¥Í¥¿¸µ:
- GitHub / tesseract-ocr / tesseract
- Tesseract documentation
- Wikipedia / Tesseract
- Qiita
- henjiganai / 2019-12-12: Python¤ÈTesseract OCR¤Çʸ»úǧ¼±
- FukuharaYohei / 2019-05-14: Tesseract¤òUbuntu¤Ë¥¤¥ó¥¹¥È¡¼¥ë¤·¤ÆPython¤Ç»È¤¦
- tifa2chan
- 2018-10-30: tesseract¤ò»È¤Ã¤Æ¤ß¤è¤¦¡Ê½é¿´¼ÔÊÔ¡Ë
- 2018-10-30: tesseract¤ò»È¤Ã¤Æ¤ß¤è¤¦¢¡Ê½é¿´¼ÔÊÔ¡Ë
´ðËܤϰʲ¼¤Î¥³¥Þ¥ó¥É¡£
<dpi> ¤Ï²èÁü¤Ë dpi ¤¬Ëä¤á¹þ¤Þ¤ì¤Æ¤¤¤ë¾ì¹ç¤ÏÉÔÍפʤ褦¤À¤¬¡¢Ëä¤á¹þ¤Þ¤ì¤Æ¤Ê¤¤¾ì¹ç¤Ï¸å½Ò¤Î¤è¤¦¤Ë·Ù¹ð¤¬½Ð¤ë¤è¤¦¤Ê¤Î¤ÇŬÀÚ¤ÊÃͤòÀßÄꤹ¤ë¤Èǧ¼±Î¨¤¬²þÁ±¤¹¤ë²ÄǽÀ¤¬¤¢¤ë¡£
DPI Ãͤ¬Ëä¤á¹þ¤Þ¤ì¤Æ¤Ê¤¤²èÁü¤Ë DPI ÃÍ(Î㤨¤Ð 96 dpi)¤òËä¤á¹þ¤ß¤¿¤¤¾ì¹ç¤Ï°Ê²¼¤Î¤è¤¦¤Ë¤¹¤ì¤ÐÎɤ¤¡£
ExifTool ¤ò»È¤¦¾ì¹ç
tesseract <src img file> <dst txt file> --lang jpn [--dpi <dpi>]<dst txt file> ¤Î³ÈÄ¥»Ò¤¬¾¡¼ê¤ËÉÕÍ¿¤µ¤ì¤ë¤Î¤Ç .txt ¤Ï¾Ê¤¤¤Æ¤ª¤¯É¬Íפ¬¤¢¤ë¡£"stdout" ¤Þ¤¿¤Ï "-" ¤Î¾ì¹çɸ½à½ÐÎÏ°·¤¤¡£
<dpi> ¤Ï²èÁü¤Ë dpi ¤¬Ëä¤á¹þ¤Þ¤ì¤Æ¤¤¤ë¾ì¹ç¤ÏÉÔÍפʤ褦¤À¤¬¡¢Ëä¤á¹þ¤Þ¤ì¤Æ¤Ê¤¤¾ì¹ç¤Ï¸å½Ò¤Î¤è¤¦¤Ë·Ù¹ð¤¬½Ð¤ë¤è¤¦¤Ê¤Î¤ÇŬÀÚ¤ÊÃͤòÀßÄꤹ¤ë¤Èǧ¼±Î¨¤¬²þÁ±¤¹¤ë²ÄǽÀ¤¬¤¢¤ë¡£
DPI Ãͤ¬Ëä¤á¹þ¤Þ¤ì¤Æ¤Ê¤¤²èÁü¤Ë DPI ÃÍ(Î㤨¤Ð 96 dpi)¤òËä¤á¹þ¤ß¤¿¤¤¾ì¹ç¤Ï°Ê²¼¤Î¤è¤¦¤Ë¤¹¤ì¤ÐÎɤ¤¡£
ExifTool ¤ò»È¤¦¾ì¹ç
exiftool -{X,Y}Resolution=96 -ResolutionUnit=inches <dst.jpg>
exiftool -PixelsPerUnit{X,Y}=$((96*10000/254)) -PixelUnits=meters <dst.png>ImageMagick¤ò»È¤¦¾ì¹ç
mogrify -density 96 -units PixelsPerInch <dst>¤Þ¤¿¤Ï
convert -density 96 -units PixelsPerInch <src> <dst>»²¹Í:
- backport / 2019-01-28: ImageMagick¤ÇPNG¥Õ¥¡¥¤¥ë¤Îdpi¤òÊѹ¹¤¹¤ë
ÆüËܸìÍѤΠlanguage file ¤È¤·¤Æ¤Ï°Ê²¼¤Î 2 ¤Ä¤¬¤¢¤ë¤è¤¦¤À¡£
ξ¼Ô¤Î°ã¤¤¤Ï¡¢Á°¼Ô¤Ï¤Û¤ÜÆɤó¤À¤Þ¤Þǧ¼±¤µ¤ì¤ë¤Î¤ËÂФ·¤Æ¡¢¸å¼Ô¤Ï1ʸ»ú1ʸ»ú¥¹¥Ú¡¼¥¹¤Ç¶èÀڤ俾õÂÖ¤Çǧ¼±¤µ¤ì¤ë¤è¤¦¤Ê¤Î¤Ç¡¢´ðËÜŪ¤ËÁ°¼Ô¤ò»È¤Ã¤Æ¤ª¤±¤ÐÌäÂê¤Ê¤µ¤½¤¦¡£
- tesseract-ocr-jpn, tesseract-ocr-jpn-vert
- tesseract-ocr-script-jpan, tesseract-ocr-script-jpan-vert
ξ¼Ô¤Î°ã¤¤¤Ï¡¢Á°¼Ô¤Ï¤Û¤ÜÆɤó¤À¤Þ¤Þǧ¼±¤µ¤ì¤ë¤Î¤ËÂФ·¤Æ¡¢¸å¼Ô¤Ï1ʸ»ú1ʸ»ú¥¹¥Ú¡¼¥¹¤Ç¶èÀڤ俾õÂÖ¤Çǧ¼±¤µ¤ì¤ë¤è¤¦¤Ê¤Î¤Ç¡¢´ðËÜŪ¤ËÁ°¼Ô¤ò»È¤Ã¤Æ¤ª¤±¤ÐÌäÂê¤Ê¤µ¤½¤¦¡£
GitHub ¤Ë¤¢¤ë¸ø¼°¥É¥¥å¥á¥ó¥È¤Ë pre-build binary ¤Ø¤Î¥ê¥ó¥¯¤¬¤¢¤ë¤¬ÌÌÅݤ½¤¦¤Ê¤Î¤Ç¡¢
Windows 10 ¤Ç WSL »È¤¨¤ÆÆÃÃÊ win32 ¤Ë¤³¤À¤ï¤ëÍýͳ¤¬¤Ê¤¤¤Ê¤é Ubuntu on WSL ¤Ç¤ä¤ë¤Î¤¬µÈ¤À¤í¤¦¡£
Windows 10 ¤Ç WSL »È¤¨¤ÆÆÃÃÊ win32 ¤Ë¤³¤À¤ï¤ëÍýͳ¤¬¤Ê¤¤¤Ê¤é Ubuntu on WSL ¤Ç¤ä¤ë¤Î¤¬µÈ¤À¤í¤¦¡£
¡ÖTesseract¡×¤Ç¥°¥°¤Ã¤¿ºÝ¡¢±¦¾å¤Ëɽ¼¨¤µ¤ì¤¿Í×Ìó
¤ò Firefox ¤Ç¥¹¥¯¥·¥ç¤·¤¿¤â¤Î¤Ç»î¤·¤Æ¤ß¤¿½ê¡¢°Ê²¼¤Î¤è¤¦¤Ê·Ù¹ð¤È¥¨¥é¡¼¤¬½Ð¤¿¡£
¥¨¥é¡¼¤ÎÊý¤ÏÎΰè¤Î¼«Æ°Ç§¼±¤ÎÌäÂê¤ß¤¿¤¤¤Ê¤Î¤Ç¡¢ÊÝα¡£
·Ù¹ð¤Ï DPI ¤¬ÉÔÀµ(=0)¤Ê¤Î¤Ç 70 ¤ò»È¤¦¤¬¡¢¿äÄêÃÍ¤Ï 162 ¤ß¤¿¤¤¤Ê»ö¤ò¸À¤Ã¤Æ¤ë¡£
¥Í¥¿¸µ¤Î @konamih ÀèÀ¸¤â¸ÀµÚ¤µ¤ì¤Æ¤¤¤ë¤¬¡¢DPI »ØÄ꤬ŬÀڤǤʤ¤¤Èǧ¼±Î¨¤Ë°±Æ¶Á¤¬½Ð¤ëÌÏÍÍ¡£
°Ê²¼¡¢Èæ³Ó
¸«¤Æ¤ÎÄ̤ꡢ¥Ç¥¹¥¯¥È¥Ã¥×ËÜÍè¤Î²òÁüÅ٤Ǥ¢¤ë 96 dpi ¤¬ºÇ¤âÎɤµ¤½¤¦¤Ê·ë²Ì¤È¤Ê¤Ã¤Æ¤¤¤ë¡£
¼ºÇÔ¤·¤Æ¤¤¤ëÉôʬ¤â¾¯¤Ê¤¯¤Ê¤¤¤¬¡¢¤³¤Î¥ì¥Ù¥ë¤Îǧ¼±¤¬ OSS ¤Ç½ÐÍè¤ë¤Î¤ÏͤêÆñ¤¤¡£
¤ò Firefox ¤Ç¥¹¥¯¥·¥ç¤·¤¿¤â¤Î¤Ç»î¤·¤Æ¤ß¤¿½ê¡¢°Ê²¼¤Î¤è¤¦¤Ê·Ù¹ð¤È¥¨¥é¡¼¤¬½Ð¤¿¡£
$ tesseract -l jpn Screenshot\ 2021-10-11\ at\ 16-40-17\ Tesseract\ -\ Google\ ¸¡º÷.png ocr Tesseract Open Source OCR Engine v4.1.1 with Leptonica Warning: Invalid resolution 0 dpi. Using 70 instead. Estimating resolution as 162 Error in boxClipToRectangle: box outside rectangle Error in pixScanForForeground: invalid box Error in boxClipToRectangle: box outside rectangle Error in pixScanForForeground: invalid box Detected 14 diacritics
¥¨¥é¡¼¤ÎÊý¤ÏÎΰè¤Î¼«Æ°Ç§¼±¤ÎÌäÂê¤ß¤¿¤¤¤Ê¤Î¤Ç¡¢ÊÝα¡£
·Ù¹ð¤Ï DPI ¤¬ÉÔÀµ(=0)¤Ê¤Î¤Ç 70 ¤ò»È¤¦¤¬¡¢¿äÄêÃÍ¤Ï 162 ¤ß¤¿¤¤¤Ê»ö¤ò¸À¤Ã¤Æ¤ë¡£
¥Í¥¿¸µ¤Î @konamih ÀèÀ¸¤â¸ÀµÚ¤µ¤ì¤Æ¤¤¤ë¤¬¡¢DPI »ØÄ꤬ŬÀڤǤʤ¤¤Èǧ¼±Î¨¤Ë°±Æ¶Á¤¬½Ð¤ëÌÏÍÍ¡£
°Ê²¼¡¢Èæ³Ó
¸«¤Æ¤ÎÄ̤ꡢ¥Ç¥¹¥¯¥È¥Ã¥×ËÜÍè¤Î²òÁüÅ٤Ǥ¢¤ë 96 dpi ¤¬ºÇ¤âÎɤµ¤½¤¦¤Ê·ë²Ì¤È¤Ê¤Ã¤Æ¤¤¤ë¡£
¼ºÇÔ¤·¤Æ¤¤¤ëÉôʬ¤â¾¯¤Ê¤¯¤Ê¤¤¤¬¡¢¤³¤Î¥ì¥Ù¥ë¤Îǧ¼±¤¬ OSS ¤Ç½ÐÍè¤ë¤Î¤ÏͤêÆñ¤¤¡£
- ¥«¥Æ¥´¥ê¡§
- ¥Ñ¥½¥³¥ó
- ¥×¥í¥°¥é¥ß¥ó¥°
¥¿¥°
¥³¥á¥ó¥È¤ò¤«¤¯