Update app.py

app.py

@@ -3,152 +3,143 @@ import numpy as np
 import json
 import gradio as gr
 import os
+import xml.etree.ElementTree as ET
 
 # ---------------- Helper functions ----------------
 def get_rotated_rect_corners(x, y, w, h, rotation_deg):
     rot_rad = np.deg2rad(rotation_deg)
     cos_r = np.cos(rot_rad)
     sin_r = np.sin(rot_rad)
-
-    R = np.array([[cos_r, -sin_r],
-                  [sin_r,  cos_r]])
-
-    cx = x + w/2
-    cy = y + h/2
-
-    local_corners = np.array([
-        [-w/2, -h/2],
-        [ w/2, -h/2],
-        [ w/2,  h/2],
-        [-w/2,  h/2]
-    ])
-
+    R = np.array([[cos_r, -sin_r], [sin_r, cos_r]])
+    cx, cy = x + w/2, y + h/2
+    local_corners = np.array([[-w/2, -h/2],[w/2,-h/2],[w/2,h/2],[-w/2,h/2]])
     rotated_corners = np.dot(local_corners, R.T)
     corners = rotated_corners + np.array([cx, cy])
     return corners.astype(np.float32)
 
 def preprocess_gray_clahe(img):
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-    clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8))
+    clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8))
     return clahe.apply(gray)
 
 def detect_and_match(img1_gray, img2_gray, method="SIFT", ratio_thresh=0.78):
-    if method == "SIFT":
-        sift = cv2.SIFT_create(nfeatures=5000)
-        kp1, des1 = sift.detectAndCompute(img1_gray, None)
-        kp2, des2 = sift.detectAndCompute(img2_gray, None)
-        matcher = cv2.BFMatcher(cv2.NORM_L2)
-    elif method == "ORB":
-        orb = cv2.ORB_create(5000)
-        kp1, des1 = orb.detectAndCompute(img1_gray, None)
-        kp2, des2 = orb.detectAndCompute(img2_gray, None)
-        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
-    elif method == "BRISK":
-        brisk = cv2.BRISK_create()
-        kp1, des1 = brisk.detectAndCompute(img1_gray, None)
-        kp2, des2 = brisk.detectAndCompute(img2_gray, None)
-        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
-    elif method == "KAZE":
-        kaze = cv2.KAZE_create()
-        kp1, des1 = kaze.detectAndCompute(img1_gray, None)
-        kp2, des2 = kaze.detectAndCompute(img2_gray, None)
-        matcher = cv2.BFMatcher(cv2.NORM_L2)
-    elif method == "AKAZE":
-        akaze = cv2.AKAZE_create()
-        kp1, des1 = akaze.detectAndCompute(img1_gray, None)
-        kp2, des2 = akaze.detectAndCompute(img2_gray, None)
-        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
-    else:
-        return None, None, []
-
-    if des1 is None or des2 is None:
-        return None, None, []
-
-    raw_matches = matcher.knnMatch(des1, des2, k=2)
-    good = []
-    for m, n in raw_matches:
-        if m.distance < ratio_thresh * n.distance:
-            good.append(m)
-    return kp1, kp2, good
-
-# ---------------- Main Homography Function ----------------
-def homography_all_detectors(flat_file, persp_file, json_file):
-    flat_img = cv2.imread(flat_file)
-    persp_img = cv2.imread(persp_file)
-    mockup = json.load(open(json_file.name))
+    if method == "SIFT": sift=cv2.SIFT_create(nfeatures=5000); matcher=cv2.BFMatcher(cv2.NORM_L2)
+    elif method=="ORB": orb=cv2.ORB_create(5000); matcher=cv2.BFMatcher(cv2.NORM_HAMMING)
+    elif method=="BRISK": brisk=cv2.BRISK_create(); matcher=cv2.BFMatcher(cv2.NORM_HAMMING)
+    elif method=="KAZE": kaze=cv2.KAZE_create(); matcher=cv2.BFMatcher(cv2.NORM_L2)
+    elif method=="AKAZE": akaze=cv2.AKAZE_create(); matcher=cv2.BFMatcher(cv2.NORM_HAMMING)
+    else: return None,None,[]
 
-    roi_data = mockup["printAreas"][0]["position"]
-    roi_x = roi_data["x"]
-    roi_y = roi_data["y"]
-    roi_w = mockup["printAreas"][0]["width"]
-    roi_h = mockup["printAreas"][0]["height"]
-    roi_rot_deg = mockup["printAreas"][0]["rotation"]
+    kp1, des1 = None, None
+    kp2, des2 = None, None
 
-    flat_gray = preprocess_gray_clahe(flat_img)
-    persp_gray = preprocess_gray_clahe(persp_img)
+    if method=="SIFT": kp1, des1 = sift.detectAndCompute(img1_gray,None); kp2, des2 = sift.detectAndCompute(img2_gray,None)
+    elif method=="ORB": kp1, des1 = orb.detectAndCompute(img1_gray,None); kp2, des2 = orb.detectAndCompute(img2_gray,None)
+    elif method=="BRISK": kp1, des1 = brisk.detectAndCompute(img1_gray,None); kp2, des2 = brisk.detectAndCompute(img2_gray,None)
+    elif method=="KAZE": kp1, des1 = kaze.detectAndCompute(img1_gray,None); kp2, des2 = kaze.detectAndCompute(img2_gray,None)
+    elif method=="AKAZE": kp1, des1 = akaze.detectAndCompute(img1_gray,None); kp2, des2 = akaze.detectAndCompute(img2_gray,None)
 
-    methods = ["SIFT", "ORB", "BRISK", "KAZE", "AKAZE"]
-    gallery_images = []
-    download_files = []
+    if des1 is None or des2 is None: return None,None,[]
 
-    for method in methods:
-        kp1, kp2, good_matches = detect_and_match(flat_gray, persp_gray, method=method)
-
-        if kp1 is None or kp2 is None or len(good_matches) < 4:
-            continue  # skip if no matches
-
-        src_pts = np.float32([kp1[m.queryIdx].pt for m in good_matches]).reshape(-1,1,2)
-        dst_pts = np.float32([kp2[m.trainIdx].pt for m in good_matches]).reshape(-1,1,2)
-        H, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
-
-        if H is None:
-            continue
+    raw_matches = matcher.knnMatch(des1, des2, k=2)
+    good = [m for m,n in raw_matches if m.distance < ratio_thresh*n.distance]
+    return kp1, kp2, good
 
-        roi_corners_flat = get_rotated_rect_corners(roi_x, roi_y, roi_w, roi_h, roi_rot_deg)
-        roi_corners_persp = cv2.perspectiveTransform(roi_corners_flat.reshape(-1,1,2), H).reshape(-1,2)
+def parse_xml_points(xml_file):
+    tree = ET.parse(xml_file)
+    root = tree.getroot()
+    points=[]
+    for pt_type in ["TopLeft","TopRight","BottomLeft","BottomRight"]:
+        elem=root.find(f".//point[@type='{pt_type}']")
+        x=float(elem.get("x")); y=float(elem.get("y"))
+        points.extend([x,y])
+    return np.array(points,dtype=np.float32).reshape(-1,2)
 
-        persp_debug = persp_img.copy()
-        cv2.polylines(persp_debug, [roi_corners_persp.astype(int)], True, (0,255,0), 2)
-        for (px, py) in roi_corners_persp:
-            cv2.circle(persp_debug, (int(px), int(py)), 5, (255,0,0), -1)
+# ---------------- Main Homography Function ----------------
+def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
+    flat_img=cv2.imread(flat_file)
+    persp_img=cv2.imread(persp_file)
+    mockup=json.load(open(json_file.name))
+    roi_data=mockup["printAreas"][0]["position"]
+    roi_x, roi_y=roi_data["x"], roi_data["y"]
+    roi_w=mockup["printAreas"][0]["width"]
+    roi_h=mockup["printAreas"][0]["height"]
+    roi_rot_deg=mockup["printAreas"][0]["rotation"]
 
-        # Convert BGR -> RGB for display
-        result_rgb = cv2.cvtColor(persp_debug, cv2.COLOR_BGR2RGB)
+    flat_gray=preprocess_gray_clahe(flat_img)
+    persp_gray=preprocess_gray_clahe(persp_img)
+    methods=["SIFT","ORB","BRISK","KAZE","AKAZE"]
 
-        # Save result for download
-        base_name = os.path.splitext(os.path.basename(persp_file))[0]
+    gallery_images=[]
+    download_files=[]
 
-        # Save with same name + detector
-        file_name = f"{base_name}_{method.lower()}.png"
-        cv2.imwrite(file_name, cv2.cvtColor(result_rgb, cv2.COLOR_RGB2BGR))
+    xml_points=parse_xml_points(xml_file.name)
 
-        gallery_images.append((result_rgb, f"{method} Result"))
+    for method in methods:
+        kp1,kp2,good_matches=detect_and_match(flat_gray,persp_gray,method=method)
+        if kp1 is None or kp2 is None or len(good_matches)<4: continue
+
+        # Feature matching lines
+        match_img = cv2.drawMatches(flat_img,kp1,persp_img,kp2,good_matches,None,flags=2)
+
+        src_pts=np.float32([kp1[m.queryIdx].pt for m in good_matches]).reshape(-1,1,2)
+        dst_pts=np.float32([kp2[m.trainIdx].pt for m in good_matches]).reshape(-1,1,2)
+        H,_ = cv2.findHomography(src_pts,dst_pts,cv2.RANSAC,5.0)
+        if H is None: continue
+
+        # ROI mapping
+        roi_corners_flat = get_rotated_rect_corners(roi_x,roi_y,roi_w,roi_h,roi_rot_deg)
+        roi_corners_persp = cv2.perspectiveTransform(roi_corners_flat.reshape(-1,1,2),H).reshape(-1,2)
+        persp_roi = persp_img.copy()
+        cv2.polylines(persp_roi,[roi_corners_persp.astype(int)],True,(0,255,0),2)
+        for px,py in roi_corners_persp: cv2.circle(persp_roi,(int(px),int(py)),5,(255,0,0),-1)
+
+        # XML ground truth mapping
+        xml_gt_img = persp_img.copy()
+        xml_mapped = cv2.perspectiveTransform(xml_points.reshape(-1,1,2),H).reshape(-1,2)
+        for px,py in xml_mapped: cv2.circle(xml_gt_img,(int(px),int(py)),5,(0,0,255),-1)
+
+        # Convert all to RGB
+        flat_rgb=cv2.cvtColor(flat_img,cv2.COLOR_BGR2RGB)
+        persp_roi_rgb=cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB)
+        match_rgb=cv2.cvtColor(match_img,cv2.COLOR_BGR2RGB)
+        xml_rgb=cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB)
+
+        # Combine all 4 in one gallery list per detector
+        combined = np.hstack([cv2.resize(flat_rgb,(256,256)),
+                              cv2.resize(match_rgb,(256,256)),
+                              cv2.resize(persp_roi_rgb,(256,256)),
+                              cv2.resize(xml_rgb,(256,256))])
+        gallery_images.append((combined,f"{method} Detector"))
+
+        # Save for download
+        base_name=os.path.splitext(os.path.basename(persp_file))[0]
+        file_name=f"{base_name}_{method.lower()}.png"
+        cv2.imwrite(file_name,combined[:,:,::-1]) # RGB->BGR
         download_files.append(file_name)
 
-    # return gallery + 5 download files (pad with None if less)
-    while len(download_files) < 5:
-        download_files.append(None)
-
-    return [gallery_images] + download_files[:5]
+    while len(download_files)<5: download_files.append(None)
+    return [gallery_images]+download_files[:5]
 
 # ---------------- Gradio UI ----------------
-iface = gr.Interface(
+iface=gr.Interface(
     fn=homography_all_detectors,
     inputs=[
-        gr.Image(label="Upload Flat Image", type="filepath"),
-        gr.Image(label="Upload Perspective Image", type="filepath"),
-        gr.File(label="Upload mockup.json", file_types=[".json"])
+        gr.Image(label="Upload Flat Image",type="filepath"),
+        gr.Image(label="Upload Perspective Image",type="filepath"),
+        gr.File(label="Upload mockup.json",file_types=[".json"]),
+        gr.File(label="Upload XML file",file_types=[".xml"])
     ],
     outputs=[
-        gr.Gallery(label="Results (per Detector)", show_label=True),
+        gr.Gallery(label="Results per Detector",show_label=True),
         gr.File(label="Download SIFT Result"),
         gr.File(label="Download ORB Result"),
         gr.File(label="Download BRISK Result"),
         gr.File(label="Download KAZE Result"),
         gr.File(label="Download AKAZE Result")
     ],
-    title="Homography ROI Projection with Multiple Feature Detectors",
-    description="Upload flat & perspective images with mockup.json. The system will project ROI using SIFT, ORB, BRISK, KAZE, and AKAZE. Each result can be viewed and downloaded."
+    title="Homography ROI Projection with Feature Matching & XML GT",
+    description="Flat + Perspective images with mockup.json & XML. Shows 4 views per detector: Flat, Feature Matches, ROI Projection, XML Ground Truth."
 )
 
 iface.launch()