Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/wordrec/lm_consistency.cpp @ 2:b50eed0cc0ef upstream

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4. The directory name has changed: no version number in the expanded directory now.
author Franz Glasner <fzglas.hg@dom66.de>
date Mon, 15 Sep 2025 11:43:07 +0200
parents
children
comparison
equal deleted inserted replaced
1:1d09e1dec1d9 2:b50eed0cc0ef
1 ///////////////////////////////////////////////////////////////////////
2 // File: lm_consistency.cpp
3 // Description: Struct for recording consistency of the paths representing
4 // OCR hypotheses.
5 // Author: Rika Antonova
6 // Created: Mon Jun 20 11:26:43 PST 2012
7 //
8 // (C) Copyright 2012, Google Inc.
9 // Licensed under the Apache License, Version 2.0 (the "License");
10 // you may not use this file except in compliance with the License.
11 // You may obtain a copy of the License at
12 // http://www.apache.org/licenses/LICENSE-2.0
13 // Unless required by applicable law or agreed to in writing, software
14 // distributed under the License is distributed on an "AS IS" BASIS,
15 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 // See the License for the specific language governing permissions and
17 // limitations under the License.
18 //
19 ////////////////////////////////////////////////////////////////////////
20
21 #include "lm_consistency.h"
22
23 #include "associate.h"
24 #include "dict.h"
25 #include "ratngs.h"
26
27 namespace tesseract {
28
29 void LMConsistencyInfo::ComputeXheightConsistency(const BLOB_CHOICE *b, bool is_punc) {
30 if (xht_decision == XH_INCONSISTENT) {
31 return; // It isn't going to get any better.
32 }
33
34 // Compute xheight consistency.
35 bool parent_null = xht_sp < 0;
36 int parent_sp = xht_sp;
37 // Debug strings.
38 if (b->yshift() > LMConsistencyInfo::kShiftThresh) {
39 xht_sp = LMConsistencyInfo::kSUP;
40 } else if (b->yshift() < -LMConsistencyInfo::kShiftThresh) {
41 xht_sp = LMConsistencyInfo::kSUB;
42 } else {
43 xht_sp = LMConsistencyInfo::kNORM;
44 }
45 xht_count[xht_sp]++;
46 if (is_punc) {
47 xht_count_punc[xht_sp]++;
48 }
49 if (!parent_null) {
50 xpos_entropy += abs(parent_sp - xht_sp);
51 }
52 // TODO(eger): Figure out a better way to account for small caps.
53 // For the first character not y-shifted, we only care if it is too small.
54 // Too large is common in drop caps and small caps.
55 // int16_t small_xht = b->min_xheight();
56 // if (parent_vse == nullptr && sp == LanguageModelConsistencyInfo::kNORM) {
57 // small_xht = 0;
58 // }
59 IntersectRange(b->min_xheight(), b->max_xheight(), &(xht_lo[xht_sp]), &(xht_hi[xht_sp]));
60
61 // Compute xheight inconsistency kinds.
62 if (parent_null) {
63 if (xht_count[kNORM] == 1) {
64 xht_decision = XH_GOOD;
65 } else {
66 xht_decision = XH_SUBNORMAL;
67 }
68 return;
69 }
70
71 // When we intersect the ranges of xheights in pixels for all characters in
72 // each position (subscript, normal, superscript),
73 // How much range must be left? 0? [exactly one pixel height for xheight] 1?
74 // TODO(eger): Extend this code to take a prior for the rest of the line.
75 const int kMinIntersectedXHeightRange = 0;
76 for (int i = 0; i < kNumPos; i++) {
77 if (xht_lo[i] > xht_hi[i] - kMinIntersectedXHeightRange) {
78 xht_decision = XH_INCONSISTENT;
79 return;
80 }
81 }
82
83 // Reject as improbable anything where there's much punctuation in subscript
84 // or superscript regions.
85 if (xht_count_punc[kSUB] > xht_count[kSUB] * 0.4 ||
86 xht_count_punc[kSUP] > xht_count[kSUP] * 0.4) {
87 xht_decision = XH_INCONSISTENT;
88 return;
89 }
90
91 // Now check that the subscript and superscript aren't too small relative to
92 // the mainline.
93 auto mainline_xht = static_cast<double>(xht_lo[kNORM]);
94 double kMinSizeRatio = 0.4;
95 if (mainline_xht > 0.0 && (static_cast<double>(xht_hi[kSUB]) / mainline_xht < kMinSizeRatio ||
96 static_cast<double>(xht_hi[kSUP]) / mainline_xht < kMinSizeRatio)) {
97 xht_decision = XH_INCONSISTENT;
98 return;
99 }
100 // TODO(eger): Check into inconsistency of super/subscript y offsets.
101 if (xpos_entropy > kMaxEntropy) {
102 xht_decision = XH_INCONSISTENT;
103 return;
104 }
105 if (xht_count[kSUB] == 0 && xht_count[kSUP] == 0) {
106 xht_decision = XH_GOOD;
107 return;
108 }
109 xht_decision = XH_SUBNORMAL;
110 }
111
112 } // namespace tesseract