File size: 4,527 Bytes
0d72d25
 
 
 
 
5138913
0d72d25
5138913
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d72d25
5138913
 
0d72d25
 
5138913
 
 
 
0d72d25
 
5138913
0d72d25
 
5138913
0d72d25
5138913
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d72d25
 
5138913
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
438fcec
0d72d25
5138913
dd80a33
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d72d25
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import gradio as gr
import cv2
import numpy as np
import json
import math
import matplotlib.pyplot as plt

# === 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, 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) + np.array([cx, cy])
    return rotated_corners.astype(np.float32)

def preprocess_gray_clahe(img):
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8))
    return clahe.apply(gray)

def detect_and_match(img1_gray, img2_gray, detector_type, ratio_thresh=0.78):
    if detector_type == "SIFT":
        detector = cv2.SIFT_create(nfeatures=5000)
        matcher = cv2.BFMatcher(cv2.NORM_L2)
    elif detector_type == "BRISK":
        detector = cv2.BRISK_create()
        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
    elif detector_type == "ORB":
        detector = cv2.ORB_create(5000)
        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
    elif detector_type == "AKAZE":
        detector = cv2.AKAZE_create()
        matcher = cv2.BFMatcher(cv2.NORM_HAMMING)
    elif detector_type == "KAZE":
        detector = cv2.KAZE_create()
        matcher = cv2.BFMatcher(cv2.NORM_L2)
    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 kp1, kp2, []

    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 get_roi_points_from_json(json_file):
    data = json.load(json_file)
    area = data["printAreas"][0]
    x = area["position"]["x"]
    y = area["position"]["y"]
    w = area["width"]
    h = area["height"]
    rot = area["rotation"]
    return x, y, w, h, rot

def process_images(flat_img, persp_img, json_file):
    # Preprocess
    flat_gray = preprocess_gray_clahe(flat_img)
    persp_gray = preprocess_gray_clahe(persp_img)
    x, y, w, h, rot = get_roi_points_from_json(json_file)

    detectors = ["SIFT","BRISK","ORB","AKAZE","KAZE"]
    gallery_images = []

    for det in detectors:
        kp1, kp2, matches = detect_and_match(flat_gray, persp_gray, det)
        if len(matches) < 4:
            # Skip if too few matches
            continue

        src_pts = np.float32([kp1[m.queryIdx].pt for m in matches]).reshape(-1,1,2)
        dst_pts = np.float32([kp2[m.trainIdx].pt for m in matches]).reshape(-1,1,2)
        H, _ = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC,5.0)

        # ROI in flat
        roi_flat = get_rotated_rect_corners(x,y,w,h,rot)
        flat_copy = flat_img.copy()
        cv2.polylines(flat_copy, [roi_flat.astype(int)], True, (0,0,255),2)

        # Project ROI to perspective
        roi_persp = cv2.perspectiveTransform(roi_flat.reshape(-1,1,2), H).reshape(-1,2)
        persp_copy = persp_img.copy()
        cv2.polylines(persp_copy, [roi_persp.astype(int)], True, (0,255,0),2)
        for px, py in roi_persp:
            cv2.circle(persp_copy, (int(px),int(py)), 5, (255,0,0), -1)

        # Side-by-side for this detector
        fig, ax = plt.subplots(1,2,figsize=(12,6))
        ax[0].imshow(flat_copy)
        ax[0].set_title(f"Flat ROI - {det}")
        ax[0].axis("off")
        ax[1].imshow(persp_copy)
        ax[1].set_title(f"Perspective ROI - {det}")
        ax[1].axis("off")
        plt.tight_layout()
        filename = f"{det}_result.png"
        plt.savefig(filename)
        plt.close(fig)
        gallery_images.append(filename)

    return gallery_images

iface = gr.Interface(
    fn=process_images,
    inputs=[
        gr.Image(type="numpy", label="Flat Image"),
        gr.Image(type="numpy", label="Perspective Image"),
        gr.File(type="file", label="JSON File")
    ],  # <-- ye closing bracket should be ]
    outputs=[  # <-- starts a new list
        gr.Gallery(label="Results"),
        gr.File(label="Download SIFT Result"),
        gr.File(label="Download ORB Result"),
        gr.File(label="Download BRISK Result"),
        gr.File(label="Download AKAZE Result"),
        gr.File(label="Download KAZE Result")
    ],  # <-- should be ] not )
    title="Homography & ROI Projection",
    description="..."
)