x: x.distance)
+    good = matches[:int(len(matches)*(per/100))]
+    imgMatch = cv2.drawMatches(img,kp2,imageT,kp1,good[:100],None,flags=2)
+
+    srcPoints = np.float32([kp2[m.queryIdx].pt for m in good]).reshape(-1,1,2)
+    dstPoints = np.float32([kp1[m.trainIdx].pt for m in good]).reshape(-1,1,2)
+
+    M, _ = cv2.findHomography(srcPoints,dstPoints,cv2.RANSAC,5.0)
+    imgScan = cv2.warpPerspective(img,M,(w,h))
+
+    imgShow = imgScan.copy()
+    imgMask = np.zeros_like(imgShow)
+
+    Data_list = []
+
+    for x,r in enumerate(roi):
+        cv2.rectangle(imgMask, ((r[0][0]), r[0][1]), ((r[1][0]), r[1][1]), (0,255,0), cv2.FILLED)
+        imgShow = cv2.addWeighted(imgShow, 0.99, imgMask, 0.1,0)
+
+        imgCrop = imgScan[r[0][1]:r[1][1], r[0][0]:r[1][0]]
+        cv2.imshow(str(x), imgCrop)
+
+        if r[2] == 'text':
+            #print(f'{r[3]} : {pytesseract.image_to_string(imgCrop)}')
+            Data_list.append(pytesseract.image_to_string(imgCrop))
+    print(Data_list)
+    
+    with open('outputFields.csv', 'a+') as f:
+        for data in Data_list:
+            print(data)
+            f.write((str(data)+','))
+        f.write('\n')
+
+    img = cv2.resize(img, (w//4,h//4), None, scale, scale)
+    imgShow = cv2.resize(imgShow, (w//4,h//4), None, scale, scale)
+    cv2.imshow(y+"2", imgShow)
+
+#imgKp1 = cv2.drawKeypoints(image, kp1, None)
+#cv2.imshow("KeyPoints", imgKp1)
+
+#cv2.imshow("Output", image)
+cv2.waitKey(0)
\ No newline at end of file

outputFields.csv

+Validations,Name,RegNo,Course,Amount