update line detecting

.gitignore

@@ -14,3 +14,5 @@ preprocessing/preprocessingImages/images/
 .vs/
 machineLearning/Object-Classification-and-Detection/Keras-Sandbox/simple-image-classification-model/pyimagesearch/__pycache__/
 depthSensing/images/
+*.jpg
+*.pyc

preprocessing/preprocessingImages/cornerDetection.py

@@ -43,17 +43,17 @@ def get_contours(img):
 
 
     # show the final points on a copy of the image
-    '''
+
     img2 = img.copy()
     for pt in coor_tuples:
         cv.circle(img2, tuple(reversed(pt)), 3, (0, 0, 255), -1)
     cv.imshow('Image with main corners', img2)
     cv.waitKey(0)
-    '''
+
 
     return coor_tuples
 
 
-# img = cv.imread("test.jpg")
-# corners = get_contours(img)
-# print(corners)
+img = cv.imread("dices-2164.jpg")
+corners = get_contours(img)
+print(corners)

preprocessing/preprocessingImages/houghLine.py

@@ -0,0 +1,54 @@
+import cv2
+import numpy as np
+from matplotlib import pyplot as plt
+from PIL import Image
+import PIL
+#from preprocessing.preprocessingImages.threshCannyEdgeFunction import threshCanny
+
+image_name = 'mask'
+imgb = cv2.imread(image_name + '.jpg')
+
+#obtain the threshold for Canny using the grayscale image
+img_grayscale = cv2.cvtColor(imgb, cv2.COLOR_BGR2GRAY)
+v = np.median(img_grayscale)
+sigma = 0.33
+#phi = 0.11
+#first threshold
+
+lower_thresh = int(max(0, (1.0 - sigma) * v))
+upper_thresh = int(min(255, (1.0 + sigma) * v))
+#second threshold
+
+'''
+if False:
+    lower_thresh = int(max(0, (1.0 - 2 * sigma) * v))
+    upper_thresh = int(min(255, v))
+#third threshold
+if False:
+    lower_thresh = int(max(0, (1.0 - 2 * sigma) * v))
+    upper_thresh = int(min(255, (1.0 + sigma) * v))
+'''
+
+#get the edge
+
+edges = cv2.Canny(imgb, lower_thresh, upper_thresh)
+#print(edges)
+#edgesimg2 = PIL.Image.fromarray(edges)
+#edgesimg2.save(image_name + '-threshold3' + '.jpg')
+
+lines = cv2.HoughLines(edges, 20, np.pi/360, 2000)
+for i in range(len(lines)):
+    for rho,theta in lines[i]:
+#for rho,theta in lines[0]:
+        a = np.cos(theta)
+        b = np.sin(theta)
+        x0 = a*rho
+        y0 = b*rho
+        x1 = int(x0 + 1000*(-b))
+        y1 = int(y0 + 1000*(a))
+        x2 = int(x0 - 1000*(-b))
+        y2 = int(y0 - 1000*(a))
+
+        cv2.line(imgb,(x1,y1),(x2,y2),(0,0,255),2)
+
+cv2.imwrite('mask-houghlines.jpg',imgb)

preprocessing/preprocessingImages/maskImage.py

@@ -0,0 +1,21 @@
+import cv2
+import numpy as np
+import matplotlib
+from matplotlib.pyplot import imshow
+from matplotlib import pyplot as plt
+
+# white color mask
+img = cv2.imread("dices-2164.jpg")
+#converted = convert_hls(img)
+image = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
+lower = np.uint8([70, 150, 150])
+upper = np.uint8([200, 255, 255])
+white_mask = cv2.inRange(image, lower, upper)
+# yellow color mask
+lower = np.uint8([10, 0,   100])
+upper = np.uint8([40, 255, 255])
+yellow_mask = cv2.inRange(image, lower, upper)
+# combine the mask
+mask = cv2.bitwise_or(white_mask, yellow_mask)
+result = img.copy()
+cv2.imwrite("mask.jpg",white_mask)

preprocessing/preprocessingImages/threshCannyEdge.py

@@ -4,7 +4,7 @@
 from PIL import Image
 import PIL
 
-image_name = 'robot-0268'
+image_name = 'mask'
 imgb = cv2.imread(image_name + '.jpg')
 
 #obtain the threshold for Canny using the grayscale image
@@ -13,10 +13,11 @@
 sigma = 0.33
 #phi = 0.11
 #first threshold
-if False:
-    lower_thresh = int(max(0, (1.0 - sigma) * v))
-    upper_thresh = int(min(255, (1.0 + sigma) * v))
+
+lower_thresh = int(max(0, (1.0 - sigma) * v))
+upper_thresh = int(min(255, (1.0 + sigma) * v))
 #second threshold
+'''
 if False:
     lower_thresh = int(max(0, (1.0 - 2 * sigma) * v))
     upper_thresh = int(min(255, v))
@@ -25,9 +26,10 @@
 upper_thresh = int(min(255, (1.0 + sigma) * v))
 
 #TODO: set lower_thresh and upper_thresh lower
+'''
 
 #get the edge
 edges = cv2.Canny(imgb, lower_thresh, upper_thresh)
 print(edges)
 edgesimg2 = PIL.Image.fromarray(edges)
-edgesimg2.save(image_name + '-threshold3' + '.jpg')
+edgesimg2.save(image_name + '-threshold' + '.jpg')