fix(ocr): decrease detection threshold and increase padding for better text extraction
Decrease the detection box threshold from 0.6 to 0.3 to ensure more text areas are identified,
and increase the padding around each detected area from 25 to 50 pixels. This leads to a more comprehensive text extraction from documents.
fix(self_modify): merge detection boxes for optimized text region detection
Merge adjacent and overlapping detection boxes to optimize text region detection in
the document. Post processing of text boxes is enhanced by consolidating them into
larger text lines, taking into account their vertical and horizontal alignment. This
improvement reduces fragmentation and improves the readability of detected text blocks.
Decrease the detection box threshold from 0.6 to 0.3 to ensure more text areas are identified, and increase the padding around each detected area from 25 to 50 pixels. This leads to a more comprehensive text extraction from documents.
Merge adjacent and overlapping detection boxes to optimize text region detection in the document. Post processing of text boxes is enhanced by consolidating them into larger text lines, taking into account their vertical and horizontal alignment. This improvement reduces fragmentation and improves the readability of detected text blocks.