feat: add contrast/sharpen strength controls, disable binarization

Major improvements to preprocessing controls:

Backend:
- Add contrast_strength (0.5-3.0) and sharpen_strength (0.5-2.0) to PreprocessingConfig
- Auto-detection now calculates optimal strength based on image quality metrics:
  - Lower contrast → Higher contrast_strength
  - Lower edge strength → Higher sharpen_strength
- Disable binarization in auto mode (rarely beneficial)
- CLAHE clipLimit now scales with contrast_strength
- Sharpening uses unsharp mask with variable strength

Frontend:
- Add strength sliders for contrast and sharpen in manual mode
- Sliders show current value and strength level (輕微/正常/強/最強)
- Move binarize option to collapsible "進階選項" section
- Updated i18n translations for strength labels

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-27 17:18:44 +08:00
parent f6d2957592
commit 5982fff71c
7 changed files with 212 additions and 53 deletions

View File

@@ -116,7 +116,9 @@ def process_task_ocr(
from app.schemas.task import PreprocessingContrastEnum
preprocess_config_obj = PreprocessingConfig(
contrast=PreprocessingContrastEnum(preprocessing_config.get("contrast", "clahe")),
contrast_strength=preprocessing_config.get("contrast_strength", 1.0),
sharpen=preprocessing_config.get("sharpen", True),
sharpen_strength=preprocessing_config.get("sharpen_strength", 1.0),
binarize=preprocessing_config.get("binarize", False)
)
@@ -772,7 +774,9 @@ async def start_task(
if options.preprocessing_config:
preprocessing_config = {
"contrast": options.preprocessing_config.contrast.value,
"contrast_strength": options.preprocessing_config.contrast_strength,
"sharpen": options.preprocessing_config.sharpen,
"sharpen_strength": options.preprocessing_config.sharpen_strength,
"binarize": options.preprocessing_config.binarize
}
logger.info(f"Preprocessing: mode={preprocessing_mode}, config={preprocessing_config}")

View File

@@ -72,13 +72,25 @@ class PreprocessingConfig(BaseModel):
default=PreprocessingContrastEnum.CLAHE,
description="Contrast enhancement method"
)
contrast_strength: float = Field(
default=1.0,
ge=0.5,
le=3.0,
description="Contrast enhancement strength (0.5=subtle, 1.0=normal, 2.0=strong, 3.0=maximum)"
)
sharpen: bool = Field(
default=True,
description="Enable sharpening for faint lines"
)
sharpen_strength: float = Field(
default=1.0,
ge=0.5,
le=2.0,
description="Sharpening strength (0.5=subtle, 1.0=normal, 1.5=strong, 2.0=maximum)"
)
binarize: bool = Field(
default=False,
description="Enable binarization (aggressive, for very low contrast)"
description="Enable binarization (aggressive, for very low contrast). Not recommended for most documents."
)

View File

@@ -110,34 +110,61 @@ class LayoutPreprocessingService:
"""
Determine optimal preprocessing config based on image quality.
Auto-detection calculates appropriate strength values:
- Lower image contrast → Higher contrast_strength
- Lower edge strength → Higher sharpen_strength
- Binarization is disabled by default (rarely beneficial)
Args:
metrics: Image quality metrics from analyze_image_quality()
Returns:
PreprocessingConfig with recommended settings
"""
# Determine contrast enhancement
# Determine contrast enhancement and strength
if metrics.contrast < self.contrast_threshold:
contrast = PreprocessingContrastEnum.CLAHE
# Calculate strength based on how far below threshold
# contrast=40 threshold, contrast=20 → strength=2.0, contrast=30 → strength=1.5
contrast_ratio = (self.contrast_threshold - metrics.contrast) / self.contrast_threshold
contrast_strength = min(1.0 + contrast_ratio * 2.0, 3.0) # Range: 1.0 to 3.0
else:
contrast = PreprocessingContrastEnum.NONE
contrast_strength = 1.0
# Determine sharpening
sharpen = metrics.edge_strength < self.edge_threshold
# Determine sharpening and strength
if metrics.edge_strength < self.edge_threshold:
sharpen = True
# Calculate strength based on how far below threshold
# edge=15 threshold, edge=5 → strength=1.67, edge=10 → strength=1.33
edge_ratio = (self.edge_threshold - metrics.edge_strength) / self.edge_threshold
sharpen_strength = min(1.0 + edge_ratio * 1.0, 2.0) # Range: 1.0 to 2.0
else:
sharpen = False
sharpen_strength = 1.0
# Determine binarization (only for very low contrast)
binarize = metrics.contrast < self.binarize_threshold
# Binarization is disabled by default - it rarely helps and often hurts
# Only enable for extremely low contrast (< 15) which indicates a scan quality issue
binarize = False # Disabled by default
logger.debug(
f"Auto config: contrast={contrast} strength={contrast_strength:.2f}, "
f"sharpen={sharpen} strength={sharpen_strength:.2f}, binarize={binarize}"
)
return PreprocessingConfig(
contrast=contrast,
contrast_strength=round(contrast_strength, 2),
sharpen=sharpen,
sharpen_strength=round(sharpen_strength, 2),
binarize=binarize
)
def apply_contrast_enhancement(
self,
image: np.ndarray,
method: PreprocessingContrastEnum
method: PreprocessingContrastEnum,
strength: float = 1.0
) -> np.ndarray:
"""
Apply contrast enhancement to image.
@@ -145,6 +172,11 @@ class LayoutPreprocessingService:
Args:
image: Input image (BGR)
method: Enhancement method (none, histogram, clahe)
strength: Enhancement strength (0.5-3.0, default 1.0)
- 0.5: Subtle enhancement
- 1.0: Normal enhancement
- 2.0: Strong enhancement
- 3.0: Maximum enhancement
Returns:
Enhanced image (BGR)
@@ -157,12 +189,17 @@ class LayoutPreprocessingService:
l_channel, a_channel, b_channel = cv2.split(lab)
if method == PreprocessingContrastEnum.HISTOGRAM:
# Standard histogram equalization
l_enhanced = cv2.equalizeHist(l_channel)
# Standard histogram equalization (strength affects blending)
l_equalized = cv2.equalizeHist(l_channel)
# Blend original with equalized based on strength
alpha = min(strength, 1.0) # Cap at 1.0 for histogram
l_enhanced = cv2.addWeighted(l_equalized, alpha, l_channel, 1 - alpha, 0)
elif method == PreprocessingContrastEnum.CLAHE:
# Contrast Limited Adaptive Histogram Equalization
# clipLimit controls contrast amplification: 2.0 is default, up to 6.0 for strong
clip_limit = self.clahe_clip_limit * strength # 2.0 * 1.0 = 2.0, 2.0 * 2.0 = 4.0
clahe = cv2.createCLAHE(
clipLimit=self.clahe_clip_limit,
clipLimit=clip_limit,
tileGridSize=self.clahe_tile_grid_size
)
l_enhanced = clahe.apply(l_channel)
@@ -175,18 +212,33 @@ class LayoutPreprocessingService:
return enhanced_bgr
def apply_sharpening(self, image: np.ndarray) -> np.ndarray:
def apply_sharpening(self, image: np.ndarray, strength: float = 1.0) -> np.ndarray:
"""
Apply sharpening to enhance edges and faint lines.
Apply sharpening to enhance edges and faint lines using unsharp mask.
Args:
image: Input image (BGR)
strength: Sharpening strength (0.5-2.0, default 1.0)
- 0.5: Subtle sharpening
- 1.0: Normal sharpening
- 1.5: Strong sharpening
- 2.0: Maximum sharpening
Returns:
Sharpened image (BGR)
"""
# Apply unsharp mask style sharpening
sharpened = cv2.filter2D(image, -1, self.sharpen_kernel)
# Use unsharp mask technique for better control
# 1. Create blurred version
# 2. Subtract from original (scaled by strength)
# 3. Add back to original
# Gaussian blur with sigma based on strength
sigma = 1.0
blurred = cv2.GaussianBlur(image, (0, 0), sigma)
# Unsharp mask: original + (original - blurred) * strength
# This is equivalent to: original * (1 + strength) - blurred * strength
sharpened = cv2.addWeighted(image, 1.0 + strength, blurred, -strength, 0)
# Clip values to valid range
sharpened = np.clip(sharpened, 0, 255).astype(np.uint8)
@@ -277,15 +329,19 @@ class LayoutPreprocessingService:
# Step 1: Contrast enhancement
if config.contrast != PreprocessingContrastEnum.NONE:
processed = self.apply_contrast_enhancement(processed, config.contrast)
processed = self.apply_contrast_enhancement(
processed,
config.contrast,
strength=config.contrast_strength
)
was_processed = True
logger.debug(f"Applied contrast enhancement: {config.contrast}")
logger.debug(f"Applied contrast enhancement: {config.contrast} (strength={config.contrast_strength})")
# Step 2: Sharpening
if config.sharpen:
processed = self.apply_sharpening(processed)
processed = self.apply_sharpening(processed, strength=config.sharpen_strength)
was_processed = True
logger.debug("Applied sharpening")
logger.debug(f"Applied sharpening (strength={config.sharpen_strength})")
# Step 3: Binarization (last step, overwrites color)
if config.binarize:

View File

@@ -41,6 +41,20 @@ export default function PreprocessingSettings({
onConfigChange({ ...config, [field]: value })
}
const getStrengthLabel = (value: number, type: 'contrast' | 'sharpen') => {
if (type === 'contrast') {
if (value <= 0.75) return t('processing.preprocessing.strength.subtle')
if (value <= 1.25) return t('processing.preprocessing.strength.normal')
if (value <= 2.0) return t('processing.preprocessing.strength.strong')
return t('processing.preprocessing.strength.maximum')
} else {
if (value <= 0.75) return t('processing.preprocessing.strength.subtle')
if (value <= 1.25) return t('processing.preprocessing.strength.normal')
if (value <= 1.5) return t('processing.preprocessing.strength.strong')
return t('processing.preprocessing.strength.maximum')
}
}
return (
<div className={cn('border rounded-lg p-4 bg-white', className)}>
{/* Header */}
@@ -131,14 +145,14 @@ export default function PreprocessingSettings({
{/* Manual Configuration (shown only when mode is 'manual') */}
{mode === 'manual' && (
<div className="mt-4 p-3 bg-gray-50 rounded-lg border border-gray-200 space-y-3">
<div className="mt-4 p-3 bg-gray-50 rounded-lg border border-gray-200 space-y-4">
<h4 className="text-sm font-medium text-gray-700">
{t('processing.preprocessing.manualConfig')}
</h4>
{/* Contrast Enhancement */}
<div>
<label className="block text-xs font-medium text-gray-600 mb-1.5">
<div className="space-y-2">
<label className="block text-xs font-medium text-gray-600">
{t('processing.preprocessing.contrast.label')}
</label>
<select
@@ -157,38 +171,99 @@ export default function PreprocessingSettings({
</option>
))}
</select>
{/* Contrast Strength Slider */}
{config.contrast !== 'none' && (
<div className="pt-1">
<div className="flex justify-between text-xs text-gray-500 mb-1">
<span>{t('processing.preprocessing.strength.label')}</span>
<span className="font-medium text-gray-700">
{config.contrast_strength.toFixed(1)} ({getStrengthLabel(config.contrast_strength, 'contrast')})
</span>
</div>
<input
type="range"
min="0.5"
max="3.0"
step="0.1"
value={config.contrast_strength}
onChange={(e) => handleConfigChange('contrast_strength', parseFloat(e.target.value))}
disabled={disabled}
className="w-full h-2 bg-gray-200 rounded-lg appearance-none cursor-pointer accent-blue-600"
/>
<div className="flex justify-between text-xs text-gray-400 mt-0.5">
<span>0.5</span>
<span>3.0</span>
</div>
</div>
)}
</div>
{/* Sharpen Toggle */}
<label className="flex items-center gap-2 cursor-pointer">
<input
type="checkbox"
checked={config.sharpen}
onChange={(e) => handleConfigChange('sharpen', e.target.checked)}
disabled={disabled}
className="w-4 h-4 rounded border-gray-300 text-blue-600 focus:ring-blue-500"
/>
<span className="text-sm text-gray-700">
{t('processing.preprocessing.sharpen')}
</span>
</label>
{/* Sharpen Section */}
<div className="space-y-2">
<label className="flex items-center gap-2 cursor-pointer">
<input
type="checkbox"
checked={config.sharpen}
onChange={(e) => handleConfigChange('sharpen', e.target.checked)}
disabled={disabled}
className="w-4 h-4 rounded border-gray-300 text-blue-600 focus:ring-blue-500"
/>
<span className="text-sm text-gray-700">
{t('processing.preprocessing.sharpen')}
</span>
</label>
{/* Binarize Toggle */}
<label className="flex items-center gap-2 cursor-pointer">
<input
type="checkbox"
checked={config.binarize}
onChange={(e) => handleConfigChange('binarize', e.target.checked)}
disabled={disabled}
className="w-4 h-4 rounded border-gray-300 text-blue-600 focus:ring-blue-500"
/>
<span className="text-sm text-gray-700">
{t('processing.preprocessing.binarize')}
</span>
<span className="text-xs text-orange-600">
({t('processing.preprocessing.binarizeWarning')})
</span>
</label>
{/* Sharpen Strength Slider */}
{config.sharpen && (
<div className="pl-6 pt-1">
<div className="flex justify-between text-xs text-gray-500 mb-1">
<span>{t('processing.preprocessing.strength.label')}</span>
<span className="font-medium text-gray-700">
{config.sharpen_strength.toFixed(1)} ({getStrengthLabel(config.sharpen_strength, 'sharpen')})
</span>
</div>
<input
type="range"
min="0.5"
max="2.0"
step="0.1"
value={config.sharpen_strength}
onChange={(e) => handleConfigChange('sharpen_strength', parseFloat(e.target.value))}
disabled={disabled}
className="w-full h-2 bg-gray-200 rounded-lg appearance-none cursor-pointer accent-blue-600"
/>
<div className="flex justify-between text-xs text-gray-400 mt-0.5">
<span>0.5</span>
<span>2.0</span>
</div>
</div>
)}
</div>
{/* Binarize Toggle - Hidden by default, shown only in advanced mode */}
<details className="pt-2">
<summary className="text-xs text-gray-500 cursor-pointer hover:text-gray-700">
{t('processing.preprocessing.advanced')}
</summary>
<div className="mt-2 pl-2 border-l-2 border-gray-200">
<label className="flex items-center gap-2 cursor-pointer">
<input
type="checkbox"
checked={config.binarize}
onChange={(e) => handleConfigChange('binarize', e.target.checked)}
disabled={disabled}
className="w-4 h-4 rounded border-gray-300 text-blue-600 focus:ring-blue-500"
/>
<span className="text-sm text-gray-700">
{t('processing.preprocessing.binarize')}
</span>
<span className="text-xs text-orange-600">
({t('processing.preprocessing.binarizeWarning')})
</span>
</label>
</div>
</details>
</div>
)}

View File

@@ -68,9 +68,9 @@
"title": "影像前處理",
"mode": {
"auto": "自動模式",
"autoDesc": "系統自動分析影像品質,決定最佳的前處理方式",
"autoDesc": "系統自動分析影像品質,決定最佳的前處理方式和強度",
"manual": "手動模式",
"manualDesc": "手動選擇前處理選項,完全控制處理流程",
"manualDesc": "手動選擇前處理選項和強度,完全控制處理流程",
"disabled": "停用前處理",
"disabledDesc": "不進行任何前處理,直接使用原始影像"
},
@@ -84,8 +84,16 @@
"clahe": "CLAHE 自適應均衡化"
},
"sharpen": "邊緣銳化",
"strength": {
"label": "強度",
"subtle": "輕微",
"normal": "正常",
"strong": "強",
"maximum": "最強"
},
"advanced": "進階選項",
"binarize": "二值化處理",
"binarizeWarning": "可能影響顏色資訊",
"binarizeWarning": "不建議使用",
"note": "前處理僅影響版面偵測階段,用於改善表格和文字區塊的識別。原始影像仍用於最終的 OCR 文字提取,確保最佳識別品質。"
}
},

View File

@@ -39,7 +39,9 @@ export default function ProcessingPage() {
const [preprocessingMode, setPreprocessingMode] = useState<PreprocessingMode>('auto')
const [preprocessingConfig, setPreprocessingConfig] = useState<PreprocessingConfig>({
contrast: 'clahe',
contrast_strength: 1.0,
sharpen: true,
sharpen_strength: 1.0,
binarize: false,
})

View File

@@ -100,7 +100,9 @@ export type PreprocessingContrast = 'none' | 'histogram' | 'clahe'
*/
export interface PreprocessingConfig {
contrast: PreprocessingContrast
contrast_strength: number // 0.5-3.0, default 1.0
sharpen: boolean
sharpen_strength: number // 0.5-2.0, default 1.0
binarize: boolean
}