adding more example and fixing previous codes

Author: codeperfectplus

.gitignore

@@ -41,4 +41,7 @@ env/
 venv/
 ENV/
 env.bak/
-venv.bak/
+venv.bak/
+
+# others
+test.py

03. Edge Detection/Real Time Edge Detection.py

@@ -4,17 +4,21 @@
 
 cap = cv2.VideoCapture(0)
 
-while(1):
+while True:
 
-    _, frame = cap.read()
+    check, frame = cap.read()
+    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
 
-    cv2.imshow('Original',frame)
-    edges = cv2.Canny(frame,100,200)
-    cv2.imshow('Edges',edges)
+    if check:
+        # applying canny edge transformation
+        edges = cv2.Canny(gray, threshold1=30, threshold2=100)
 
-    k = cv2.waitKey(5) & 0xFF
-    if k == 27:
-        break
+        # showing the output frame
+        cv2.imshow('Original',frame)
+        cv2.imshow('Edges', edges)
 
+        if cv2.waitKey(5) & 0xFF == 27:
+            break
+
+cap.release()
 cv2.destroyAllWindows()
-cap.release()

03. Edge Detection/cannyEdgeDetection.py

@@ -1,23 +1,25 @@
 '''
 Edge detection with canny algo
-edges = cv2.Canny('/path/to/img', minVal, maxVal, apertureSize, L2gradient)  
+edges = cv2.Canny('/path/to/img', threshold1, threshold2, apertureSize, L2gradient)
 
-minVal= minimu, intensity gradent
-L2gradient: Its default value is false, if value is true, Canny () uses a more computationally expensive equation to detect edges, 
+L2gradient: Its default value is false, if value is true, Canny () uses a more computationally expensive equation to detect edges,
 which provides more accuracy at the cost of resources.
 '''
 import cv2
 
 img = cv2.imread(r'./Media/face-001.jpg')
-edges = cv2.Canny(img, 100, 100)
-print(edges)
+gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
-cv2.imshow("Edge Detected Image",edges)
+# applying canny edge transformations
+edges = cv2.Canny(gray_img, threshold1=30, threshold2=100)
+
+# showing the output frame
+cv2.imshow("Edge Detected Image", edges)
 
 k = cv2.waitKey(0) & 0xFF
 
 if k == 27:
     cv2.destroyAllWindows()
 elif k == ord('s'):
     cv2.imwrite("./Media/edge-detection.jpg", edges)
-    cv2.destroyAllWindows()
+    cv2.destroyAllWindows()

07. Face Detection/blurTheFace.py

@@ -1,26 +1,53 @@
 ''' Real time Face bluring using webcam '''
 
-import numpy as np
 import cv2
+import numpy as np
+import time
 
-face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+# https://raw.githubusercontent.com/opencv/opencv/master/samples/dnn/face_detector/deploy.prototxt
+prototxt_path = "07. Face Detection/deploy.prototxt.txt"
+# https://raw.githubusercontent.com/opencv/opencv_3rdparty/dnn_samples_face_detector_20180205_fp16/res10_300x300_ssd_iter_140000_fp16.caffemodel 
+model_path = "07. Face Detection/res10_300x300_ssd_iter_140000.caffemodel"
 
-cap = cv2.VideoCapture(0)
+# load Caffe model
+model = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)
 
-while 1:
-    ret, frame = cap.read()
-    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
-    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
-
-    for (x,y,w,h) in faces:
-        roi_color = frame[y:y+h, x:x+w]
-        roi_color = cv2.GaussianBlur(roi_color, (23, 23), 30)
-        frame[y: y+h, x: x+w] = roi_color
+cap = cv2.VideoCapture(0)
 
-    cv2.imshow('bluredFace', frame)
-    if cv2.waitKey(30) & 0xff == ord("q"):
+while True:
+    start = time.time()
+    _, image = cap.read()
+    # get width and height of the image
+    h, w = image.shape[:2]
+    kernel_width = (w // 7) | 1
+    kernel_height = (h // 7) | 1
+    # preprocess the image: resize and performs mean subtraction
+    blob = cv2.dnn.blobFromImage(image, 1.0, (300, 300), (104.0, 177.0, 123.0))
+    # set the image into the input of the neural network
+    model.setInput(blob)
+    # perform inference and get the result
+    output = np.squeeze(model.forward())
+    for i in range(0, output.shape[0]):
+        confidence = output[i, 2]
+        # get the confidence
+        # if confidence is above 40%, then blur the bounding box (face)
+        if confidence > 0.4:
+            # get the surrounding box cordinates and upscale them to original image
+            box = output[i, 3:7] * np.array([w, h, w, h])
+            # convert to integers
+            start_x, start_y, end_x, end_y = box.astype(np.int)
+            # get the face image
+            face = image[start_y: end_y, start_x: end_x]
+            # apply gaussian blur to this face
+            face = cv2.GaussianBlur(face, (kernel_width, kernel_height), 0)
+            # put the blurred face into the original image
+            image[start_y: end_y, start_x: end_x] = face
+    cv2.imshow("image", image)
+    if cv2.waitKey(1) == ord("q"):
         break
-    
+    time_elapsed = time.time() - start
+    fps = 1 / time_elapsed
+    print("FPS:", fps)
 
-cap.release()
-cv2.destroyAllWindows()
+cv2.destroyAllWindows()
+cap.release()

07. Face Detection/realTimeFaceDetectionDNN.py

@@ -3,17 +3,21 @@
 import numpy as np
 import cv2
 
-proto='./deploy.prototxt.txt'
-model='./res10_300x300_ssd_iter_140000.caffemodel'
-confThresh=0.5
-net = cv2.dnn.readNetFromCaffe(proto, model)
+# https://raw.githubusercontent.com/opencv/opencv/master/samples/dnn/face_detector/deploy.prototxt
+prototxt_path = "07. Face Detection/deploy.prototxt.txt"
+# https://raw.githubusercontent.com/opencv/opencv_3rdparty/dnn_samples_face_detector_20180205_fp16/res10_300x300_ssd_iter_140000_fp16.caffemodel 
+model_path = "07. Face Detection/res10_300x300_ssd_iter_140000.caffemodel"
+
+confThresh = 0.5
+net = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)
 
 cam=cv2.VideoCapture(0)
+
 while True:
-    ret,frame=cam.read()
-    frame=cv2.flip(frame,1)
+    ret, frame = cam.read()
+    frame = cv2.flip(frame, 1)
     (h, w) = frame.shape[:2]
-    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0,(300, 300), (104.0, 177.0, 123.0))
+    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0))
 
     net.setInput(blob)
     detections = net.forward()

17. Color Trackbar/colorTrackbar.py

@@ -2,12 +2,13 @@
 
 import numpy as np
 import cv2
+
 def nothing(x):
     pass
 
 # Create a black image, a window
-img = np.zeros((300,512,3), np.uint8)
-cv2.namedWindow('image')
+img = np.zeros((300, 512, 3), np.uint8)
+cv2.namedWindow('Color Tracker')
 
 # create trackbars for color change
 cv2.createTrackbar('R','image',0,255,nothing)
@@ -35,4 +36,4 @@ def nothing(x):
     else:
         img[:] = [b,g,r]
 
-cv2.destroyAllWindows()
+cv2.destroyAllWindows()

18. SIFT Feature Extraction/Compare Features.py

@@ -0,0 +1,29 @@
+import numpy as np
+import cv2
+
+# loading and resizing the image 
+img1 = cv2.imread('./Media/book.png')
+img2 = cv2.imread('./Media/book_on_table.jpeg')
+
+img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
+img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
+
+sift = cv2.SIFT_create()
+
+keypoints1, descrptors1 = sift.detectAndCompute(img1, None)
+keypoints2, descrptors2 = sift.detectAndCompute(img2, None)
+
+bf = cv2.BFMatcher(cv2.NORM_L1, crossCheck=True)
+
+matches = bf.match(descrptors1, descrptors2)
+matches = sorted(matches, key= lambda x: x.distance)
+
+matched_img = cv2.drawMatches(img1, keypoints1, img2, keypoints2, matches[:20], img2, flags=2)
+
+# showing the output
+cv2.imshow('image', cv2.resize(matched_img, (800, 600)))
+
+k = cv2.waitKey(0) & 0xff
+
+if k == 27:
+    cv2.destroyAllWindows()

18. SIFT Feature Extraction/README.md

@@ -0,0 +1,10 @@
+**SIFT** stands for `Scale Invariant Feature Transform`, it is a feature extraction method (among others, such as `HOG feature extraction`) where image content is transformed into local feature coordinates that are invariant to translation, scale and other image transformations.
+
+Below are the advantages of SIFT:
+
+- Locality: Features are local; robust to occlusion and clutter.
+- Distinctiveness: Individual features extracted can be matched to a large dataset of objects.
+- Quantity: Using SIFT, we can extract many features from small objects.
+- Efficiency: SIFT is close to real-time performance.
+
+[SIFT original paper](https://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf)

18. SIFT Feature Extraction/basic.py

@@ -0,0 +1,17 @@
+import numpy as np
+import cv2
+
+img = cv2.imread('./Media/apple.jpeg')
+gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+
+sift = cv2.SIFT_create()
+
+keypoints, descrptors = sift.detectAndCompute(img, None)
+sift_image = cv2.drawKeypoints(gray_img, keypoints, img)
+
+cv2.imshow('image', sift_image)
+
+k = cv2.waitKey(0) & 0xff
+
+if k == 27:
+    cv2.destroyAllWindows()