feat: add Structure step to Kombi mode in OCR Overlay page
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 28s
CI / test-go-edu-search (push) Successful in 33s
CI / test-python-klausur (push) Failing after 2m1s
CI / test-python-agent-core (push) Successful in 19s
CI / test-nodejs-website (push) Successful in 19s

Insert the Struktur detection step between Zuschneiden and
PP-OCRv5+Tesseract in the Kombi pipeline on /ai/ocr-overlay.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-16 12:59:05 +01:00
parent 5b5213c2b9
commit 1d34785e2b
2 changed files with 16 additions and 7 deletions

View File

@@ -7,6 +7,7 @@ import { StepOrientation } from '@/components/ocr-pipeline/StepOrientation'
import { StepDeskew } from '@/components/ocr-pipeline/StepDeskew' import { StepDeskew } from '@/components/ocr-pipeline/StepDeskew'
import { StepDewarp } from '@/components/ocr-pipeline/StepDewarp' import { StepDewarp } from '@/components/ocr-pipeline/StepDewarp'
import { StepCrop } from '@/components/ocr-pipeline/StepCrop' import { StepCrop } from '@/components/ocr-pipeline/StepCrop'
import { StepStructureDetection } from '@/components/ocr-pipeline/StepStructureDetection'
import { StepRowDetection } from '@/components/ocr-pipeline/StepRowDetection' import { StepRowDetection } from '@/components/ocr-pipeline/StepRowDetection'
import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecognition' import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecognition'
import { OverlayReconstruction } from '@/components/ocr-overlay/OverlayReconstruction' import { OverlayReconstruction } from '@/components/ocr-overlay/OverlayReconstruction'
@@ -74,9 +75,13 @@ export default function OcrOverlayPage() {
const baseSteps = isKombi ? KOMBI_STEPS : PADDLE_DIRECT_STEPS const baseSteps = isKombi ? KOMBI_STEPS : PADDLE_DIRECT_STEPS
setMode(m) setMode(m)
// For Kombi: if grid_editor_result exists, jump to grid editor step (5) // For Kombi: if grid_editor_result exists, jump to grid editor step (6)
// If word_result exists but no grid, jump to grid editor (6)
// If structure_result exists, jump to kombi step (5)
const hasGrid = isKombi && data.grid_editor_result const hasGrid = isKombi && data.grid_editor_result
const activeStep = hasGrid ? 5 : 4 const hasWords = isKombi && data.word_result
const hasStructure = isKombi && data.structure_result
const activeStep = hasGrid ? 6 : hasWords ? 6 : hasStructure ? 5 : 4
setSteps( setSteps(
baseSteps.map((s, i) => ({ baseSteps.map((s, i) => ({
...s, ...s,
@@ -246,6 +251,11 @@ export default function OcrOverlayPage() {
case 3: case 3:
return <StepCrop sessionId={sessionId} onNext={handleNext} /> return <StepCrop sessionId={sessionId} onNext={handleNext} />
case 4: case 4:
if (mode === 'kombi') {
return <StepStructureDetection sessionId={sessionId} onNext={handleNext} />
}
return <PaddleDirectStep sessionId={sessionId} onNext={handleNext} />
case 5:
return mode === 'kombi' ? ( return mode === 'kombi' ? (
<PaddleDirectStep <PaddleDirectStep
sessionId={sessionId} sessionId={sessionId}
@@ -258,10 +268,8 @@ export default function OcrOverlayPage() {
runningLabel="PP-OCRv5 + Tesseract laufen..." runningLabel="PP-OCRv5 + Tesseract laufen..."
engineKey="kombi" engineKey="kombi"
/> />
) : ( ) : null
<PaddleDirectStep sessionId={sessionId} onNext={handleNext} /> case 6:
)
case 5:
return mode === 'kombi' ? ( return mode === 'kombi' ? (
<GridEditor sessionId={sessionId} onNext={handleNext} /> <GridEditor sessionId={sessionId} onNext={handleNext} />
) : null ) : null
@@ -521,7 +529,7 @@ export default function OcrOverlayPage() {
: 'text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300' : 'text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300'
}`} }`}
> >
Kombi (6 Schritte) Kombi (7 Schritte)
</button> </button>
</div> </div>

View File

@@ -69,6 +69,7 @@ export const KOMBI_STEPS: PipelineStep[] = [
{ id: 'deskew', name: 'Begradigung', icon: '📐', status: 'pending' }, { id: 'deskew', name: 'Begradigung', icon: '📐', status: 'pending' },
{ id: 'dewarp', name: 'Entzerrung', icon: '🔧', status: 'pending' }, { id: 'dewarp', name: 'Entzerrung', icon: '🔧', status: 'pending' },
{ id: 'crop', name: 'Zuschneiden', icon: '✂️', status: 'pending' }, { id: 'crop', name: 'Zuschneiden', icon: '✂️', status: 'pending' },
{ id: 'structure', name: 'Struktur', icon: '🔍', status: 'pending' },
{ id: 'kombi', name: 'PP-OCRv5 + Tesseract', icon: '🔀', status: 'pending' }, { id: 'kombi', name: 'PP-OCRv5 + Tesseract', icon: '🔀', status: 'pending' },
{ id: 'grid-editor', name: 'Tabelle', icon: '📊', status: 'pending' }, { id: 'grid-editor', name: 'Tabelle', icon: '📊', status: 'pending' },
] ]