feat: enhance layout preprocessing and unify image scaling proposal

Backend changes:
- Add image scaling configuration for PP-Structure processing
- Enhance layout preprocessing service with scaling support
- Update OCR service with improved memory management
- Add PP-Structure enhanced processing improvements

Frontend changes:
- Update preprocessing settings UI
- Fix processing page layout and state management
- Update API types for new parameters

Proposals:
- Archive add-layout-preprocessing proposal (completed)
- Add unify-image-scaling proposal for consistent coordinate handling

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-28 09:23:19 +08:00
parent 86bbea6fbf
commit dda9621e17
17 changed files with 826 additions and 104 deletions

View File

@@ -30,7 +30,7 @@ export default function PreprocessingSettings({
}: PreprocessingSettingsProps) {
const { t } = useTranslation()
const modes: PreprocessingMode[] = ['auto', 'manual', 'disabled']
const contrastOptions: PreprocessingContrast[] = ['none', 'histogram', 'clahe']
const contrastOptions: PreprocessingContrast[] = ['none', 'histogram', 'clahe', 'document']
const getModeInfo = (m: PreprocessingMode) => ({
label: t(`processing.preprocessing.mode.${m}`),

View File

@@ -81,7 +81,8 @@
"label": "對比度增強",
"none": "不增強",
"histogram": "直方圖均衡化",
"clahe": "CLAHE 自適應均衡化"
"clahe": "CLAHE 自適應均衡化",
"document": "掃描件優化 (背景校正+CLAHE)"
},
"sharpen": "邊緣銳化",
"strength": {

View File

@@ -382,23 +382,49 @@ export default function ProcessingPage() {
</div>
)}
{/* Direct Track Notice - Show when document is editable PDF */}
{documentAnalysis && documentAnalysis.recommended_track === 'direct' && (
<Card className="border-blue-200 bg-blue-50">
{/* Document Analysis Info */}
{documentAnalysis && (
<Card className={documentAnalysis.recommended_track === 'direct' ? 'border-blue-200 bg-blue-50' : 'border-green-200 bg-green-50'}>
<CardContent className="pt-4">
<div className="flex items-start gap-3">
<Info className="w-5 h-5 text-blue-600 flex-shrink-0 mt-0.5" />
<div>
<p className="text-sm font-medium text-blue-800"> PDF</p>
<p className="text-sm text-blue-700 mt-1">
PDF 使
</p>
{documentAnalysis.text_coverage && (
<p className="text-xs text-blue-600 mt-2">
: {(documentAnalysis.text_coverage * 100).toFixed(1)}%
</p>
<Info className={`w-5 h-5 flex-shrink-0 mt-0.5 ${documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}`} />
<div className="flex-1">
{documentAnalysis.recommended_track === 'direct' ? (
<>
<p className="text-sm font-medium text-blue-800"> PDF</p>
<p className="text-sm text-blue-700 mt-1">
PDF 使
</p>
</>
) : (
<>
<p className="text-sm font-medium text-green-800">
{documentAnalysis.is_editable ? '混合文件' : '掃描文件 / 影像'}
</p>
<p className="text-sm text-green-700 mt-1">
{documentAnalysis.reason}
</p>
</>
)}
<div className="flex flex-wrap gap-4 mt-2 text-xs">
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
: {documentAnalysis.recommended_track === 'direct' ? '直接提取' : documentAnalysis.recommended_track === 'ocr' ? 'OCR 識別' : '混合處理'}
</span>
{documentAnalysis.page_count && (
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
: {documentAnalysis.page_count}
</span>
)}
{documentAnalysis.text_coverage !== null && (
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
: {(documentAnalysis.text_coverage * 100).toFixed(1)}%
</span>
)}
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
: {(documentAnalysis.confidence * 100).toFixed(0)}%
</span>
</div>
</div>
</div>
</CardContent>

View File

@@ -408,7 +408,7 @@ class ApiClientV2 {
* Analyze document to get recommended processing track
*/
async analyzeDocument(taskId: string): Promise<DocumentAnalysisResponse> {
const response = await this.client.get<DocumentAnalysisResponse>(`/tasks/${taskId}/analyze`)
const response = await this.client.post<DocumentAnalysisResponse>(`/tasks/${taskId}/analyze`)
return response.data
}

View File

@@ -92,8 +92,12 @@ export type PreprocessingMode = 'auto' | 'manual' | 'disabled'
/**
* Contrast enhancement method for preprocessing.
* - none: No contrast enhancement
* - histogram: Standard histogram equalization
* - clahe: Contrast Limited Adaptive Histogram Equalization (good for most cases)
* - document: Background normalization + CLAHE (best for scanned documents)
*/
export type PreprocessingContrast = 'none' | 'histogram' | 'clahe'
export type PreprocessingContrast = 'none' | 'histogram' | 'clahe' | 'document'
/**
* Preprocessing configuration for layout detection enhancement.