blech

stackoverflow.py

@@ -0,0 +1,30 @@
+# https://stackoverflow.com/questions/24385714/detect-text-region-in-image-using-opencv
+
+import cv2
+import numpy as np
+
+# Load image, convert to HSV format, define lower/upper ranges, and perform
+# color segmentation to create a binary mask
+image = cv2.imread('1.jpg')
+hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
+lower = np.array([0, 0, 218])
+upper = np.array([157, 54, 255])
+mask = cv2.inRange(hsv, lower, upper)
+
+# Create horizontal kernel and dilate to connect text characters
+kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,3))
+dilate = cv2.dilate(mask, kernel, iterations=5)
+
+# Find contours and filter using aspect ratio
+# Remove non-text contours by filling in the contour
+cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+cnts = cnts[0] if len(cnts) == 2 else cnts[1]
+for c in cnts:
+    x,y,w,h = cv2.boundingRect(c)
+    ar = w / float(h)
+    if ar < 5:
+        cv2.drawContours(dilate, [c], -1, (0,0,0), -1)
+
+# Bitwise dilated image with mask, invert, then OCR
+result = 255 - cv2.bitwise_and(dilate, mask)
+result.show()

stackoverflow2.py

@@ -0,0 +1,66 @@
+import cv2
+import numpy as np
+from PIL import Image, ImageDraw
+
+def dbg(arr2d):
+   dbg = {}
+   for x in arr2d:
+     for y in x:
+       dbg[y] = dbg.get(y, 0) + 1
+   print(dbg)
+   #return
+   img = Image.new("1", (max([len(x) for x in arr2d]), len(arr2d)))
+   draw = ImageDraw.Draw(img)
+   for x in range(len(arr2d)):
+      for y in range(len(arr2d[x])):
+         draw.point( (y,x), fill=1 if arr2d[x][y] > 100 else 0)
+   img.show()
+
+def draw_boxes(arr2d, boxes):
+   img = Image.new("1", (max([len(x) for x in arr2d]), len(arr2d)))
+   draw = ImageDraw.Draw(img)
+   for x in range(len(arr2d)):
+      for y in range(len(arr2d[x])):
+         draw.point( (y,x), fill=1 if arr2d[x][y] > 100 else 0)
+   for box in boxes:
+      x0 = box[0]
+      y0 = box[1]
+      x1 = box[0] + box[2]
+      y1 = box[1] + box[3]
+      draw.line( [(x0,y0), (x1,y0)], fill=1)
+      draw.line( [(x1,y0), (x1,y1)], fill=1)
+      draw.line( [(x1,y1), (x0,y1)], fill=1)
+      draw.line( [(x0,y1), (x0,y0)], fill=1)
+   img.show()
+
+# Load image, convert to HSV format, define lower/upper ranges, and perform
+# color segmentation to create a binary mask
+image = cv2.imread('1.png')
+hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
+lower = np.array([0, 0, 0])
+upper = np.array([0, 255, 200])
+mask = cv2.inRange(hsv, lower, upper)
+#dbg(mask)
+
+# Create horizontal kernel and dilate to connect text characters
+kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,3))
+dilate = cv2.dilate(mask, kernel, iterations=0)
+#dbg(dilate)
+
+# Find contours and filter using aspect ratio
+# Remove non-text contours by filling in the contour
+cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+cnts = cnts[0] if len(cnts) == 2 else cnts[1]
+draw_boxes(dilate, [cv2.boundingRect(c) for c in cnts])
+for c in cnts:
+    x,y,w,h = cv2.boundingRect(c)
+    ar = w / float(h)
+    print(x, y, w, h)
+    if ar < 5:
+        cv2.drawContours(dilate, [c], -1, (0,0,0), -1)
+#dbg(dilate)
+exit()
+
+# Bitwise dilated image with mask, invert, then OCR
+result = 255 - cv2.bitwise_and(dilate, mask)
+dbg(result)