Update app.py

app.py

@@ -65,26 +65,8 @@ def fit_to_box(img, target_h=600, target_w=600):
     canvas[top:top+new_h, left:left+new_w] = resized
     return canvas
 
-# ---------------- NEW: Remap keypoints to boxed image coords ----------------
-def remap_keypoints_to_box(kps, orig_shape, target_h=600, target_w=600):
-    h, w = orig_shape[:2]
-    scale = min(target_w / w, target_h / h)
-    new_w, new_h = int(w * scale), int(h * scale)
-    top = (target_h - new_h) // 2
-    left = (target_w - new_w) // 2
-
-    kps_new = []
-    for kp in kps:
-        x, y = kp.pt
-        x_new = x * scale + left
-        y_new = y * scale + top
-        kps_new.append(cv2.KeyPoint(x_new, y_new, max(1.0, kp.size * scale),
-                                    kp.angle, kp.response, kp.octave, kp.class_id))
-    return kps_new
-
 # ---------------- Add Heading on Top ----------------
 def add_heading(img, text):
-    # add white band on top
     h, w = img.shape[:2]
     band_h = 40
     canvas = np.ones((h+band_h, w, 3), dtype=np.uint8) * 255
@@ -94,7 +76,7 @@ def add_heading(img, text):
     return canvas
 
 # ---------------- Main Function ----------------
-def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
+def homography_show_three(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))
@@ -107,67 +89,51 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
     persp_gray = preprocess_gray_clahe(persp_img)
     xml_points = parse_xml_points(xml_file.name)
 
-    methods = ["SIFT","ORB","BRISK","KAZE","AKAZE"]
-    gallery_paths = []
-    download_files = []
-
-    for method in methods:
-        kp1,kp2,good_matches = detect_and_match(flat_gray,persp_gray,method)
-        if kp1 is None or kp2 is None or len(good_matches)<4: continue
-
-        flat_box = fit_to_box(flat_img, 600, 600)
-        persp_box = fit_to_box(persp_img, 600, 600)
-
-        kp1_box = remap_keypoints_to_box(kp1, flat_img.shape, 600, 600)
-        kp2_box = remap_keypoints_to_box(kp2, persp_img.shape, 600, 600)
-
-        match_img = cv2.drawMatches(flat_box, kp1_box, persp_box, kp2_box, good_matches, None, flags=2)
+    # --- SIFT (only to get Homography) ---
+    kp1,kp2,good_matches = detect_and_match(flat_gray,persp_gray,"SIFT")
+    if kp1 is None or kp2 is None or len(good_matches)<4:
+        return ["Not enough matches found"], None, None, None
 
-        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
+    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)
 
-        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)
+    # --- 1. Flat image with ROI from JSON ---
+    flat_with_roi = flat_img.copy()
+    roi_corners_flat = get_rotated_rect_corners(roi_x,roi_y,roi_w,roi_h,roi_rot_deg)
+    cv2.polylines(flat_with_roi,[roi_corners_flat.astype(int)],True,(0,255,0),2)
+    for px,py in roi_corners_flat: cv2.circle(flat_with_roi,(int(px),int(py)),5,(255,0,0),-1)
 
-        xml_gt_img = persp_img.copy()
-        ordered_pts = ['TopLeft', 'TopRight', 'BottomRight', 'BottomLeft']
-        xml_polygon = [xml_points[pt] for pt in ordered_pts]
-        pts = np.array(xml_polygon, np.int32).reshape((-1,1,2))
-        cv2.polylines(xml_gt_img,[pts],isClosed=True,color=(255,0,0),thickness=3)
+    # --- 2. Perspective image with Homography ROI ---
+    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)
 
-        flat_rgb = fit_to_box(cv2.cvtColor(flat_img,cv2.COLOR_BGR2RGB),600,600)
-        match_rgb = fit_to_box(cv2.cvtColor(match_img,cv2.COLOR_BGR2RGB),600,600)
-        roi_rgb = fit_to_box(cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB),600,600)
-        xml_rgb = fit_to_box(cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB),600,600)
+    # --- 3. Perspective image with Ground Truth ROI from XML ---
+    xml_gt_img = persp_img.copy()
+    ordered_pts = ['TopLeft', 'TopRight', 'BottomRight', 'BottomLeft']
+    xml_polygon = [xml_points[pt] for pt in ordered_pts]
+    pts = np.array(xml_polygon, np.int32).reshape((-1,1,2))
+    cv2.polylines(xml_gt_img,[pts],isClosed=True,color=(255,0,0),thickness=3)
 
-        # Add headings
-        flat_rgb = add_heading(flat_rgb, "Flat Image")
-        match_rgb = add_heading(match_rgb, "Flat -> Perspective Feature Matching")
-        roi_rgb = add_heading(roi_rgb, "Perspective Image with Homography ROI  ")
-        xml_rgb = add_heading(xml_rgb, "    Perspective GT ROI")
+    # Resize + Headings
+    flat_rgb = add_heading(fit_to_box(cv2.cvtColor(flat_with_roi,cv2.COLOR_BGR2RGB),600,600), "Flat Image with JSON ROI")
+    roi_rgb  = add_heading(fit_to_box(cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB),600,600), "Perspective Image with Homography ROI")
+    xml_rgb  = add_heading(fit_to_box(cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB),600,600), "Perspective Image with GT ROI")
 
-        # Merge 2x2 grid
-        top = np.hstack([flat_rgb, match_rgb])
-        bottom = np.hstack([roi_rgb, xml_rgb])
-        combined_grid = np.vstack([top, bottom])
+    # Side-by-side 1 row
+    combined = np.hstack([flat_rgb, roi_rgb, xml_rgb])
 
-        base_name = os.path.splitext(os.path.basename(persp_file))[0]
-        file_name = f"{base_name}_{method.lower()}.png"
-        cv2.imwrite(file_name, cv2.cvtColor(combined_grid,cv2.COLOR_RGB2BGR))
-        gallery_paths.append(file_name)
-        download_files.append(file_name)
+    base_name = os.path.splitext(os.path.basename(persp_file))[0]
+    file_name = f"{base_name}_result.png"
+    cv2.imwrite(file_name, cv2.cvtColor(combined,cv2.COLOR_RGB2BGR))
 
-    while len(download_files)<5: download_files.append(None)
-    return gallery_paths, download_files[0], download_files[1], download_files[2], download_files[3], download_files[4]
+    return [file_name], file_name, None, None, None
 
 # ---------------- Gradio UI ----------------
 iface = gr.Interface(
-    fn=homography_all_detectors,
+    fn=homography_show_three,
     inputs=[
         gr.Image(label="Upload Flat Image",type="filepath"),
         gr.Image(label="Upload Perspective Image",type="filepath"),
@@ -175,15 +141,11 @@ iface = gr.Interface(
         gr.File(label="Upload XML file",file_types=[".xml"])
     ],
     outputs=[
-        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")
+        gr.Gallery(label="Final Result",show_label=True),
+        gr.File(label="Download Result")
     ],
-    title="Homography ROI + Feature Matching + XML GT",
-    description="Flat + Perspective images with mockup.json & XML. Aspect ratio preserved, images centered in uniform boxes, headings added."
+    title="Homography ROI vs GT ROI",
+    description="Shows Flat image with JSON ROI, Perspective with Homography ROI, and Perspective with GT ROI in one row."
 )
 
 iface.launch()