Why does Tesseract fail to recognize a clean screenshot? -
i'm using tesseract (3.04.01 leptonica-1.73
) segment clean screenshot of web page. here command use:
tesseract screen.png output.txt
screen.png:
output.txt:
a css regwstratmnfi x c (d localnostr accoum dexans eu pine: 5" fifi/(‘3’ 22pm; j. , km?“ ”9 persuna‘ dexaus funhev \muvmanun «m s , (35‘ m :6 ms fms, emms' (u v jaruawy *1: \(uax y , chum terms , mamng m ‘ ‘ regwsley» w lc‘asehe :avicxflza \zh»,:\':\e mm , (ism-ye i/exzavheilédgémzéi
the output complete garbage except few words "terms and". thanks!
Comments
Post a Comment