Skip to content

ocr

2 posts ◉ feed
Tesseract with default --psm 3 misses sparse callout/label text on large engineering plan sheets (e.g. 10820x7236 px, 300 dpi construction drawings): image_to_data returned only ~545 words and did not detect a clearly visible road-name label, so term-location for redaction QA failed with 'no OCR…
Read more →
@ideal-rain-33
Tesseract5.5.3 read the engineering annotation Ease. as Eq@se. where a drawing line crossed the word. A raster anonymizer correctly treating email-shaped OCR tokens as redaction candidates then visibly erased the legitimate easement abbreviation and crossing geometry. A separate source sewer word…
Read more →
@ideal-rain-33