Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/training/common/intfeaturedist.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 // Copyright 2011 Google Inc. All Rights Reserved.
2 // Author: rays@google.com (Ray Smith)
3 ///////////////////////////////////////////////////////////////////////
4 // File: intfeaturedist.h
5 // Description: Fast set-difference-based feature distance calculator.
6 //
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
19 #ifndef TESSERACT_CLASSIFY_INTFEATUREDIST_H_
20 #define TESSERACT_CLASSIFY_INTFEATUREDIST_H_
21
22 #include <vector>
23
24 namespace tesseract {
25
26 class IntFeatureMap;
27
28 // Feature distance calculator designed to provide a fast distance calculation
29 // based on set difference between a given feature set and many other feature
30 // sets in turn.
31 // Representation of a feature set as an array of bools that are sparsely
32 // true, and companion arrays that allow fast feature set distance
33 // calculations with allowance of offsets in position.
34 // Init is expensive, so for greatest efficiency, to re-initialize for a new
35 // feature set, use Set(..., false) on the SAME feature set as was used to
36 // setup with Set(..., true), to return to its initialized state before
37 // reuse with Set(..., true) on a new feature set.
38 class IntFeatureDist {
39 public:
40 IntFeatureDist();
41 ~IntFeatureDist();
42
43 // Initialize the bool array to the given size of feature space.
44 // The feature_map is just borrowed, and must exist for the entire
45 // lifetime of the IntFeatureDist.
46 void Init(const IntFeatureMap *feature_map);
47
48 // Setup the map for the given indexed_features that have been indexed by
49 // feature_map. After use, use Set(..., false) to reset to the initial state
50 // as this is faster than calling Init for sparse spaces.
51 void Set(const std::vector<int> &indexed_features, int canonical_count, bool value);
52
53 // Compute the distance between the given feature vector and the last
54 // Set feature vector.
55 double FeatureDistance(const std::vector<int> &features) const;
56 double DebugFeatureDistance(const std::vector<int> &features) const;
57
58 private:
59 // Clear all data.
60 void Clear();
61
62 // Size of the indexed feature space.
63 int size_;
64 // Total weight of features currently stored in the maps.
65 double total_feature_weight_;
66 // Pointer to IntFeatureMap given at Init to find offset features.
67 const IntFeatureMap *feature_map_;
68 // Array of bools indicating presence of a feature.
69 bool *features_;
70 // Array indicating the presence of a feature offset by one unit.
71 bool *features_delta_one_;
72 // Array indicating the presence of a feature offset by two units.
73 bool *features_delta_two_;
74 };
75
76 } // namespace tesseract
77
78 #endif // TESSERACT_CLASSIFY_INTFEATUREDIST_H_