Tesseract OCR 词库训练时一些错误的解决办法_巳夲拏彧

个人资料

微博

正文字体大小：大中小

Tesseract OCR 词库训练时一些错误的解决办法

(2014-09-07 19:53:29)

标签：

分类：想想专业

错误一：

tesseract code.one.exp19.tif code.one.exp19 -l eng

-psm 7 box.train

Tesseract Open Source OCR Engine v3.02 with Leptonica

APPLY_BOXES: boxfile line 3/3 ((50,8),(59,24)): FAILURE! Couldn't find a matchin

g blob

APPLY_BOXES:

Boxes read from boxfile: 4

Boxes failed resegmentation: 1

APPLY_BOXES: Unlabelled word at :Bounding box=(50,4)->(60,24)

Found 3 good blobs.

Leaving 2 unlabelled blobs in 0 words.

1 remaining unlabelled words deleted.

TRAINING ... Font name = one

Generated training data for 1 words

解决：

BOX文件RECT不正确，需要调整，实在是调整不了的换个图片

错误二：

Warning: No shape table file present: shapetable

解决：

需要先调用 shapeclustering 命令

阅读┊ 收藏 ┊ 喜欢 ▼ ┊打印┊举报/Report