Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/classify/ocrfeatures.h @ 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 ** Filename: features.h
3 ** Purpose: Generic definition of a feature.
4 ** Author: Dan Johnson
5 **
6 ** (c) Copyright Hewlett-Packard Company, 1988.
7 ** Licensed under the Apache License, Version 2.0 (the "License");
8 ** you may not use this file except in compliance with the License.
9 ** You may obtain a copy of the License at
10 ** http://www.apache.org/licenses/LICENSE-2.0
11 ** Unless required by applicable law or agreed to in writing, software
12 ** distributed under the License is distributed on an "AS IS" BASIS,
13 ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 ** See the License for the specific language governing permissions and
15 ** limitations under the License.
16 ******************************************************************************/
17
18 #ifndef FEATURES_H
19 #define FEATURES_H
20
21 #include "blobs.h"
22
23 #include <cstdio>
24 #include <string> // for std::string
25
26 namespace tesseract {
27
28 class DENORM;
29
30 #undef Min
31 #undef Max
32 #define FEAT_NAME_SIZE 80
33
34 // A character is described by multiple sets of extracted features. Each
35 // set contains a number of features of a particular type, for example, a
36 // set of bays, or a set of closures, or a set of microfeatures. Each
37 // feature consists of a number of parameters. All features within a
38 // feature set contain the same number of parameters. All circular
39 // parameters are required to be the first parameters in the feature.
40
41 struct PARAM_DESC {
42 bool Circular; // true if dimension wraps around
43 bool NonEssential; // true if dimension not used in searches
44 float Min; // low end of range for circular dimensions
45 float Max; // high end of range for circular dimensions
46 float Range; // Max - Min
47 float HalfRange; // (Max - Min)/2
48 float MidRange; // (Max + Min)/2
49 };
50
51 struct FEATURE_DESC_STRUCT {
52 uint16_t NumParams; // total # of params
53 const char *ShortName; // short name for feature
54 const PARAM_DESC *ParamDesc; // array - one per param
55 };
56 using FEATURE_DESC = FEATURE_DESC_STRUCT *;
57
58 struct FEATURE_STRUCT {
59 /// Constructor for a new feature of the specified type.
60 /// @param FeatureDesc description of feature to be created.
61 FEATURE_STRUCT(const FEATURE_DESC_STRUCT *FeatureDesc) : Type(FeatureDesc), Params(FeatureDesc->NumParams) {
62 }
63 ~FEATURE_STRUCT() {
64 }
65 const FEATURE_DESC_STRUCT *Type; // points to description of feature type
66 std::vector<float> Params; // variable size array - params for feature
67 };
68 using FEATURE = FEATURE_STRUCT *;
69
70 struct FEATURE_SET_STRUCT {
71 /// Creator for a new feature set large enough to
72 /// hold the specified number of features.
73 /// @param NumFeatures maximum # of features to be put in feature set
74 FEATURE_SET_STRUCT(int numFeatures) : NumFeatures(0), MaxNumFeatures(numFeatures), Features(numFeatures) {
75 }
76
77 ~FEATURE_SET_STRUCT() {
78 for (uint16_t i = 0; i < NumFeatures; i++) {
79 delete Features[i];
80 }
81 }
82
83 uint16_t NumFeatures; // number of features in set
84 uint16_t MaxNumFeatures; // maximum size of feature set
85 std::vector<FEATURE_STRUCT *> Features; // variable size array of features
86 };
87 using FEATURE_SET = FEATURE_SET_STRUCT *;
88
89 // A generic character description as a char pointer. In reality, it will be
90 // a pointer to some data structure. Paired feature extractors/matchers need
91 // to agree on the data structure to be used, however, the high level
92 // classifier does not need to know the details of this data structure.
93 using CHAR_FEATURES = char *;
94
95 /*----------------------------------------------------------------------
96 Macros for defining the parameters of a new features
97 ----------------------------------------------------------------------*/
98 #define StartParamDesc(Name) const PARAM_DESC Name[] = {
99 #define DefineParam(Circular, NonEssential, Min, Max) \
100 {Circular, \
101 NonEssential, \
102 Min, \
103 Max, \
104 (Max) - (Min), \
105 (((Max) - (Min)) / 2.0), \
106 (((Max) + (Min)) / 2.0)},
107
108 #define EndParamDesc \
109 } \
110 ;
111
112 /*----------------------------------------------------------------------
113 Macro for describing a new feature. The parameters of the macro
114 are as follows:
115
116 DefineFeature (Name, NumLinear, NumCircular, ShortName, ParamName)
117 ----------------------------------------------------------------------*/
118 #define DefineFeature(Name, NL, NC, SN, PN) \
119 const FEATURE_DESC_STRUCT Name = {((NL) + (NC)), SN, PN};
120
121 /*----------------------------------------------------------------------
122 Generic routines that work for all feature types
123 ----------------------------------------------------------------------*/
124 bool AddFeature(FEATURE_SET FeatureSet, FEATURE Feature);
125
126 FEATURE_SET ReadFeatureSet(FILE *File, const FEATURE_DESC_STRUCT *FeatureDesc);
127
128 void WriteFeatureSet(FEATURE_SET FeatureSet, std::string &str);
129
130 } // namespace tesseract
131
132 #endif