Flexible inhaltsbasierte Spaltenerkennung (2-Phasen)
Ersetzt hardcodierte Positionsregeln durch ein zweistufiges System: Phase A erkennt Spaltengeometrie (Clustering), Phase B klassifiziert Typen per Inhalt (Sprache/Rolle) mit 3-stufiger Fallback-Kette. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -64,11 +64,14 @@ export interface DewarpGroundTruth {
|
||||
}
|
||||
|
||||
export interface PageRegion {
|
||||
type: 'column_en' | 'column_de' | 'column_example' | 'page_ref' | 'column_marker' | 'header' | 'footer'
|
||||
type: 'column_en' | 'column_de' | 'column_example' | 'page_ref'
|
||||
| 'column_marker' | 'column_text' | 'header' | 'footer'
|
||||
x: number
|
||||
y: number
|
||||
width: number
|
||||
height: number
|
||||
classification_confidence?: number
|
||||
classification_method?: string
|
||||
}
|
||||
|
||||
export interface ColumnResult {
|
||||
|
||||
Reference in New Issue
Block a user