Spaces:
Runtime error
Runtime error
File size: 8,422 Bytes
eb5a9e1 |
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 |
"""
Image Processor Module
Handles all image processing operations including loading, validation,
resizing, normalization, and format conversion.
"""
import hashlib
import magic
from pathlib import Path
from typing import Tuple, Optional, Union
import numpy as np
from PIL import Image, ImageOps
from loguru import logger
from core.config import config
from core.exceptions import (
ImageProcessingError,
InvalidFileError,
FileSizeError,
UnsupportedFormatError,
)
class ImageProcessor:
"""
Process images for analysis.
Handles validation, resizing, normalization, and format conversion
for images before they are passed to AI models.
"""
def __init__(self):
"""Initialize ImageProcessor."""
self.max_size = config.MAX_IMAGE_SIZE
self.max_dimension = config.IMAGE_MAX_DIMENSION
self.allowed_formats = config.ALLOWED_IMAGE_FORMATS
logger.info("ImageProcessor initialized")
def load_image(self, image_path: Union[str, Path]) -> Image.Image:
"""
Load image from file path.
Args:
image_path: Path to image file
Returns:
PIL Image object
Raises:
InvalidFileError: If image cannot be loaded
"""
try:
image_path = Path(image_path)
if not image_path.exists():
raise InvalidFileError(
f"Image file not found: {image_path}",
{"path": str(image_path)}
)
# Validate file
self.validate_image(image_path)
# Load image
image = Image.open(image_path)
# Convert to RGB if necessary
if image.mode != "RGB":
image = image.convert("RGB")
logger.info(f"Loaded image: {image_path.name} ({image.size})")
return image
except Exception as e:
logger.error(f"Failed to load image: {e}")
raise InvalidFileError(
f"Cannot load image: {str(e)}",
{"path": str(image_path), "error": str(e)}
)
def validate_image(self, image_path: Path) -> bool:
"""
Validate image file.
Args:
image_path: Path to image file
Returns:
True if valid
Raises:
FileSizeError: If file too large
UnsupportedFormatError: If format not supported
InvalidFileError: If file is corrupted
"""
# Check file size
file_size = image_path.stat().st_size
if file_size > self.max_size:
raise FileSizeError(
f"Image too large: {file_size / 1024 / 1024:.1f}MB",
{"max_size": self.max_size, "actual_size": file_size}
)
# Check file extension
ext = image_path.suffix.lower()
if ext not in self.allowed_formats:
raise UnsupportedFormatError(
f"Unsupported image format: {ext}",
{"allowed": self.allowed_formats, "received": ext}
)
# Check MIME type using magic bytes
try:
mime = magic.from_file(str(image_path), mime=True)
if not mime.startswith("image/"):
raise InvalidFileError(
f"File is not a valid image: {mime}",
{"mime_type": mime}
)
except Exception as e:
logger.warning(f"Could not verify MIME type: {e}")
return True
def resize_image(
self,
image: Image.Image,
max_size: Optional[Tuple[int, int]] = None,
maintain_aspect_ratio: bool = True
) -> Image.Image:
"""
Resize image to specified dimensions.
Args:
image: PIL Image object
max_size: Maximum (width, height) tuple
maintain_aspect_ratio: Whether to maintain aspect ratio
Returns:
Resized PIL Image
"""
if max_size is None:
max_size = config.DEFAULT_IMAGE_SIZE
original_size = image.size
if maintain_aspect_ratio:
# Calculate new size maintaining aspect ratio
image.thumbnail(max_size, Image.Resampling.LANCZOS)
else:
# Resize to exact dimensions
image = image.resize(max_size, Image.Resampling.LANCZOS)
logger.debug(f"Resized image: {original_size} -> {image.size}")
return image
def normalize_image(self, image: Image.Image) -> np.ndarray:
"""
Normalize image to numpy array with values [0, 1].
Args:
image: PIL Image object
Returns:
Normalized numpy array (H, W, C)
"""
# Convert to numpy array
img_array = np.array(image, dtype=np.float32)
# Normalize to [0, 1]
img_array = img_array / 255.0
logger.debug(f"Normalized image to shape: {img_array.shape}")
return img_array
def apply_exif_orientation(self, image: Image.Image) -> Image.Image:
"""
Apply EXIF orientation to image.
Args:
image: PIL Image object
Returns:
Oriented PIL Image
"""
try:
image = ImageOps.exif_transpose(image)
logger.debug("Applied EXIF orientation")
except Exception as e:
logger.warning(f"Could not apply EXIF orientation: {e}")
return image
def get_image_hash(self, image_path: Path) -> str:
"""
Generate SHA256 hash of image file.
Args:
image_path: Path to image file
Returns:
Hex string of hash
"""
sha256_hash = hashlib.sha256()
with open(image_path, "rb") as f:
# Read in chunks to handle large files
for chunk in iter(lambda: f.read(8192), b""):
sha256_hash.update(chunk)
return sha256_hash.hexdigest()
def process(
self,
image_path: Union[str, Path],
resize: bool = True,
normalize: bool = False,
apply_orientation: bool = True
) -> Union[Image.Image, np.ndarray]:
"""
Complete image processing pipeline.
Args:
image_path: Path to image file
resize: Whether to resize image
normalize: Whether to normalize to numpy array
apply_orientation: Whether to apply EXIF orientation
Returns:
Processed image (PIL Image or numpy array)
"""
try:
# Load image
image = self.load_image(image_path)
# Apply EXIF orientation
if apply_orientation:
image = self.apply_exif_orientation(image)
# Resize if needed
if resize:
image = self.resize_image(image)
# Normalize if needed
if normalize:
return self.normalize_image(image)
return image
except Exception as e:
logger.error(f"Image processing failed: {e}")
raise ImageProcessingError(
f"Failed to process image: {str(e)}",
{"path": str(image_path), "error": str(e)}
)
def get_image_info(self, image_path: Union[str, Path]) -> dict:
"""
Get information about an image.
Args:
image_path: Path to image file
Returns:
Dictionary with image information
"""
image_path = Path(image_path)
image = self.load_image(image_path)
return {
"filename": image_path.name,
"format": image.format,
"mode": image.mode,
"size": image.size,
"width": image.size[0],
"height": image.size[1],
"file_size": image_path.stat().st_size,
"hash": self.get_image_hash(image_path),
}
|