mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-24 02:59:07 +08:00
fix issue 755; add example config files from tesseract manpage
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@894 d0cd1f9f-072b-0410-8dd7-cf729c803f20
This commit is contained in:
parent
fdb1669cda
commit
53a3e0f88a
@ -94,7 +94,7 @@ FLOAT32 Classify::ComputeNormMatch(CLASS_ID ClassId,
|
|||||||
PROTOTYPE *Proto;
|
PROTOTYPE *Proto;
|
||||||
int ProtoId;
|
int ProtoId;
|
||||||
|
|
||||||
if (ClassId > NormProtos->NumProtos) {
|
if (ClassId >= NormProtos->NumProtos) {
|
||||||
ClassId = NO_CLASS;
|
ClassId = NO_CLASS;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -68,7 +68,7 @@ class Trie : public Dawg {
|
|||||||
};
|
};
|
||||||
|
|
||||||
// Minimum number of concrete characters at the beginning of user patterns.
|
// Minimum number of concrete characters at the beginning of user patterns.
|
||||||
static const int kSaneNumConcreteChars = 4;
|
static const int kSaneNumConcreteChars = 0;
|
||||||
// Various unicode whitespace characters are used to denote unichar patterns,
|
// Various unicode whitespace characters are used to denote unichar patterns,
|
||||||
// (character classifier would never produce these whitespace characters as a
|
// (character classifier would never produce these whitespace characters as a
|
||||||
// valid classification).
|
// valid classification).
|
||||||
|
4
tessdata/configs/bazaar
Normal file
4
tessdata/configs/bazaar
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
load_system_dawg F
|
||||||
|
load_freq_dawg F
|
||||||
|
user_words_suffix user-words
|
||||||
|
user_patterns_suffix user-patterns
|
2
tessdata/eng.user-patterns
Normal file
2
tessdata/eng.user-patterns
Normal file
@ -0,0 +1,2 @@
|
|||||||
|
1-\d\d\d-GOOG-411
|
||||||
|
www.\n\\\*.com
|
5
tessdata/eng.user-words
Normal file
5
tessdata/eng.user-words
Normal file
@ -0,0 +1,5 @@
|
|||||||
|
the
|
||||||
|
quick
|
||||||
|
brown
|
||||||
|
fox
|
||||||
|
jumped
|
Loading…
Reference in New Issue
Block a user