jtessboxeditor训练字库遇到的问题
想学习下OCR文字训练
运行结果
PS D:\A> mftraining -F font_properties -U unicharset -O num_1.unicharset num_1.font.exp0.tr
Warning: No shape table file present: shapetable
Failed to load unicharset from file unicharset
Building unicharset for training from scratch...
Failed to load unicharset from file unicharset
Building unicharset from scratch...
Failed to load unicharset from file unicharset
Building unicharset from scratch...
Failed to load unicharset from file unicharset
Building unicharset from scratch...
Reading num_1.font.exp0.tr ...
Flat shape table summary: Number of shapes = 0 max unichars = 0 number with multiple unichars = 0
Warning: no protos/configs for Joined in CreateIntTemplates()
Warning: no protos/configs for |Broken|0|1 in CreateIntTemplates()
Class->NumConfigs == this->fontset_table_.at(Class->font_set_id).size():Error:Assert failed:in file ../../../src/classify/intproto.cpp, line 948
PS D:\A> cntraining num_1.font.exp0.tr
Reading num_1.font.exp0.tr ...
PS D:\A>
按照这个教程做的，运行到第七步生成出的文件没有 inttemp、pffmtable、normproto 这三个
使用jTessBoxEditorFX-2.2.0制作自己的字库_Keras深度学习的博客-CSDN博客_jtessboxeditor下载
这是我生成出来得文件
jTessBoxEditor训练字库以及字库的合并
https://blog.csdn.net/and_bjdbc/article/details/86234679
如果有其他问题，可以发出来
提供参考链接【Tesseract4.0 5.0训练字库 OCR 提高识别率必备(超详情)】，链接：https://www.cnblogs.com/interdrp/p/15423165.html
【博文细化讲解了第7步，期望能帮助到你】
看人家说这你试试
shapeclustering -F font_properties -U unicharset lang.fontname.exp0.tr lang.fontname.exp1.tr ...
