File size: 6,239 Bytes
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
import gradio as gr
import cv2
import numpy as np
import matplotlib.pyplot as plt
import json
import math
import os
def ransac(image1, image2, detector_type):
"""
Finds the homography matrix using the RANSAC algorithm with the selected feature detector.
"""
gray1 = cv2.cvtColor(image1, cv2.COLOR_RGB2GRAY)
gray2 = cv2.cvtColor(image2, cv2.COLOR_RGB2GRAY)
if detector_type == "SIFT":
detector = cv2.SIFT_create()
matcher = cv2.FlannBasedMatcher(dict(algorithm=1, trees=5), dict(checks=50))
elif detector_type == "ORB":
detector = cv2.ORB_create()
matcher = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)
elif detector_type == "BRISK":
detector = cv2.BRISK_create()
matcher = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)
elif detector_type == "AKAZE":
detector = cv2.AKAZE_create()
matcher = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)
elif detector_type == "KAZE":
detector = cv2.KAZE_create()
matcher = cv2.BFMatcher(cv2.NORM_L2, crossCheck=True)
else:
return None
kp1, des1 = detector.detectAndCompute(gray1, None)
kp2, des2 = detector.detectAndCompute(gray2, None)
if des1 is None or des2 is None or len(kp1) < 2 or len(kp2) < 2:
return None
try:
if detector_type == "SIFT":
matches = matcher.knnMatch(des1, des2, k=2)
good_matches = []
if matches:
for m, n in matches:
if m.distance < 0.75 * n.distance:
good_matches.append(m)
else:
matches = matcher.match(des1, des2)
good_matches = sorted(matches, key=lambda x: x.distance)
except cv2.error as e:
print(f"Error during matching: {e}")
return None
if len(good_matches) > 10:
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)
return H
else:
return None
def get_bounding_box_points(json_data):
"""
Extracts and calculates the four corner points of the bounding box, assuming x,y are top-left.
"""
print_area = json_data['printAreas'][0]
x = print_area['position']['x']
y = print_area['position']['y']
w = print_area['width']
h = print_area['height']
rotation_deg = print_area['rotation']
points = np.float32([
[0, 0],
[w, 0],
[w, h],
[0, h]
]).reshape(-1, 1, 2)
rotation_rad = math.radians(rotation_deg)
cos_theta = math.cos(rotation_rad)
sin_theta = math.sin(rotation_rad)
rotation_matrix = np.array([
[cos_theta, -sin_theta],
[sin_theta, cos_theta]
])
rotated_points = np.dot(points.reshape(-1, 2), rotation_matrix.T)
final_points = rotated_points + np.array([x, y])
return final_points.reshape(-1, 1, 2)
def process_and_plot_all_detectors(image1_np, image2_np, json_file):
"""
Processes the images with all available detectors and returns image data for display and download.
"""
if image1_np is None or image2_np is None:
return [None] * 6
try:
with open(json_file.name, 'r') as f:
data = json.load(f)
except Exception as e:
print(f"Error: Could not read JSON file. {e}")
return [None] * 6
detectors = ["SIFT", "ORB", "BRISK", "AKAZE", "KAZE"]
gallery_images = []
download_files = [None] * 5
for i, detector_type in enumerate(detectors):
H = ransac(image1_np, image2_np, detector_type)
if H is not None:
box_points = get_bounding_box_points(data)
output_flat_img = image1_np.copy()
cv2.polylines(output_flat_img, [np.int32(box_points)], isClosed=True, color=(0, 0, 255), thickness=5)
transformed_box_points = cv2.perspectiveTransform(box_points, H)
output_perspective_img = image2_np.copy()
cv2.polylines(output_perspective_img, [np.int32(transformed_box_points)], isClosed=True, color=(0, 0, 255), thickness=5)
fig, axes = plt.subplots(1, 3, figsize=(18, 6))
axes[0].imshow(cv2.cvtColor(output_flat_img, cv2.COLOR_BGR2RGB))
axes[0].set_title(f'Original (Flat) - {detector_type}')
axes[0].axis('off')
axes[1].imshow(cv2.cvtColor(image2_np, cv2.COLOR_BGR2RGB))
axes[1].set_title('Original (Perspective)')
axes[1].axis('off')
axes[2].imshow(cv2.cvtColor(output_perspective_img, cv2.COLOR_BGR2RGB))
axes[2].set_title('Projected Bounding Box')
axes[2].axis('off')
plt.tight_layout()
file_name = f"result_{detector_type.lower()}.png"
plt.savefig(file_name)
plt.close(fig)
gallery_images.append(file_name)
download_files[i] = file_name
else:
print(f"Warning: Homography matrix could not be found with {detector_type} detector. Skipping this result.")
# We don't append None to the gallery_images list to avoid the error.
# download_files[i] remains None, which is handled correctly by gr.File.
return [gallery_images] + download_files
iface = gr.Interface(
fn=process_and_plot_all_detectors,
inputs=[
gr.Image(type="numpy", label="Image 1 (Flat)"),
gr.Image(type="numpy", label="Image 2 (Perspective)"),
gr.File(type="filepath", label="JSON File")
],
outputs=[
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")
],
title="Homography and Bounding Box Projection with All Detectors",
description="Upload two images and a JSON file to see the bounding box projection for all 5 feature extraction methods. Each result can be downloaded separately."
)
iface.launch() |