refactor YOLO crop model
This commit is contained in:
Nguyễn Phước Thành
@@ -1,56 +0,0 @@
|
||||
# ID Card Cropper
|
||||
|
||||
Script đơn giản để cắt ID cards từ ảnh sử dụng Roboflow API.
|
||||
|
||||
## Cách sử dụng
|
||||
|
||||
```bash
|
||||
python id_card_cropper.py input_folder output_folder
|
||||
```
|
||||
|
||||
### Ví dụ:
|
||||
|
||||
```bash
|
||||
# Sử dụng API key mặc định
|
||||
python id_card_cropper.py data/IDcards/Archive output/cropped_cards
|
||||
|
||||
# Sử dụng API key tùy chỉnh
|
||||
python id_card_cropper.py data/IDcards/Archive output/cropped_cards --api-key YOUR_API_KEY
|
||||
```
|
||||
|
||||
## Tham số
|
||||
|
||||
- `input_folder`: Thư mục chứa ảnh cần xử lý
|
||||
- `output_folder`: Thư mục lưu ID cards đã cắt
|
||||
- `--api-key`: API key Roboflow (mặc định: demo key)
|
||||
|
||||
## Hỗ trợ định dạng ảnh
|
||||
|
||||
- JPG/JPEG
|
||||
- PNG
|
||||
- BMP
|
||||
- TIFF
|
||||
|
||||
## Kết quả
|
||||
|
||||
Script sẽ:
|
||||
1. Tìm tất cả ảnh trong thư mục input
|
||||
2. Phát hiện ID cards trong mỗi ảnh
|
||||
3. Cắt và lưu ID cards vào thư mục output
|
||||
4. Đặt tên file theo format: `{tên_ảnh_gốc}_card_{số}.jpg`
|
||||
|
||||
## Ví dụ kết quả
|
||||
|
||||
```
|
||||
output/cropped_cards/
|
||||
├── im1__card_1.jpg
|
||||
├── im5_card_1.jpg
|
||||
├── im11_card_1.jpg
|
||||
└── im11_card_2.jpg
|
||||
```
|
||||
|
||||
## Lưu ý
|
||||
|
||||
- Cần kết nối internet để sử dụng Roboflow API
|
||||
- Có delay 1 giây giữa các request để tránh rate limiting
|
||||
- Chỉ lưu ID cards đã cắt, không lưu ảnh gốc với bounding boxes
|
||||
@@ -3,7 +3,7 @@
|
||||
|
||||
# Paths configuration
|
||||
paths:
|
||||
input_dir: "data/Archive"
|
||||
input_dir: "data/IDcards/processed"
|
||||
output_dir: "out"
|
||||
log_file: "logs/data_augmentation.log"
|
||||
|
||||
@@ -17,7 +17,7 @@ augmentation:
|
||||
|
||||
# Processing configuration
|
||||
processing:
|
||||
target_size: [224, 224] # [width, height]
|
||||
target_size: [640, 640] # [width, height] - Increased for better coverage
|
||||
batch_size: 32
|
||||
num_augmentations: 3 # number of augmented versions per image
|
||||
save_format: "jpg"
|
||||
|
||||
@@ -1,222 +0,0 @@
|
||||
2025-08-05 18:53:06,981 - src.model.yolo_detector - INFO - Using pre-trained YOLOv8n model
|
||||
2025-08-05 18:53:07,004 - src.model.yolo_detector - INFO - Using device: cuda
|
||||
2025-08-05 18:53:07,038 - src.model.yolo_detector - INFO - Using pre-trained YOLOv8n model
|
||||
2025-08-05 18:53:07,038 - src.model.yolo_detector - INFO - Using device: cuda
|
||||
2025-08-05 18:53:07,361 - src.model.yolo_detector - INFO - Using pre-trained YOLOv8n model
|
||||
2025-08-05 18:53:07,362 - src.model.yolo_detector - INFO - Using device: cuda
|
||||
2025-08-05 18:53:07,363 - src.model.id_card_processor - INFO - Detecting and cropping ID cards...
|
||||
2025-08-05 18:53:07,363 - src.model.yolo_detector - ERROR - No images found in data\IDcards
|
||||
2025-08-05 18:53:07,364 - src.model.id_card_processor - INFO - Processing cropped ID cards...
|
||||
2025-08-05 18:53:07,364 - src.model.id_card_processor - ERROR - No images found in data\test_output\cropped
|
||||
2025-08-05 19:04:14,903 - src.model.yolo_detector - INFO - Using pre-trained YOLOv8n model
|
||||
2025-08-05 19:04:14,995 - src.model.yolo_detector - INFO - Using device: cuda
|
||||
2025-08-05 19:04:14,996 - src.model.id_card_processor - INFO - Detecting and cropping ID cards...
|
||||
2025-08-05 19:04:14,997 - src.model.yolo_detector - INFO - Processing 29 images from data\IDcards and subdirectories
|
||||
2025-08-05 19:04:14,998 - src.model.yolo_detector - INFO - Processing 1/29: im10.png
|
||||
2025-08-05 19:04:19,785 - src.model.yolo_detector - INFO - Found 1 detections in im10.png
|
||||
2025-08-05 19:04:19,813 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im10_card_1.jpg
|
||||
2025-08-05 19:04:19,813 - src.model.yolo_detector - INFO - Processed im10.png: 1 cards cropped
|
||||
2025-08-05 19:04:19,814 - src.model.yolo_detector - INFO - Processing 2/29: im11.png
|
||||
2025-08-05 19:04:19,926 - src.model.yolo_detector - INFO - Found 2 detections in im11.png
|
||||
2025-08-05 19:04:19,937 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im11_card_1.jpg
|
||||
2025-08-05 19:04:19,946 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im11_card_2.jpg
|
||||
2025-08-05 19:04:19,946 - src.model.yolo_detector - INFO - Processed im11.png: 2 cards cropped
|
||||
2025-08-05 19:04:19,946 - src.model.yolo_detector - INFO - Processing 3/29: im12.png
|
||||
2025-08-05 19:04:20,056 - src.model.yolo_detector - INFO - Found 2 detections in im12.png
|
||||
2025-08-05 19:04:20,069 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im12_card_1.jpg
|
||||
2025-08-05 19:04:20,082 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im12_card_2.jpg
|
||||
2025-08-05 19:04:20,083 - src.model.yolo_detector - INFO - Processed im12.png: 2 cards cropped
|
||||
2025-08-05 19:04:20,083 - src.model.yolo_detector - INFO - Processing 4/29: im13.png
|
||||
2025-08-05 19:04:20,116 - src.model.yolo_detector - INFO - Found 0 detections in im13.png
|
||||
2025-08-05 19:04:20,117 - src.model.yolo_detector - WARNING - No ID cards detected in im13.png
|
||||
2025-08-05 19:04:20,117 - src.model.yolo_detector - INFO - Processing 5/29: im14.png
|
||||
2025-08-05 19:04:20,156 - src.model.yolo_detector - INFO - Found 1 detections in im14.png
|
||||
2025-08-05 19:04:20,172 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im14_card_1.jpg
|
||||
2025-08-05 19:04:20,173 - src.model.yolo_detector - INFO - Processed im14.png: 1 cards cropped
|
||||
2025-08-05 19:04:20,174 - src.model.yolo_detector - INFO - Processing 6/29: im15.png
|
||||
2025-08-05 19:04:20,208 - src.model.yolo_detector - INFO - Found 1 detections in im15.png
|
||||
2025-08-05 19:04:20,222 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im15_card_1.jpg
|
||||
2025-08-05 19:04:20,222 - src.model.yolo_detector - INFO - Processed im15.png: 1 cards cropped
|
||||
2025-08-05 19:04:20,223 - src.model.yolo_detector - INFO - Processing 7/29: im1_.png
|
||||
2025-08-05 19:04:20,466 - src.model.yolo_detector - INFO - Found 0 detections in im1_.png
|
||||
2025-08-05 19:04:20,466 - src.model.yolo_detector - WARNING - No ID cards detected in im1_.png
|
||||
2025-08-05 19:04:20,466 - src.model.yolo_detector - INFO - Processing 8/29: im2.png
|
||||
2025-08-05 19:04:20,534 - src.model.yolo_detector - INFO - Found 2 detections in im2.png
|
||||
2025-08-05 19:04:20,564 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im2_card_1.jpg
|
||||
2025-08-05 19:04:20,594 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im2_card_2.jpg
|
||||
2025-08-05 19:04:20,594 - src.model.yolo_detector - INFO - Processed im2.png: 2 cards cropped
|
||||
2025-08-05 19:04:20,595 - src.model.yolo_detector - INFO - Processing 9/29: im3.png
|
||||
2025-08-05 19:04:20,648 - src.model.yolo_detector - INFO - Found 1 detections in im3.png
|
||||
2025-08-05 19:04:20,671 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im3_card_1.jpg
|
||||
2025-08-05 19:04:20,671 - src.model.yolo_detector - INFO - Processed im3.png: 1 cards cropped
|
||||
2025-08-05 19:04:20,672 - src.model.yolo_detector - INFO - Processing 10/29: im4.png
|
||||
2025-08-05 19:04:20,724 - src.model.yolo_detector - INFO - Found 1 detections in im4.png
|
||||
2025-08-05 19:04:20,753 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im4_card_1.jpg
|
||||
2025-08-05 19:04:20,754 - src.model.yolo_detector - INFO - Processed im4.png: 1 cards cropped
|
||||
2025-08-05 19:04:20,754 - src.model.yolo_detector - INFO - Processing 11/29: im5.png
|
||||
2025-08-05 19:04:20,798 - src.model.yolo_detector - INFO - Found 2 detections in im5.png
|
||||
2025-08-05 19:04:20,816 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im5_card_1.jpg
|
||||
2025-08-05 19:04:20,835 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im5_card_2.jpg
|
||||
2025-08-05 19:04:20,836 - src.model.yolo_detector - INFO - Processed im5.png: 2 cards cropped
|
||||
2025-08-05 19:04:20,837 - src.model.yolo_detector - INFO - Processing 12/29: im6.png
|
||||
2025-08-05 19:04:20,994 - src.model.yolo_detector - INFO - Found 2 detections in im6.png
|
||||
2025-08-05 19:04:21,052 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im6_card_1.jpg
|
||||
2025-08-05 19:04:21,118 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im6_card_2.jpg
|
||||
2025-08-05 19:04:21,119 - src.model.yolo_detector - INFO - Processed im6.png: 2 cards cropped
|
||||
2025-08-05 19:04:21,120 - src.model.yolo_detector - INFO - Processing 13/29: im7.png
|
||||
2025-08-05 19:04:21,159 - src.model.yolo_detector - INFO - Found 3 detections in im7.png
|
||||
2025-08-05 19:04:21,168 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im7_card_1.jpg
|
||||
2025-08-05 19:04:21,176 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im7_card_2.jpg
|
||||
2025-08-05 19:04:21,184 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im7_card_3.jpg
|
||||
2025-08-05 19:04:21,184 - src.model.yolo_detector - INFO - Processed im7.png: 3 cards cropped
|
||||
2025-08-05 19:04:21,185 - src.model.yolo_detector - INFO - Processing 14/29: im8.png
|
||||
2025-08-05 19:04:21,353 - src.model.yolo_detector - INFO - Found 2 detections in im8.png
|
||||
2025-08-05 19:04:21,387 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im8_card_1.jpg
|
||||
2025-08-05 19:04:21,423 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im8_card_2.jpg
|
||||
2025-08-05 19:04:21,424 - src.model.yolo_detector - INFO - Processed im8.png: 2 cards cropped
|
||||
2025-08-05 19:04:21,425 - src.model.yolo_detector - INFO - Processing 15/29: im9.png
|
||||
2025-08-05 19:04:21,522 - src.model.yolo_detector - INFO - Found 1 detections in im9.png
|
||||
2025-08-05 19:04:21,532 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\Archive\im9_card_1.jpg
|
||||
2025-08-05 19:04:21,532 - src.model.yolo_detector - INFO - Processed im9.png: 1 cards cropped
|
||||
2025-08-05 19:04:21,532 - src.model.yolo_detector - INFO - Processing 16/29: im10.png
|
||||
2025-08-05 19:04:21,585 - src.model.yolo_detector - INFO - Found 3 detections in im10.png
|
||||
2025-08-05 19:04:21,601 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im10_card_1.jpg
|
||||
2025-08-05 19:04:21,618 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im10_card_2.jpg
|
||||
2025-08-05 19:04:21,636 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im10_card_3.jpg
|
||||
2025-08-05 19:04:21,636 - src.model.yolo_detector - INFO - Processed im10.png: 3 cards cropped
|
||||
2025-08-05 19:04:21,638 - src.model.yolo_detector - INFO - Processing 17/29: im11.png
|
||||
2025-08-05 19:04:21,679 - src.model.yolo_detector - INFO - Found 2 detections in im11.png
|
||||
2025-08-05 19:04:21,696 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im11_card_1.jpg
|
||||
2025-08-05 19:04:21,712 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im11_card_2.jpg
|
||||
2025-08-05 19:04:21,713 - src.model.yolo_detector - INFO - Processed im11.png: 2 cards cropped
|
||||
2025-08-05 19:04:21,713 - src.model.yolo_detector - INFO - Processing 18/29: im12.png
|
||||
2025-08-05 19:04:21,755 - src.model.yolo_detector - INFO - Found 0 detections in im12.png
|
||||
2025-08-05 19:04:21,756 - src.model.yolo_detector - WARNING - No ID cards detected in im12.png
|
||||
2025-08-05 19:04:21,756 - src.model.yolo_detector - INFO - Processing 19/29: im13.png
|
||||
2025-08-05 19:04:21,793 - src.model.yolo_detector - INFO - Found 1 detections in im13.png
|
||||
2025-08-05 19:04:21,806 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im13_card_1.jpg
|
||||
2025-08-05 19:04:21,806 - src.model.yolo_detector - INFO - Processed im13.png: 1 cards cropped
|
||||
2025-08-05 19:04:21,806 - src.model.yolo_detector - INFO - Processing 20/29: im14.png
|
||||
2025-08-05 19:04:21,846 - src.model.yolo_detector - INFO - Found 2 detections in im14.png
|
||||
2025-08-05 19:04:21,862 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im14_card_1.jpg
|
||||
2025-08-05 19:04:21,877 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im14_card_2.jpg
|
||||
2025-08-05 19:04:21,877 - src.model.yolo_detector - INFO - Processed im14.png: 2 cards cropped
|
||||
2025-08-05 19:04:21,878 - src.model.yolo_detector - INFO - Processing 21/29: im15.png
|
||||
2025-08-05 19:04:21,914 - src.model.yolo_detector - INFO - Found 0 detections in im15.png
|
||||
2025-08-05 19:04:21,914 - src.model.yolo_detector - WARNING - No ID cards detected in im15.png
|
||||
2025-08-05 19:04:21,914 - src.model.yolo_detector - INFO - Processing 22/29: im1_.png
|
||||
2025-08-05 19:04:21,959 - src.model.yolo_detector - INFO - Found 3 detections in im1_.png
|
||||
2025-08-05 19:04:21,971 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im1__card_1.jpg
|
||||
2025-08-05 19:04:21,983 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im1__card_2.jpg
|
||||
2025-08-05 19:04:21,996 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im1__card_3.jpg
|
||||
2025-08-05 19:04:21,997 - src.model.yolo_detector - INFO - Processed im1_.png: 3 cards cropped
|
||||
2025-08-05 19:04:21,997 - src.model.yolo_detector - INFO - Processing 23/29: im2.png
|
||||
2025-08-05 19:04:22,101 - src.model.yolo_detector - INFO - Found 1 detections in im2.png
|
||||
2025-08-05 19:04:22,174 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im2_card_1.jpg
|
||||
2025-08-05 19:04:22,174 - src.model.yolo_detector - INFO - Processed im2.png: 1 cards cropped
|
||||
2025-08-05 19:04:22,176 - src.model.yolo_detector - INFO - Processing 24/29: im3.png
|
||||
2025-08-05 19:04:22,220 - src.model.yolo_detector - INFO - Found 2 detections in im3.png
|
||||
2025-08-05 19:04:22,235 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im3_card_1.jpg
|
||||
2025-08-05 19:04:22,251 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im3_card_2.jpg
|
||||
2025-08-05 19:04:22,252 - src.model.yolo_detector - INFO - Processed im3.png: 2 cards cropped
|
||||
2025-08-05 19:04:22,252 - src.model.yolo_detector - INFO - Processing 25/29: im5.png
|
||||
2025-08-05 19:04:22,307 - src.model.yolo_detector - INFO - Found 1 detections in im5.png
|
||||
2025-08-05 19:04:22,316 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im5_card_1.jpg
|
||||
2025-08-05 19:04:22,316 - src.model.yolo_detector - INFO - Processed im5.png: 1 cards cropped
|
||||
2025-08-05 19:04:22,317 - src.model.yolo_detector - INFO - Processing 26/29: im6.png
|
||||
2025-08-05 19:04:22,375 - src.model.yolo_detector - INFO - Found 2 detections in im6.png
|
||||
2025-08-05 19:04:22,387 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im6_card_1.jpg
|
||||
2025-08-05 19:04:22,397 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im6_card_2.jpg
|
||||
2025-08-05 19:04:22,398 - src.model.yolo_detector - INFO - Processed im6.png: 2 cards cropped
|
||||
2025-08-05 19:04:22,399 - src.model.yolo_detector - INFO - Processing 27/29: im7.png
|
||||
2025-08-05 19:04:22,441 - src.model.yolo_detector - INFO - Found 1 detections in im7.png
|
||||
2025-08-05 19:04:22,458 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im7_card_1.jpg
|
||||
2025-08-05 19:04:22,459 - src.model.yolo_detector - INFO - Processed im7.png: 1 cards cropped
|
||||
2025-08-05 19:04:22,460 - src.model.yolo_detector - INFO - Processing 28/29: im8.png
|
||||
2025-08-05 19:04:22,492 - src.model.yolo_detector - INFO - Found 2 detections in im8.png
|
||||
2025-08-05 19:04:22,502 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im8_card_1.jpg
|
||||
2025-08-05 19:04:22,509 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im8_card_2.jpg
|
||||
2025-08-05 19:04:22,510 - src.model.yolo_detector - INFO - Processed im8.png: 2 cards cropped
|
||||
2025-08-05 19:04:22,510 - src.model.yolo_detector - INFO - Processing 29/29: im9.png
|
||||
2025-08-05 19:04:22,540 - src.model.yolo_detector - INFO - Found 1 detections in im9.png
|
||||
2025-08-05 19:04:22,546 - src.model.yolo_detector - INFO - Saved cropped image to data\processed_id_cards\cropped\titre-sejour-fr\im9_card_1.jpg
|
||||
2025-08-05 19:04:22,546 - src.model.yolo_detector - INFO - Processed im9.png: 1 cards cropped
|
||||
2025-08-05 19:04:22,546 - src.model.yolo_detector - INFO - Batch processing completed:
|
||||
2025-08-05 19:04:22,548 - src.model.yolo_detector - INFO - - Total images: 29
|
||||
2025-08-05 19:04:22,548 - src.model.yolo_detector - INFO - - Processed: 25
|
||||
2025-08-05 19:04:22,548 - src.model.yolo_detector - INFO - - Total detections: 42
|
||||
2025-08-05 19:04:22,549 - src.model.yolo_detector - INFO - - Total cropped: 42
|
||||
2025-08-05 19:04:22,549 - src.model.id_card_processor - INFO - Processing cropped ID cards...
|
||||
2025-08-05 19:04:22,552 - src.model.id_card_processor - INFO - Processing 42 images from data\processed_id_cards\cropped and subdirectories
|
||||
2025-08-05 19:04:22,552 - src.model.id_card_processor - INFO - Processing 1/42: im10_card_1.jpg
|
||||
2025-08-05 19:04:22,564 - src.model.id_card_processor - INFO - Removing background from im10_card_1.jpg
|
||||
2025-08-05 19:04:22,877 - src.model.id_card_processor - INFO - Enhancing im10_card_1.jpg
|
||||
2025-08-05 19:04:23,016 - src.model.id_card_processor - INFO - Normalizing im10_card_1.jpg
|
||||
2025-08-05 19:04:23,023 - src.model.id_card_processor - INFO - Processed im10_card_1.jpg
|
||||
2025-08-05 19:04:23,023 - src.model.id_card_processor - INFO - Processing 2/42: im11_card_1.jpg
|
||||
2025-08-05 19:04:23,034 - src.model.id_card_processor - INFO - Removing background from im11_card_1.jpg
|
||||
2025-08-05 19:04:23,264 - src.model.id_card_processor - INFO - Enhancing im11_card_1.jpg
|
||||
2025-08-05 19:04:23,265 - src.model.id_card_processor - INFO - Normalizing im11_card_1.jpg
|
||||
2025-08-05 19:04:23,270 - src.model.id_card_processor - INFO - Processed im11_card_1.jpg
|
||||
2025-08-05 19:04:23,271 - src.model.id_card_processor - INFO - Processing 3/42: im11_card_2.jpg
|
||||
2025-08-05 19:04:23,282 - src.model.id_card_processor - INFO - Removing background from im11_card_2.jpg
|
||||
2025-08-05 19:04:23,312 - src.model.id_card_processor - INFO - Enhancing im11_card_2.jpg
|
||||
2025-08-05 19:04:23,313 - src.model.id_card_processor - INFO - Normalizing im11_card_2.jpg
|
||||
2025-08-05 19:04:23,316 - src.model.id_card_processor - INFO - Processed im11_card_2.jpg
|
||||
2025-08-05 19:04:23,316 - src.model.id_card_processor - INFO - Processing 4/42: im12_card_1.jpg
|
||||
2025-08-05 19:04:23,328 - src.model.id_card_processor - INFO - Removing background from im12_card_1.jpg
|
||||
2025-08-05 19:04:23,670 - src.model.id_card_processor - INFO - Enhancing im12_card_1.jpg
|
||||
2025-08-05 19:04:23,671 - src.model.id_card_processor - INFO - Normalizing im12_card_1.jpg
|
||||
2025-08-05 19:04:23,675 - src.model.id_card_processor - INFO - Processed im12_card_1.jpg
|
||||
2025-08-05 19:04:23,676 - src.model.id_card_processor - INFO - Processing 5/42: im12_card_2.jpg
|
||||
2025-08-05 19:04:23,686 - src.model.id_card_processor - INFO - Removing background from im12_card_2.jpg
|
||||
2025-08-05 19:04:29,279 - src.model.id_card_processor - INFO - Enhancing im12_card_2.jpg
|
||||
2025-08-05 19:04:29,284 - src.model.id_card_processor - INFO - Normalizing im12_card_2.jpg
|
||||
2025-08-05 19:04:29,289 - src.model.id_card_processor - INFO - Processed im12_card_2.jpg
|
||||
2025-08-05 19:04:29,290 - src.model.id_card_processor - INFO - Processing 6/42: im14_card_1.jpg
|
||||
2025-08-05 19:04:29,301 - src.model.id_card_processor - INFO - Removing background from im14_card_1.jpg
|
||||
2025-08-05 19:04:29,774 - src.model.id_card_processor - INFO - Enhancing im14_card_1.jpg
|
||||
2025-08-05 19:04:29,775 - src.model.id_card_processor - INFO - Normalizing im14_card_1.jpg
|
||||
2025-08-05 19:04:29,779 - src.model.id_card_processor - INFO - Processed im14_card_1.jpg
|
||||
2025-08-05 19:04:29,780 - src.model.id_card_processor - INFO - Processing 7/42: im15_card_1.jpg
|
||||
2025-08-05 19:04:29,791 - src.model.id_card_processor - INFO - Removing background from im15_card_1.jpg
|
||||
2025-08-05 19:04:30,009 - src.model.id_card_processor - INFO - Enhancing im15_card_1.jpg
|
||||
2025-08-05 19:04:30,010 - src.model.id_card_processor - INFO - Normalizing im15_card_1.jpg
|
||||
2025-08-05 19:04:30,015 - src.model.id_card_processor - INFO - Processed im15_card_1.jpg
|
||||
2025-08-05 19:04:30,015 - src.model.id_card_processor - INFO - Processing 8/42: im2_card_1.jpg
|
||||
2025-08-05 19:04:30,017 - src.model.id_card_processor - INFO - Removing background from im2_card_1.jpg
|
||||
2025-08-05 19:04:31,861 - src.model.id_card_processor - INFO - Enhancing im2_card_1.jpg
|
||||
2025-08-05 19:04:31,863 - src.model.id_card_processor - INFO - Normalizing im2_card_1.jpg
|
||||
2025-08-05 19:04:31,869 - src.model.id_card_processor - INFO - Processed im2_card_1.jpg
|
||||
2025-08-05 19:04:31,869 - src.model.id_card_processor - INFO - Processing 9/42: im2_card_2.jpg
|
||||
2025-08-05 19:04:31,884 - src.model.id_card_processor - INFO - Removing background from im2_card_2.jpg
|
||||
2025-08-05 19:04:38,985 - src.model.id_card_processor - INFO - Enhancing im2_card_2.jpg
|
||||
2025-08-05 19:04:38,996 - src.model.id_card_processor - INFO - Normalizing im2_card_2.jpg
|
||||
2025-08-05 19:04:39,007 - src.model.id_card_processor - INFO - Processed im2_card_2.jpg
|
||||
2025-08-05 19:04:39,008 - src.model.id_card_processor - INFO - Processing 10/42: im3_card_1.jpg
|
||||
2025-08-05 19:04:39,009 - src.model.id_card_processor - INFO - Removing background from im3_card_1.jpg
|
||||
2025-08-05 19:04:39,177 - src.model.id_card_processor - INFO - Enhancing im3_card_1.jpg
|
||||
2025-08-05 19:04:39,178 - src.model.id_card_processor - INFO - Normalizing im3_card_1.jpg
|
||||
2025-08-05 19:04:39,182 - src.model.id_card_processor - INFO - Processed im3_card_1.jpg
|
||||
2025-08-05 19:04:39,182 - src.model.id_card_processor - INFO - Processing 11/42: im4_card_1.jpg
|
||||
2025-08-05 19:04:39,184 - src.model.id_card_processor - INFO - Removing background from im4_card_1.jpg
|
||||
2025-08-05 19:04:39,374 - src.model.id_card_processor - INFO - Enhancing im4_card_1.jpg
|
||||
2025-08-05 19:04:39,375 - src.model.id_card_processor - INFO - Normalizing im4_card_1.jpg
|
||||
2025-08-05 19:04:39,379 - src.model.id_card_processor - INFO - Processed im4_card_1.jpg
|
||||
2025-08-05 19:04:39,379 - src.model.id_card_processor - INFO - Processing 12/42: im5_card_1.jpg
|
||||
2025-08-05 19:04:39,389 - src.model.id_card_processor - INFO - Removing background from im5_card_1.jpg
|
||||
2025-08-05 19:04:39,842 - src.model.id_card_processor - INFO - Enhancing im5_card_1.jpg
|
||||
2025-08-05 19:04:39,843 - src.model.id_card_processor - INFO - Normalizing im5_card_1.jpg
|
||||
2025-08-05 19:04:39,846 - src.model.id_card_processor - INFO - Processed im5_card_1.jpg
|
||||
2025-08-05 19:04:39,846 - src.model.id_card_processor - INFO - Processing 13/42: im5_card_2.jpg
|
||||
2025-08-05 19:04:39,859 - src.model.id_card_processor - INFO - Removing background from im5_card_2.jpg
|
||||
2025-08-05 19:04:42,430 - src.model.id_card_processor - INFO - Enhancing im5_card_2.jpg
|
||||
2025-08-05 19:04:42,434 - src.model.id_card_processor - INFO - Normalizing im5_card_2.jpg
|
||||
2025-08-05 19:04:42,438 - src.model.id_card_processor - INFO - Processed im5_card_2.jpg
|
||||
2025-08-05 19:04:42,439 - src.model.id_card_processor - INFO - Processing 14/42: im6_card_1.jpg
|
||||
2025-08-05 19:04:42,449 - src.model.id_card_processor - INFO - Removing background from im6_card_1.jpg
|
||||
2025-08-05 19:04:47,647 - src.model.id_card_processor - INFO - Enhancing im6_card_1.jpg
|
||||
2025-08-05 19:04:47,652 - src.model.id_card_processor - INFO - Normalizing im6_card_1.jpg
|
||||
2025-08-05 19:04:47,657 - src.model.id_card_processor - INFO - Processed im6_card_1.jpg
|
||||
2025-08-05 19:04:47,657 - src.model.id_card_processor - INFO - Processing 15/42: im6_card_2.jpg
|
||||
2025-08-05 19:04:47,680 - src.model.id_card_processor - INFO - Removing background from im6_card_2.jpg
|
||||
@@ -1,9 +1,9 @@
|
||||
"""
|
||||
Data Augmentation Package
|
||||
Data Augmentation Package for ID Cards
|
||||
"""
|
||||
|
||||
__version__ = "1.0.0"
|
||||
__author__ = "OCR Data Augmentation Tool"
|
||||
__version__ = "2.0.0"
|
||||
__author__ = "ID Card Data Augmentation Tool"
|
||||
|
||||
from .utils import *
|
||||
from .image_processor import ImageProcessor
|
||||
@@ -12,12 +12,12 @@ from .config_manager import ConfigManager
|
||||
|
||||
__all__ = [
|
||||
"ImageProcessor",
|
||||
"DataAugmentation",
|
||||
"DataAugmentation",
|
||||
"ConfigManager",
|
||||
"setup_logging",
|
||||
"get_image_files",
|
||||
"load_image",
|
||||
"save_image",
|
||||
"validate_image",
|
||||
"create_augmented_filename",
|
||||
"print_progress",
|
||||
]
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,40 +0,0 @@
|
||||
"""
|
||||
Configuration file for data augmentation
|
||||
"""
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# Paths
|
||||
BASE_DIR = Path(__file__).parent.parent
|
||||
DATA_DIR = BASE_DIR / "data"
|
||||
INPUT_IMAGES_DIR = DATA_DIR / "dataset" / "training_data" / "images"
|
||||
OUTPUT_DIR = DATA_DIR / "augmented_data"
|
||||
|
||||
# Data augmentation parameters
|
||||
AUGMENTATION_CONFIG = {
|
||||
"rotation_range": 15, # degrees
|
||||
"width_shift_range": 0.1, # fraction of total width
|
||||
"height_shift_range": 0.1, # fraction of total height
|
||||
"brightness_range": [0.8, 1.2], # brightness factor
|
||||
"zoom_range": [0.9, 1.1], # zoom factor
|
||||
"horizontal_flip": True,
|
||||
"vertical_flip": False,
|
||||
"fill_mode": "nearest",
|
||||
"cval": 0,
|
||||
"rescale": 1./255,
|
||||
}
|
||||
|
||||
# Processing parameters
|
||||
PROCESSING_CONFIG = {
|
||||
"target_size": (224, 224), # (width, height)
|
||||
"batch_size": 32,
|
||||
"num_augmentations": 3, # number of augmented versions per image
|
||||
"save_format": "jpg",
|
||||
"quality": 95,
|
||||
}
|
||||
|
||||
# Supported image formats
|
||||
SUPPORTED_FORMATS = ['.jpg', '.jpeg', '.png', '.bmp', '.tiff']
|
||||
|
||||
# Create output directory if it doesn't exist
|
||||
OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
|
||||
@@ -1,5 +1,5 @@
|
||||
"""
|
||||
Data augmentation class for image augmentation - ONLY ROTATION
|
||||
Data augmentation class for image augmentation - ONLY ROTATION with quality preservation
|
||||
"""
|
||||
import cv2
|
||||
import numpy as np
|
||||
@@ -23,32 +23,134 @@ class DataAugmentation:
|
||||
self.config = config or {}
|
||||
self.image_processor = ImageProcessor()
|
||||
|
||||
def rotate_image(self, image: np.ndarray, angle: float) -> np.ndarray:
|
||||
def rotate_image_preserve_quality(self, image: np.ndarray, angle: float) -> np.ndarray:
|
||||
"""
|
||||
Rotate image by given angle
|
||||
Rotate image by given angle with white background and crop to preserve quality
|
||||
|
||||
Args:
|
||||
image: Input image
|
||||
angle: Rotation angle in degrees
|
||||
|
||||
Returns:
|
||||
Rotated image
|
||||
Rotated and cropped image
|
||||
"""
|
||||
height, width = image.shape[:2]
|
||||
center = (width // 2, height // 2)
|
||||
|
||||
# Calculate new dimensions for rotation
|
||||
angle_rad = math.radians(angle)
|
||||
cos_val = abs(math.cos(angle_rad))
|
||||
sin_val = abs(math.sin(angle_rad))
|
||||
|
||||
# Calculate new width and height
|
||||
new_width = int(width * cos_val + height * sin_val)
|
||||
new_height = int(height * cos_val + width * sin_val)
|
||||
|
||||
# Create larger canvas with white background
|
||||
canvas = np.ones((new_height, new_width, 3), dtype=np.uint8) * 255
|
||||
|
||||
# Calculate offset to center the image
|
||||
offset_x = (new_width - width) // 2
|
||||
offset_y = (new_height - height) // 2
|
||||
|
||||
# Ensure offsets are valid
|
||||
if offset_x >= 0 and offset_y >= 0 and offset_x + width <= new_width and offset_y + height <= new_height:
|
||||
# Place original image in center of canvas
|
||||
canvas[offset_y:offset_y+height, offset_x:offset_x+width] = image
|
||||
else:
|
||||
# If calculation is wrong, use a simpler approach
|
||||
canvas = np.ones((max(height, width) * 2, max(height, width) * 2, 3), dtype=np.uint8) * 255
|
||||
center_y, center_x = canvas.shape[0] // 2, canvas.shape[1] // 2
|
||||
start_y = center_y - height // 2
|
||||
start_x = center_x - width // 2
|
||||
canvas[start_y:start_y+height, start_x:start_x+width] = image
|
||||
new_width, new_height = canvas.shape[1], canvas.shape[0]
|
||||
|
||||
# Calculate center for rotation
|
||||
center = (new_width // 2, new_height // 2)
|
||||
|
||||
# Create rotation matrix
|
||||
rotation_matrix = cv2.getRotationMatrix2D(center, angle, 1.0)
|
||||
|
||||
# Perform rotation
|
||||
rotated = cv2.warpAffine(image, rotation_matrix, (width, height),
|
||||
borderMode=cv2.BORDER_REPLICATE)
|
||||
rotated = cv2.warpAffine(canvas, rotation_matrix, (new_width, new_height),
|
||||
borderMode=cv2.BORDER_CONSTANT, borderValue=(255, 255, 255))
|
||||
|
||||
# Crop white borders to get the actual image content
|
||||
rotated = self._crop_white_borders(rotated)
|
||||
|
||||
return rotated
|
||||
|
||||
def _crop_white_borders(self, image: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Crop white borders from image to get the actual content
|
||||
|
||||
Args:
|
||||
image: Input image with white borders
|
||||
|
||||
Returns:
|
||||
Cropped image without white borders
|
||||
"""
|
||||
# Convert to grayscale for edge detection
|
||||
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
|
||||
|
||||
# Find non-white pixels (content)
|
||||
non_white = gray < 250 # Threshold for white pixels
|
||||
|
||||
# Find bounding box of content
|
||||
coords = cv2.findNonZero(non_white.astype(np.uint8))
|
||||
if coords is not None:
|
||||
x, y, w, h = cv2.boundingRect(coords)
|
||||
return image[y:y+h, x:x+w]
|
||||
|
||||
return image
|
||||
|
||||
def resize_preserve_aspect(self, image: np.ndarray, target_size: Tuple[int, int]) -> np.ndarray:
|
||||
"""
|
||||
Resize image preserving aspect ratio with white padding
|
||||
|
||||
Args:
|
||||
image: Input image
|
||||
target_size: Target size (width, height)
|
||||
|
||||
Returns:
|
||||
Resized image with preserved aspect ratio
|
||||
"""
|
||||
target_width, target_height = target_size
|
||||
img_height, img_width = image.shape[:2]
|
||||
|
||||
# Calculate aspect ratios
|
||||
target_aspect = target_width / target_height
|
||||
img_aspect = img_width / img_height
|
||||
|
||||
if img_aspect > target_aspect:
|
||||
# Image is wider than target
|
||||
new_width = target_width
|
||||
new_height = int(target_width / img_aspect)
|
||||
else:
|
||||
# Image is taller than target
|
||||
new_height = target_height
|
||||
new_width = int(target_height * img_aspect)
|
||||
|
||||
# Resize image
|
||||
resized = cv2.resize(image, (new_width, new_height), interpolation=cv2.INTER_AREA)
|
||||
|
||||
# Create white background
|
||||
result = np.ones((target_height, target_width, 3), dtype=np.uint8) * 255
|
||||
|
||||
# Calculate offset to center the image
|
||||
offset_x = (target_width - new_width) // 2
|
||||
offset_y = (target_height - new_height) // 2
|
||||
|
||||
# Place resized image in center
|
||||
result[offset_y:offset_y+new_height, offset_x:offset_x+new_width] = resized
|
||||
|
||||
return result
|
||||
|
||||
|
||||
|
||||
def augment_single_image(self, image: np.ndarray, num_augmentations: int = None) -> List[np.ndarray]:
|
||||
"""
|
||||
Apply rotation augmentation to a single image
|
||||
Apply rotation augmentation to a single image with quality preservation
|
||||
|
||||
Args:
|
||||
image: Input image
|
||||
@@ -65,12 +167,18 @@ class DataAugmentation:
|
||||
angles = rotation_config.get("angles", [30, 60, 120, 150, 180, 210, 240, 300, 330])
|
||||
|
||||
for i in range(num_augmentations):
|
||||
# Start with original image
|
||||
augmented = image.copy()
|
||||
|
||||
# Apply rotation with random angle from the specified list
|
||||
# Apply rotation with quality preservation
|
||||
if rotation_config.get("enabled", False):
|
||||
angle = random.choice(angles)
|
||||
augmented = self.rotate_image(augmented, angle)
|
||||
augmented = self.rotate_image_preserve_quality(augmented, angle)
|
||||
|
||||
# Resize preserving aspect ratio
|
||||
target_size = self.image_processor.target_size
|
||||
if target_size:
|
||||
augmented = self.resize_preserve_aspect(augmented, target_size)
|
||||
|
||||
augmented_images.append(augmented)
|
||||
|
||||
@@ -78,7 +186,7 @@ class DataAugmentation:
|
||||
|
||||
def augment_image_file(self, image_path: Path, output_dir: Path, num_augmentations: int = None) -> List[Path]:
|
||||
"""
|
||||
Augment a single image file and save results
|
||||
Augment a single image file and save results with quality preservation
|
||||
|
||||
Args:
|
||||
image_path: Path to input image
|
||||
@@ -88,8 +196,8 @@ class DataAugmentation:
|
||||
Returns:
|
||||
List of paths to saved augmented images
|
||||
"""
|
||||
# Load image
|
||||
image = load_image(image_path, self.image_processor.target_size)
|
||||
# Load image without resizing to preserve original quality
|
||||
image = load_image(image_path, None) # Load original size
|
||||
if image is None:
|
||||
return []
|
||||
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
"""
|
||||
Image processing class for basic image operations
|
||||
Image processing class for data augmentation
|
||||
"""
|
||||
import cv2
|
||||
import numpy as np
|
||||
from pathlib import Path
|
||||
from typing import Tuple, Optional, List
|
||||
from utils import load_image, save_image, validate_image, get_image_files
|
||||
from typing import Tuple, Optional
|
||||
from utils import load_image
|
||||
|
||||
class ImageProcessor:
|
||||
"""Class for basic image processing operations"""
|
||||
"""Class for image processing operations used in data augmentation"""
|
||||
|
||||
def __init__(self, target_size: Tuple[int, int] = None):
|
||||
"""
|
||||
@@ -17,67 +17,7 @@ class ImageProcessor:
|
||||
Args:
|
||||
target_size: Target size for image resizing (width, height)
|
||||
"""
|
||||
self.target_size = target_size or (224, 224) # Default size
|
||||
|
||||
def load_and_preprocess(self, image_path: Path) -> Optional[np.ndarray]:
|
||||
"""
|
||||
Load and preprocess image
|
||||
|
||||
Args:
|
||||
image_path: Path to image file
|
||||
|
||||
Returns:
|
||||
Preprocessed image as numpy array or None if failed
|
||||
"""
|
||||
if not validate_image(image_path):
|
||||
print(f"Invalid image file: {image_path}")
|
||||
return None
|
||||
|
||||
image = load_image(image_path, self.target_size)
|
||||
if image is None:
|
||||
return None
|
||||
|
||||
# Normalize pixel values
|
||||
image = image.astype(np.float32) / 255.0
|
||||
|
||||
return image
|
||||
|
||||
def resize_image(self, image: np.ndarray, target_size: Tuple[int, int]) -> np.ndarray:
|
||||
"""
|
||||
Resize image to target size
|
||||
|
||||
Args:
|
||||
image: Input image as numpy array
|
||||
target_size: Target size (width, height)
|
||||
|
||||
Returns:
|
||||
Resized image
|
||||
"""
|
||||
return cv2.resize(image, target_size, interpolation=cv2.INTER_AREA)
|
||||
|
||||
def normalize_image(self, image: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Normalize image pixel values to [0, 1]
|
||||
|
||||
Args:
|
||||
image: Input image
|
||||
|
||||
Returns:
|
||||
Normalized image
|
||||
"""
|
||||
return image.astype(np.float32) / 255.0
|
||||
|
||||
def denormalize_image(self, image: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Denormalize image pixel values to [0, 255]
|
||||
|
||||
Args:
|
||||
image: Input image (normalized)
|
||||
|
||||
Returns:
|
||||
Denormalized image
|
||||
"""
|
||||
return (image * 255).astype(np.uint8)
|
||||
self.target_size = target_size or (640, 640) # Default size for ID cards
|
||||
|
||||
def get_image_info(self, image_path: Path) -> dict:
|
||||
"""
|
||||
@@ -107,68 +47,4 @@ class ImageProcessor:
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"Error getting image info for {image_path}: {e}")
|
||||
return {}
|
||||
|
||||
def batch_process_images(self, input_dir: Path, output_dir: Path) -> List[Path]:
|
||||
"""
|
||||
Process all images in a directory
|
||||
|
||||
Args:
|
||||
input_dir: Input directory containing images
|
||||
output_dir: Output directory for processed images
|
||||
|
||||
Returns:
|
||||
List of processed image paths
|
||||
"""
|
||||
image_files = get_image_files(input_dir)
|
||||
processed_files = []
|
||||
|
||||
print(f"Found {len(image_files)} images to process")
|
||||
|
||||
for i, image_path in enumerate(image_files):
|
||||
print_progress(i + 1, len(image_files), "Processing images")
|
||||
|
||||
# Load and preprocess image
|
||||
image = self.load_and_preprocess(image_path)
|
||||
if image is None:
|
||||
continue
|
||||
|
||||
# Create output path
|
||||
output_path = output_dir / image_path.name
|
||||
|
||||
# Denormalize for saving
|
||||
image = self.denormalize_image(image)
|
||||
|
||||
# Save processed image
|
||||
if save_image(image, output_path):
|
||||
processed_files.append(output_path)
|
||||
|
||||
print(f"\nProcessed {len(processed_files)} images successfully")
|
||||
return processed_files
|
||||
|
||||
def create_thumbnail(self, image: np.ndarray, size: Tuple[int, int] = (100, 100)) -> np.ndarray:
|
||||
"""
|
||||
Create thumbnail of image
|
||||
|
||||
Args:
|
||||
image: Input image
|
||||
size: Thumbnail size (width, height)
|
||||
|
||||
Returns:
|
||||
Thumbnail image
|
||||
"""
|
||||
return cv2.resize(image, size, interpolation=cv2.INTER_AREA)
|
||||
|
||||
def convert_to_grayscale(self, image: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Convert image to grayscale
|
||||
|
||||
Args:
|
||||
image: Input image (RGB)
|
||||
|
||||
Returns:
|
||||
Grayscale image
|
||||
"""
|
||||
if len(image.shape) == 3:
|
||||
return cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
|
||||
return image
|
||||
return {}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
13
src/utils.py
13
src/utils.py
@@ -32,14 +32,7 @@ def get_image_files(directory: Path) -> List[Path]:
|
||||
image_files.extend(directory.glob(f"*{ext.upper()}"))
|
||||
return sorted(image_files)
|
||||
|
||||
def validate_image(image_path: Path) -> bool:
|
||||
"""Validate if file is a valid image"""
|
||||
try:
|
||||
with Image.open(image_path) as img:
|
||||
img.verify()
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def load_image(image_path: Path, target_size: Tuple[int, int] = None) -> Optional[np.ndarray]:
|
||||
"""Load and resize image"""
|
||||
@@ -83,9 +76,7 @@ def create_augmented_filename(original_path: Path, index: int, suffix: str = "au
|
||||
suffix = f"_{suffix}_{index:02d}"
|
||||
return original_path.parent / f"{stem}{suffix}{original_path.suffix}"
|
||||
|
||||
def get_file_size_mb(file_path: Path) -> float:
|
||||
"""Get file size in MB"""
|
||||
return file_path.stat().st_size / (1024 * 1024)
|
||||
|
||||
|
||||
def print_progress(current: int, total: int, prefix: str = "Progress"):
|
||||
"""Print progress bar"""
|
||||
|
||||
Reference in New Issue
Block a user