fixes & changes closed

app.py

@@ -95,10 +95,31 @@ def calculate_pip_width(image, original_img, pixel_per_metric):
         cv2.circle(img, (int(xB), int(yB)), 5, color_circle, -1)
         cv2.line(img, (int(xA), int(yA)), (int(xB), int(yB)), color_line, 2)
         d_mm = d / pixel_per_metric
-        d_mm = d_mm - 2.5
+        d_mm = d_mm - 1.5
         cv2.putText(img, "{:.1f}".format(d_mm), (int(xA - 15), int(yA - 10)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2)
-        # print(d_mm)
-        return d_mm, img
+        print(d_mm)
+        return d_mm
+    
+    def process_point(point, cnt, m1, b):
+        x1, x2 = point[0], point[0]
+        y1 = m1 * x1 + b
+        y2 = m1 * x2 + b
+
+        result = 1.0
+        while result > 0:
+            result = cv2.pointPolygonTest(cnt, (x1, y1), False)
+            x1 += 1
+            y1 = m1 * x1 + b
+        x1 -= 1
+
+        result = 1.0
+        while result > 0:
+            result = cv2.pointPolygonTest(cnt, (x2, y2), False)
+            x2 -= 1
+            y2 = m1 * x2 + b
+        x2 += 1
+
+        return x1, y1, x2, y2
     
     og_img = original_img.copy()
     imgH, imgW, _ = image.shape
@@ -111,18 +132,15 @@ def calculate_pip_width(image, original_img, pixel_per_metric):
     cv2.drawContours(imgcpy, contours, -1, (0, 255, 0), 2)
     # print("length : ",len(contours))
     
-    d_mm = 0  
     marked_img = image.copy()
 
     if len(contours) > 0:
-        # print("hi")
         cnt = max(contours, key=cv2.contourArea)
         frame2 = cv2.cvtColor(og_img, cv2.COLOR_BGR2RGB)
         handsLM = mp.solutions.hands.Hands(max_num_hands=1, min_detection_confidence=0.8, min_tracking_confidence=0.8)
         pr = handsLM.process(frame2)
-        # print(pr.multi_hand_landmarks)
+        print(pr.multi_hand_landmarks)
         if pr.multi_hand_landmarks:
-            # print("inside")
             for hand_landmarks in pr.multi_hand_landmarks:
                 lmlist = []
                 for id, landMark in enumerate(hand_landmarks.landmark):
@@ -133,39 +151,67 @@ def calculate_pip_width(image, original_img, pixel_per_metric):
                     pip_joint = [lmlist[14][1], lmlist[14][2]]
                     mcp_joint = [lmlist[13][1], lmlist[13][2]]
 
+                    midpoint_x = (pip_joint[0] + mcp_joint[0]) / 2
+                    midpoint_y = (pip_joint[1] + mcp_joint[1]) / 2
+                    midpoint = [midpoint_x, midpoint_y]
+
                     m2 = (pip_joint[1] - mcp_joint[1]) / (pip_joint[0] - mcp_joint[0])
                     m1 = -1 / m2
                     b = pip_joint[1] - m1 * pip_joint[0]
 
-                    x1, x2 = pip_joint[0], pip_joint[0]
-                    y1 = m1 * x1 + b
-                    y2 = m1 * x2 + b
+                    #pip_joint
+                    x1_pip, y1_pip, x2_pip, y2_pip = process_point(pip_joint, cnt, m1, b)
+
+                    m2 = (midpoint_y - mcp_joint[1]) / (midpoint_x - mcp_joint[0])
+                    m1 = -1 / m2
+                    b = midpoint_y - m1 * midpoint_x
+
+                    #midpoint
+                    x1_mid, y1_mid, x2_mid, y2_mid = process_point(midpoint, cnt, m1, b)
+
+                    d_mm_pip = calSize(x1_pip, y1_pip, x2_pip, y2_pip, (255, 0, 0), (255, 0, 255), original_img)
+                    d_mm_mid = calSize(x1_mid, y1_mid, x2_mid, y2_mid, (0, 255, 0), (0, 0, 255), original_img)
+
+    largest_d_mm = max(int(d_mm_mid),int(d_mm_pip))
+    return original_img, largest_d_mm, imgcpy, marked_img
+
+def mark_hand_landmarks(image_path):
+
+    mp_hands = mp.solutions.hands
+    hands = mp_hands.Hands()
+    mp_draw = mp.solutions.drawing_utils
 
-                    result = 1.0
-                    while result > 0:
-                        result = cv2.pointPolygonTest(cnt, (x1, y1), False)
-                        x1 += 1
-                        y1 = m1 * x1 + b
-                    x1 -= 1
+    img = image_path
+    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
-                    result = 1.0
-                    while result > 0:
-                        result = cv2.pointPolygonTest(cnt, (x2, y2), False)
-                        x2 -= 1
-                        y2 = m1 * x2 + b
-                    x2 += 1
+    results = hands.process(img_rgb)
 
-                    d_mm, marked_img = calSize(x1, y1, x2, y2, (255, 0, 0), (255, 0, 255), original_img)
+    if results.multi_hand_landmarks:
+        for hand_landmarks in results.multi_hand_landmarks:
+            mp_draw.draw_landmarks(img, hand_landmarks, mp_hands.HAND_CONNECTIONS)
+            
+            mcp = hand_landmarks.landmark[13]
+            pip = hand_landmarks.landmark[14]
+            
+            img_height, img_width, _ = img.shape
+            
+            mcp_x, mcp_y = int(mcp.x * img_width), int(mcp.y * img_height)
+            pip_x, pip_y = int(pip.x * img_width), int(pip.y * img_height)
+            
+            cv2.circle(img, (mcp_x, mcp_y), 10, (255, 0, 0), -1)
+            cv2.circle(img, (pip_x, pip_y), 10, (255, 0, 0), -1)
 
-    return original_img, d_mm, imgcpy, marked_img
+    return img
 
 def show_resized_image(images, titles, scale=0.5):
     num_images = len(images)
-    fig, axes = plt.subplots(1, num_images, figsize=(15, 5))
-
-    if num_images == 1:
-        axes = [axes]
+    
+    fig, axes = plt.subplots(2, 3, figsize=(17, 13))  
+    axes = axes.flatten()  
 
+    for ax in axes[num_images:]:
+        ax.axis('off')
+    
     for ax, img, title in zip(axes, images, titles):
         resized_image = cv2.resize(img, None, fx=scale, fy=scale, interpolation=cv2.INTER_LINEAR)
         ax.imshow(cv2.cvtColor(resized_image, cv2.COLOR_BGR2RGB))
@@ -187,12 +233,24 @@ def get_ring_size(mm_value):
         return ring_size_dict[closest_mm]
 
 st.set_page_config(layout="wide", page_title="Ring Size Measurement")
-
 st.write("## Determine Your Ring Size")
 st.write(
-    "📏 Upload an image of your finger to measure the width and determine your ring size. The measurement will be displayed along with a visual breakdown of the image processing flow."
+    "📏 Upload an image of your hand to measure the finger width and determine your ring size. The measurement will be displayed along with a visual breakdown of the image processing flow."
 )
 st.sidebar.write("## Upload :gear:")
+#~~
+st.write("### Workflow Overview")
+st.image("FlowChart.png", caption="Workflow Overview", use_column_width=True)
+
+st.write("### Detailed Workflow")
+st.write("1. **Hough Circle Transform:** The Hough Circle Transform is a technique used to detect circles in an image. It works by transforming the image into a parameter space, identifying circles based on their radius and center coordinates. This method is effective for locating circular objects, such as a coin, within the image.")
+st.write("2. **Pixel Per Metric Ratio:** The Pixel Per Metric Ratio is used to convert pixel measurements into real-world units. By comparing the pixel length obtained from image analysis (i.e., Hough Circle) with the known real-world measurement of the reference object (coin), we get the ratio. This ratio then allows us to accurately scale and size estimation of objects within the image.")
+st.write("3. **Background Removal:** Removing the background first ensures that only the relevant subject is highlighted. We start by converting the image to grayscale and applying thresholding to distinguish the subject from the background. Erosion and dilation then clean up the image, improving the detection of specific features like individual fingers.")
+st.write("4. **Contour Detection:** We use Contour Detection to find the largest contour, which allows us to outline or draw a boundary around the subject (i.e., hand). This highlights the object's shape and edges, improving the precision of the subject.")
+st.write("5. **Finding Hand Landmarks:** This involves using the MediaPipe library to identify key points on the hand, such as the PIP (Proximal Interphalangeal) and MCP (Metacarpophalangeal) joints of the ring finger. This enables precise tracking and analysis of finger positions and movements.")
+st.write("6. **Determining Finger Width:** Here we use the slope formula `[y = mx + b]` with PIP and MCP points to measure the finger's width. We project outward perpendicularly from the PIP point towards the MCP point, then apply a point polygon test to accurately determine the pixel width of the finger.")
+st.write("7. **Predicting Ring Size:** Predicting Ring Size involves calculating the finger’s diameter using the Pixel Per Metric Ratio and the largest width measurement at the PIP or MCP joint. This diameter is then used to predict the appropriate ring size.")
+#~~
 
 MAX_FILE_SIZE = 5 * 1024 * 1024  # 5MB
 
@@ -204,6 +262,8 @@ def process_image_and_get_results(upload):
     original_img = image_np.copy()
     og_img1 = image_np.copy()
     og_img2 = image_np.copy()
+    img_1 = image_np.copy()
+    hand_lms = mark_hand_landmarks(img_1)
 
     pixel_per_metric, mm_per_pixel, image_with_coin_info = calculate_pixel_per_metric(image_np)
     processed_image = process_image(og_img1)
@@ -211,8 +271,9 @@ def process_image_and_get_results(upload):
 
     ring_size = get_ring_size(width_mm)
     return {
-        "processed_image": pip_mark_img,
+        "processed_image": image_with_pip_width,
         "original_image": og_img2,
+        "hand_lm_marked_image": hand_lms,
         "image_with_coin_info": image_with_coin_info,
         "contour_image": contour_image,
         "width_mm": width_mm,
@@ -246,8 +307,8 @@ if my_upload is not None:
             st.write("## How It Works")
             st.write("Here's a step-by-step breakdown of how your image is processed to determine your ring size:")
             img_stream = show_resized_image(
-                [results["original_image"], results["image_with_coin_info"], results["contour_image"], results["processed_image"]],
-                ['Original Image', 'Image with Coin Info', 'Contour Boundary Image', 'Ring Finger Width'],
+                [results["original_image"], results["image_with_coin_info"], results["contour_image"], results["hand_lm_marked_image"], results["processed_image"]],
+                ['Original Image', 'Image with Coin Info', 'Contour Boundary Image', 'Hand Landmarks', 'Ring Finger Width'],
                 scale=0.5
             )
             st.image(img_stream, caption="Processing Flow", use_column_width=True)