Spaces:
Sleeping
Sleeping
File size: 27,386 Bytes
699b5d2 29bcdf2 699b5d2 29bcdf2 699b5d2 af547ff 699b5d2 af547ff c2ddd50 2cc5732 c2ddd50 29bcdf2 8be899f af547ff c2ddd50 af547ff c2ddd50 2cc5732 af547ff 2cc5732 af547ff 2cc5732 af547ff 2cc5732 699b5d2 2cc5732 699b5d2 2cc5732 699b5d2 2cc5732 1cede7c 2cc5732 af547ff 2cc5732 699b5d2 af547ff 2cc5732 699b5d2 2cc5732 af547ff 2cc5732 e4bd3a9 ad617e9 2cc5732 af547ff 2cc5732 af547ff e4bd3a9 af547ff 2cc5732 e4bd3a9 2cc5732 e4bd3a9 2cc5732 699b5d2 2cc5732 c2ddd50 699b5d2 c2ddd50 d58b258 2cc5732 af547ff d58b258 af547ff d58b258 af547ff d58b258 c2ddd50 af547ff d58b258 c2ddd50 2cc5732 c2ddd50 2cc5732 af547ff 2cc5732 af547ff 2cc5732 af547ff 2cc5732 af547ff 2cc5732 d58b258 2cc5732 e4bd3a9 699b5d2 c2ddd50 2cc5732 e4bd3a9 c2ddd50 2cc5732 af547ff d58b258 2cc5732 c2ddd50 e4bd3a9 b6905f2 2cc5732 c2ddd50 af547ff 2cc5732 c2ddd50 af547ff 2cc5732 af547ff e4bd3a9 af547ff e4bd3a9 af547ff e4bd3a9 af547ff e4bd3a9 c2ddd50 2cc5732 29bcdf2 8be899f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 |
import os
import random
import string
import io
import joblib
import cv2
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, models
from tensorflow.keras.applications import ResNet50, EfficientNetB0
from tensorflow.keras.applications.resnet import preprocess_input
from tensorflow.keras.applications.efficientnet import preprocess_input
from tensorflow.keras.layers import Lambda # Đảm bảo nhập Lambda từ tensorflow.keras.layers
from keras.applications import ResNet50
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import (
confusion_matrix,
ConfusionMatrixDisplay,
accuracy_score,
precision_score,
recall_score,
f1_score
)
import matplotlib.pyplot as plt
from skimage.feature import graycomatrix, graycoprops
from PIL import Image
import streamlit as st
import cloudinary
import cloudinary.uploader
from cloudinary.utils import cloudinary_url
import torch
# Cloudinary Configuration
cloudinary.config(
cloud_name = os.getenv("CLOUD"),
api_key = os.getenv("API"),
api_secret = os.getenv("SECRET"),
secure=True
)
# Set page config
st.set_page_config(
page_title="Stone Detection & Classification",
page_icon="🪨",
layout="wide"
)
def generate_random_filename(extension="png"):
random_string = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
return f"temp_image_{random_string}.{extension}"
# Custom CSS to improve the appearance
st.markdown("""
<style>
.main {
padding: 2rem;
}
.stButton>button {
width: 100%;
margin-top: 1rem;
}
.upload-text {
text-align: center;
padding: 2rem;
}
</style>
""", unsafe_allow_html=True)
def upload_to_cloudinary(file_path, label):
"""
Upload file to Cloudinary with specified label as folder
"""
try:
# Upload to Cloudinary
upload_result = cloudinary.uploader.upload(
file_path,
folder=label,
public_id=f"{label}_{os.path.basename(file_path)}"
)
# Generate optimized URLs
optimize_url, _ = cloudinary_url(
upload_result['public_id'],
fetch_format="auto",
quality="auto"
)
auto_crop_url, _ = cloudinary_url(
upload_result['public_id'],
width=500,
height=500,
crop="auto",
gravity="auto"
)
return {
"upload_result": upload_result,
"optimize_url": optimize_url,
"auto_crop_url": auto_crop_url
}
except Exception as e:
return f"Error uploading to Cloudinary: {str(e)}"
def resize_to_square(image):
"""Resize image to square while maintaining aspect ratio"""
size = max(image.shape[0], image.shape[1])
new_img = np.zeros((size, size, 3), dtype=np.uint8)
# Calculate position to paste original image
x_center = (size - image.shape[1]) // 2
y_center = (size - image.shape[0]) // 2
# Copy the image into center of result image
new_img[y_center:y_center+image.shape[0],
x_center:x_center+image.shape[1]] = image
return new_img
def color_histogram(image, bins=16):
"""
Tính histogram màu cho ảnh RGB
Args:
image (np.ndarray): Ảnh đầu vào
bins (int): Số lượng bins của histogram
Returns:
np.ndarray: Histogram màu được chuẩn hóa
"""
# Kiểm tra và chuyển đổi ảnh
if image is None or image.size == 0:
raise ValueError("Ảnh không hợp lệ")
# Đảm bảo ảnh ở dạng uint8
if image.dtype != np.uint8:
image = (image * 255).astype(np.uint8)
# Tính histogram cho từng kênh màu
hist_r = cv2.calcHist([image], [0], None, [bins], [0, 256]).flatten()
hist_g = cv2.calcHist([image], [1], None, [bins], [0, 256]).flatten()
hist_b = cv2.calcHist([image], [2], None, [bins], [0, 256]).flatten()
# Chuẩn hóa histogram
hist_r = hist_r / np.sum(hist_r) if np.sum(hist_r) > 0 else hist_r
hist_g = hist_g / np.sum(hist_g) if np.sum(hist_g) > 0 else hist_g
hist_b = hist_b / np.sum(hist_b) if np.sum(hist_b) > 0 else hist_b
return np.concatenate([hist_r, hist_g, hist_b])
def color_moments(image):
"""
Tính các moment màu cho ảnh
Args:
image (np.ndarray): Ảnh đầu vào
Returns:
np.ndarray: Các moment màu
"""
# Kiểm tra và chuyển đổi ảnh
if image is None or image.size == 0:
raise ValueError("Ảnh không hợp lệ")
# Đảm bảo ảnh ở dạng float và chuẩn hóa
img = image.astype(np.float32) / 255.0 if image.max() > 1 else image.astype(np.float32)
moments = []
for i in range(3): # Cho mỗi kênh màu
channel = img[:,:,i]
# Tính các moment
mean = np.mean(channel)
std = np.std(channel)
skewness = np.mean(((channel - mean) / (std + 1e-8)) ** 3)
moments.extend([mean, std, skewness])
return np.array(moments)
def dominant_color_descriptor(image, k=3):
"""
Xác định các màu chính thống trị trong ảnh
Args:
image (np.ndarray): Ảnh đầu vào
k (int): Số lượng màu chủ đạo
Returns:
np.ndarray: Các màu chủ đạo và tỷ lệ
"""
# Kiểm tra và chuyển đổi ảnh
if image is None or image.size == 0:
raise ValueError("Ảnh không hợp lệ")
# Đảm bảo ảnh ở dạng uint8
if image.dtype != np.uint8:
image = (image * 255).astype(np.uint8)
# Reshape ảnh thành mảng pixel
pixels = image.reshape(-1, 3)
# Các tham số cho K-means
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 100, 0.2)
flags = cv2.KMEANS_RANDOM_CENTERS
try:
# Thực hiện phân cụm K-means
_, labels, centers = cv2.kmeans(
pixels.astype(np.float32), k, None, criteria, 10, flags
)
# Tính toán số lượng và tỷ lệ của từng cụm
unique, counts = np.unique(labels, return_counts=True)
percentages = counts / len(labels)
# Kết hợp các màu và tỷ lệ
dominant_colors = centers.flatten()
color_percentages = percentages
return np.concatenate([dominant_colors, color_percentages])
except Exception:
# Trả về mảng 0 nếu có lỗi
return np.zeros(2 * k)
def color_coherence_vector(image, k=3):
"""
Tính vector liên kết màu
Args:
image (np.ndarray): Ảnh đầu vào
k (int): Số lượng vùng
Returns:
np.ndarray: Vector liên kết màu
"""
# Kiểm tra và chuyển đổi ảnh
if image is None or image.size == 0:
raise ValueError("Ảnh không hợp lệ")
# Chuyển sang ảnh xám
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# Đảm bảo ảnh ở dạng uint8
if gray.dtype != np.uint8:
gray = np.uint8(gray)
# Áp dụng Otsu's thresholding
_, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# Phân tích thành phần liên thông
num_labels, labels = cv2.connectedComponents(binary)
ccv = []
for i in range(1, min(k+1, num_labels)):
region_mask = (labels == i)
total_pixels = np.sum(region_mask)
coherent_pixels = total_pixels
ccv.extend([coherent_pixels, total_pixels])
# Đảm bảo độ dài vector
while len(ccv) < 2 * k:
ccv.append(0)
return np.array(ccv)
def edge_features(image, bins=16):
"""
Trích xuất đặc trưng cạnh từ ảnh
Args:
image (np.ndarray): Ảnh đầu vào
bins (int): Số lượng bins của histogram
Returns:
np.ndarray: Đặc trưng cạnh
"""
# Kiểm tra và chuyển đổi ảnh
if image is None or image.size == 0:
raise ValueError("Ảnh không hợp lệ")
# Chuyển sang ảnh xám
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# Đảm bảo ảnh ở dạng uint8
if gray.dtype != np.uint8:
gray = np.uint8(gray)
# Tính Sobel edges
sobel_x = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=3)
sobel_y = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=3)
sobel_mag = np.sqrt(sobel_x**2 + sobel_y**2)
# Chuẩn hóa độ lớn Sobel
sobel_mag = np.uint8(255 * sobel_mag / np.max(sobel_mag))
# Tính histogram của Sobel magnitude
sobel_hist = cv2.calcHist([sobel_mag], [0], None, [bins], [0, 256]).flatten()
sobel_hist = sobel_hist / np.sum(sobel_hist) if np.sum(sobel_hist) > 0 else sobel_hist
# Tính mật độ cạnh bằng Canny
canny_edges = cv2.Canny(gray, 100, 200)
edge_density = np.sum(canny_edges) / (gray.shape[0] * gray.shape[1])
return np.concatenate([sobel_hist, [edge_density]])
import pywt # Thư viện xử lý wavelet
def histogram_in_color_space(image, color_space='HSV', bins=16):
"""
Tính histogram của ảnh trong một không gian màu mới.
"""
if color_space == 'HSV':
converted = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
elif color_space == 'LAB':
converted = cv2.cvtColor(image, cv2.COLOR_RGB2Lab)
else:
raise ValueError("Unsupported color space")
histograms = []
for i in range(3): # 3 kênh màu
hist = cv2.calcHist([converted], [i], None, [bins], [0, 256]).flatten()
hist = hist / np.sum(hist)
histograms.append(hist)
return np.concatenate(histograms)
def glcm_features(image, distances=[1, 2, 3], angles=[0, np.pi/4, np.pi/2, 3*np.pi/4], levels=256):
"""
Tính các đặc trưng GLCM của ảnh grayscale.
"""
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# Đảm bảo ảnh ở dạng uint8
if gray.dtype != np.uint8:
gray = (gray * 255).astype(np.uint8)
glcm = graycomatrix(gray, distances=distances, angles=angles, levels=levels, symmetric=True, normed=True)
features = []
# Các thuộc tính phổ biến: contrast, homogeneity, energy, correlation
for prop in ['contrast', 'homogeneity', 'energy', 'correlation']:
features.extend(graycoprops(glcm, prop).flatten())
return np.array(features)
def gabor_features(image, kernels=None):
"""
Tính các đặc trưng từ bộ lọc Gabor.
"""
if kernels is None:
kernels = []
for theta in np.arange(0, np.pi, np.pi / 4): # Các góc từ 0 đến 180 độ
for sigma in [1, 3]: # Các giá trị sigma
for frequency in [0.1, 0.5]: # Các tần số
kernel = cv2.getGaborKernel((9, 9), sigma, theta, 1/frequency, gamma=0.5, ktype=cv2.CV_32F)
kernels.append(kernel)
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
features = []
for kernel in kernels:
filtered = cv2.filter2D(gray, cv2.CV_32F, kernel)
features.append(filtered.mean())
features.append(filtered.var())
return np.array(features)
def wavelet_features(image, wavelet='db1', level=3):
"""
Trích xuất các hệ số wavelet từ ảnh grayscale.
"""
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
coeffs = pywt.wavedec2(gray, wavelet, level=level)
features = []
for coeff in coeffs:
if isinstance(coeff, tuple): # Chi tiết (LH, HL, HH)
for subband in coeff:
features.append(subband.mean())
features.append(subband.var())
else: # Xấp xỉ (LL)
features.append(coeff.mean())
features.append(coeff.var())
return np.array(features)
from skimage.feature import local_binary_pattern
from skimage.color import rgb2gray
from skimage.measure import shannon_entropy
from skimage.feature import hog
def illumination_features(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
mean_brightness = np.mean(gray)
contrast = np.std(gray)
return np.array([mean_brightness, contrast])
def saturation_index(image):
hsv = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
s_channel = hsv[:, :, 1]
mean_saturation = np.mean(s_channel)
std_saturation = np.std(s_channel)
return np.array([mean_saturation, std_saturation])
def local_binary_pattern_features(image, num_points=24, radius=3):
gray = rgb2gray(image)
lbp = local_binary_pattern(gray, num_points, radius, method="uniform")
hist, _ = np.histogram(lbp.ravel(), bins=np.arange(0, num_points + 3), range=(0, num_points + 2))
hist = hist / np.sum(hist)
return hist
def fourier_transform_features(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
f_transform = np.fft.fft2(gray)
f_shift = np.fft.fftshift(f_transform)
magnitude_spectrum = 20 * np.log(np.abs(f_shift) + 1)
mean_frequency = np.mean(magnitude_spectrum)
std_frequency = np.std(magnitude_spectrum)
return np.array([mean_frequency, std_frequency])
def fractal_dimension(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
size = gray.shape[0] * gray.shape[1]
edges = cv2.Canny(gray, 100, 200)
count = np.sum(edges > 0)
fractal_dim = np.log(count + 1) / np.log(size)
return np.array([fractal_dim])
def glossiness_index(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
_, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
glossiness = np.mean(gray[binary == 255])
return np.array([glossiness])
def histogram_oriented_gradients(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
features, _ = hog(gray, orientations=9, pixels_per_cell=(8, 8), cells_per_block=(2, 2), visualize=True)
return features
def color_entropy(image):
entropy = shannon_entropy(image)
return np.array([entropy])
def spatial_color_distribution(image, grid_size=4):
h, w, _ = image.shape
features = []
for i in range(grid_size):
for j in range(grid_size):
x_start = i * h // grid_size
x_end = (i + 1) * h // grid_size
y_start = j * w // grid_size
y_end = (j + 1) * w // grid_size
patch = image[x_start:x_end, y_start:y_end]
hist = cv2.calcHist([patch], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256]).flatten()
hist = hist / np.sum(hist)
features.extend(hist)
return np.array(features)
def uniform_region_features(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
num_labels, labels = cv2.connectedComponents(gray)
unique, counts = np.unique(labels, return_counts=True)
uniformity = np.sum((counts / np.sum(counts)) ** 2)
return np.array([uniformity])
def color_space_features(image):
ycbcr = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)
ycbcr_hist = cv2.calcHist([ycbcr], [1, 2], None, [16, 16], [0, 256, 0, 256]).flatten()
lab = cv2.cvtColor(image, cv2.COLOR_RGB2Lab)
lab_hist = cv2.calcHist([lab], [1, 2], None, [16, 16], [0, 256, 0, 256]).flatten()
ycbcr_hist = ycbcr_hist / np.sum(ycbcr_hist)
lab_hist = lab_hist / np.sum(lab_hist)
return np.concatenate([ycbcr_hist, lab_hist])
@st.cache_resource
def extract_features(image):
color_hist = color_histogram(image)
color_mom = color_moments(image)
dom_color = dominant_color_descriptor(image)
ccv = color_coherence_vector(image)
edges = edge_features(image)
hsv_hist = histogram_in_color_space(image, color_space='HSV')
glcm = glcm_features(image)
gabor = gabor_features(image)
wavelet = wavelet_features(image)
illumination = illumination_features(image)
saturation = saturation_index(image)
lbp = local_binary_pattern_features(image)
fourier = fourier_transform_features(image)
fractal = fractal_dimension(image)
return np.concatenate([
color_hist,
color_mom,
dom_color,
ccv,
edges,
hsv_hist,
glcm,
gabor,
wavelet,
illumination,
saturation,
lbp,
fourier,
fractal,
])
def load_models():
"""Load both object detection and classification models"""
# Load object detection model
device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
object_detection_model = torch.load("fasterrcnn_resnet50_fpn_090824.pth", map_location=device)
object_detection_model.to(device)
object_detection_model.eval()
# Load classification model
classification_model = tf.keras.models.load_model('mlp_model.h5')
return object_detection_model, classification_model, device
def create_efficientnetb0_feature_extractor(input_shape=(256, 256, 3), num_classes=None):
# Xây dựng mô hình EfficientNetB0 đã huấn luyện sẵn từ TensorFlow
inputs = layers.Input(shape=input_shape)
# Thêm lớp Lambda để tiền xử lý ảnh
x = Lambda(preprocess_input, output_shape=input_shape)(inputs) # Xử lý ảnh đầu vào
# Sử dụng mô hình EfficientNetB0 đã được huấn luyện sẵn
efficientnetb0_model = EfficientNetB0(include_top=False, weights='imagenet', input_tensor=x)
# Trích xuất đặc trưng từ mô hình EfficientNetB0
x = layers.GlobalAveragePooling2D()(efficientnetb0_model.output)
if num_classes:
x = layers.Dense(num_classes, activation='softmax')(x) # Thêm lớp phân loại (nếu có)
return models.Model(inputs=inputs, outputs=x)
def perform_object_detection(image, model, device):
original_size = image.size
target_size = (256, 256)
frame_resized = cv2.resize(np.array(image), dsize=target_size, interpolation=cv2.INTER_AREA)
frame_rgb = cv2.cvtColor(frame_resized, cv2.COLOR_RGB2BGR).astype(np.float32)
frame_rgb /= 255.0
frame_rgb = frame_rgb.transpose(2, 0, 1)
frame_rgb = torch.from_numpy(frame_rgb).float().unsqueeze(0).to(device)
with torch.no_grad():
outputs = model(frame_rgb)
boxes = outputs[0]['boxes'].cpu().detach().numpy().astype(np.int32)
labels = outputs[0]['labels'].cpu().detach().numpy().astype(np.int32)
scores = outputs[0]['scores'].cpu().detach().numpy()
result_image = frame_resized.copy()
cropped_images = []
detected_boxes = []
for i in range(len(boxes)):
if scores[i] >= 0.75:
x1, y1, x2, y2 = boxes[i]
if (int(labels[i])-1) == 1 or (int(labels[i])-1) == 0:
color = (0, 255, 0) # Green bounding box
label_text = f'Region {i}'
# Scale coordinates to original image size
original_h, original_w = original_size[::-1]
scale_h, scale_w = original_h / target_size[0], original_w / target_size[1]
x1_orig, y1_orig = int(x1 * scale_w), int(y1 * scale_h)
x2_orig, y2_orig = int(x2 * scale_w), int(y2 * scale_h)
# Crop and process detected region
cropped_image = np.array(image)[y1_orig:y2_orig, x1_orig:x2_orig]
# Check if image has 4 channels (RGBA), convert to RGB
if cropped_image.shape[-1] == 4:
cropped_image = cv2.cvtColor(cropped_image, cv2.COLOR_RGBA2RGB)
else:
cropped_image = cv2.cvtColor(cropped_image, cv2.COLOR_BGR2RGB)
# Resize cropped image
resized_crop = resize_to_square(cropped_image)
cropped_images.append([i,resized_crop])
detected_boxes.append((x1, y1, x2, y2))
# Draw bounding box
cv2.rectangle(result_image, (x1, y1), (x2, y2), color, 1)
cv2.putText(result_image, label_text, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 255, 255), 1, cv2.LINE_AA) # Yellow text, smaller font
return Image.fromarray(result_image), cropped_images, detected_boxes
def preprocess_image(image):
"""Preprocess the image for classification"""
# Convert image to numpy array and resize
img_array = np.array(image)
img_array = cv2.resize(img_array, (256, 256))
# Extract custom features (ensure this returns a 1D array)
features = extract_features(img_array)
features = features.flatten() # Ensure 1D
# Extract EfficientNet features
model_extractor = create_efficientnetb0_feature_extractor()
model_features = model_extractor.predict(np.expand_dims(img_array, axis=0))
model_features = model_features.flatten() # Convert to 1D array
# Combine features
features_combined = np.concatenate([features, model_features])
features_combined = features_combined.reshape(1, -1) # Reshape to 2D for scaler
# Load and apply scaler
scaler = joblib.load('scaler.pkl')
processed_image = scaler.transform(features_combined)
return processed_image
def get_top_predictions(prediction, class_names, top_k=5):
"""Get top k predictions with their probabilities"""
top_indices = prediction.argsort()[0][-top_k:][::-1]
top_predictions = [
(class_names[i], float(prediction[0][i]) * 100)
for i in top_indices
]
return top_predictions
def main():
st.title("🪨 Stone Detection & Classification")
st.write("Upload an image to detect and classify stone surfaces")
if 'predictions' not in st.session_state:
st.session_state.predictions = None
col1, col2 = st.columns(2)
with col1:
st.subheader("Upload Image")
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
image = Image.open(uploaded_file)
st.image(image, caption="Uploaded Image", use_column_width=True)
with st.spinner('Processing image...'):
try:
# Load both models
object_detection_model, classification_model, device = load_models()
# Perform object detection
result_image, cropped_images, detected_boxes = perform_object_detection(
image, object_detection_model, device
)
if not cropped_images:
st.warning("No stone surfaces detected in the image")
return
# Display detection results
st.subheader("Detection Results")
st.image(result_image, caption="Detected Stone Surfaces", use_column_width=True)
# Process each detected region
class_names = ['10', '6.5', '7', '7.5', '8', '8.5', '9', '9.2', '9.5', '9.7']
all_predictions = []
all_image=[]
for idx, cropped_image in cropped_images:
processed_image = preprocess_image(cropped_image)
prediction = classification_model.predict(processed_image)
top_predictions = get_top_predictions(prediction, class_names)
all_predictions.append([idx,top_predictions])
all_image.append(cropped_image)
# Store in session state
st.session_state.predictions = all_predictions
st.session_state.image = all_image
except Exception as e:
st.error(f"Error during processing: {str(e)}")
with col2:
st.subheader("Classification Results")
if st.session_state.predictions is not None:
for idx, predictions in st.session_state.predictions:
st.markdown(f"### Region {idx}")
st.image(st.session_state.image[idx], use_column_width=True)
# Display main prediction
top_class, top_confidence = predictions[0]
st.markdown(f"**Primary Prediction: Grade {top_class}**")
st.markdown(f"**Confidence: {top_confidence:.2f}%**")
st.progress(top_confidence / 100)
# Display all predictions for this region
st.markdown("**Top 5 Predictions**")
for class_name, confidence in predictions:
col_label, col_bar, col_value = st.columns([2, 6, 2])
with col_label:
st.write(f"Grade {class_name}")
with col_bar:
st.progress(confidence / 100)
with col_value:
st.write(f"{confidence:.2f}%")
st.markdown("---")
st.markdown("</div>", unsafe_allow_html=True)
# User Confirmation Section
st.markdown("### Xác nhận độ chính xác của mô hình")
st.write("Giúp chúng tôi cải thiện mô hình bằng cách xác nhận độ chính xác của dự đoán.")
# Accuracy Radio Button
accuracy_option = st.radio(
"Dự đoán có chính xác không?",
["Chọn", "Chính xác", "Không chính xác"],
index=0,
key=f"accuracy_radio_{idx}"
)
if accuracy_option == "Không chính xác":
# Input for correct grade
correct_grade = st.selectbox(
"Chọn màu đá đúng:",
['10', '6.5', '7', '7.5', '8', '8.5', '9', '9.2', '9.5', '9.7'],
index=None,
placeholder="Chọn màu đúng",
key=f"selectbox_correct_grade_{idx}"
)
# Kiểm tra xem đã tải lên hay chưa
if f"uploaded_{idx}" not in st.session_state:
st.session_state[f"uploaded_{idx}"] = False
# Chỉ thực hiện khi người dùng đã chọn giá trị và chưa tải lên
if correct_grade and not st.session_state[f"uploaded_{idx}"]:
st.info(f"Đã chọn màu đúng: {correct_grade}")
# Resize hình ảnh xuống 256x256
resized_image = Image.fromarray(st.session_state.image[idx]).resize((256, 256))
temp_image_path = generate_random_filename()
# Lưu tệp resize tạm thời
resized_image.save(temp_image_path)
# Tải ảnh lên Cloudinary
cloudinary_result = upload_to_cloudinary(temp_image_path, correct_grade)
if isinstance(cloudinary_result, dict):
st.success(f"Hình ảnh đã được tải lên thành công cho màu {correct_grade}")
st.write(f"URL công khai: {cloudinary_result['upload_result']['secure_url']}")
# Đánh dấu trạng thái đã tải lên
st.session_state[f"uploaded_{idx}"] = True
else:
st.error(cloudinary_result)
else:
st.info("Upload an image to see detection and classification results")
if __name__ == "__main__":
main() |