import cv2 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, sin_r = np.cos(rot_rad), np.sin(rot_rad) 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) return (rotated_corners + np.array([cx,cy])).astype(np.float32) def preprocess_gray_clahe(img): gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 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": detector=cv2.SIFT_create(nfeatures=5000); matcher=cv2.BFMatcher(cv2.NORM_L2) elif method=="ORB": detector=cv2.ORB_create(5000); matcher=cv2.BFMatcher(cv2.NORM_HAMMING) elif method=="BRISK": detector=cv2.BRISK_create(); matcher=cv2.BFMatcher(cv2.NORM_HAMMING) elif method=="KAZE": detector=cv2.KAZE_create(); matcher=cv2.BFMatcher(cv2.NORM_L2) elif method=="AKAZE": detector=cv2.AKAZE_create(); matcher=cv2.BFMatcher(cv2.NORM_HAMMING) else: return None,None,[] kp1, des1 = detector.detectAndCompute(img1_gray,None) kp2, des2 = detector.detectAndCompute(img2_gray,None) if des1 is None or des2 is None: return None,None,[] 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 def parse_xml_points(xml_file): tree = ET.parse(xml_file) root = tree.getroot() transform = root.find('.//transform') points = {} for pt in transform.findall('.//point'): pt_type = pt.attrib['type'] x = float(pt.attrib['x']) y = float(pt.attrib['y']) points[pt_type] = (x, y) return points # ---------------- Fit-to-Box Helper ---------------- def fit_to_box(img, target_h=600, target_w=600): h, w = img.shape[:2] scale = min(target_w/w, target_h/h) # preserve aspect ratio new_w, new_h = int(w*scale), int(h*scale) resized = cv2.resize(img, (new_w, new_h)) # symmetric padding top = (target_h - new_h) // 2 bottom = target_h - new_h - top left = (target_w - new_w) // 2 right = target_w - new_w - left canvas = np.ones((target_h, target_w, 3), dtype=np.uint8) * 255 canvas[top:top+new_h, left:left+new_w] = resized return canvas # ---------------- Add Heading on Top ---------------- def add_heading(img, text): h, w = img.shape[:2] band_h = 40 canvas = np.ones((h+band_h, w, 3), dtype=np.uint8) * 255 canvas[band_h:] = img cv2.putText(canvas, text, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,0,0), 2, cv2.LINE_AA) return canvas # ---------------- Placeholder if matching fails ---------------- def get_placeholder(method): canvas = np.ones((600, 1800, 3), dtype=np.uint8) * 255 cv2.putText(canvas, f"{method}: Not enough feature matching", (50, 300), cv2.FONT_HERSHEY_SIMPLEX, 2, (0,0,255), 3, cv2.LINE_AA) return canvas # ---------------- Main 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, roi_h = mockup["printAreas"][0]["width"], mockup["printAreas"][0]["height"] roi_rot_deg = mockup["printAreas"][0]["rotation"] flat_gray = preprocess_gray_clahe(flat_img) 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: placeholder = get_placeholder(method) fname = f"{method.lower()}_placeholder.png" cv2.imwrite(fname, placeholder) gallery_paths.append(fname) download_files.append(fname) 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) if H is None: placeholder = get_placeholder(method) fname = f"{method.lower()}_placeholder.png" cv2.imwrite(fname, placeholder) gallery_paths.append(fname) download_files.append(fname) continue # 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) # 2. Perspective 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),5) for px,py in roi_corners_persp: cv2.circle(persp_roi,(int(px),int(py)),5,(255,0,0),5) # 3. Perspective with GT 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=5) # Convert to RGB + resize + add headings flat_rgb = add_heading(fit_to_box(cv2.cvtColor(flat_with_roi,cv2.COLOR_BGR2RGB),600,600), "Flat Image with ROI") roi_rgb = add_heading(fit_to_box(cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB),600,600), "Perspective Homography ROI") xml_rgb = add_heading(fit_to_box(cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB),600,600), " Perspective GT ROI") # Concatenate side by side combined_row = 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_row,cv2.COLOR_RGB2BGR)) gallery_paths.append(file_name) download_files.append(file_name) 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] # ---------------- Gradio UI ---------------- 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.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") ], title="Homography ROI + XML GT", description="Flat with ROI + Perspective ROI (Homography + GT). Aspect ratio preserved, images centered in uniform boxes, headings added." ) iface.launch()