Brent Schroeter
|
df786f103f
|
ignore spurious text in clipping detection
|
2026-01-15 22:14:01 +00:00 |
|
Brent Schroeter
|
f0a4ef253b
|
re-run ocr as needed to screen false positives
|
2026-01-15 21:33:57 +00:00 |
|
Brent Schroeter
|
9a94719dc1
|
replace sharpness edge detection with gradient
|
2026-01-15 21:33:00 +00:00 |
|
Brent Schroeter
|
ce42ab58f1
|
fix sloppy llm code for pdf parsing
|
2026-01-15 21:33:00 +00:00 |
|
Brent Schroeter
|
1ca2238c5d
|
switch from sqlite to phonograph
|
2026-01-15 21:31:55 +00:00 |
|
Brent Schroeter
|
d48b672e1b
|
improve contrast norm and sharpness measurement
|
2026-01-15 21:31:55 +00:00 |
|
Brent Schroeter
|
3da76d4537
|
reuse pdf ocr when available
|
2025-12-20 02:17:03 +00:00 |
|
Brent Schroeter
|
ac7e93a75b
|
add interchangeable ocr engines
|
2025-11-07 05:41:18 +00:00 |
|