Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/classify/blobclass.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 ** Filename: blobclass.c
3 ** Purpose: High level blob classification and training routines.
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 #include <cstdio>
19
20 #include "classify.h"
21 #include "featdefs.h"
22 #include "mf.h"
23 #include "normfeat.h"
24
25 namespace tesseract {
26
27 /*---------------------------------------------------------------------------*/
28
29 // Extracts features from the given blob and saves them in the tr_file_data_
30 // member variable.
31 // fontname: Name of font that this blob was printed in.
32 // cn_denorm: Character normalization transformation to apply to the blob.
33 // fx_info: Character normalization parameters computed with cn_denorm.
34 // blob_text: Ground truth text for the blob.
35 void Classify::LearnBlob(const std::string &fontname, TBLOB *blob, const DENORM &cn_denorm,
36 const INT_FX_RESULT_STRUCT &fx_info, const char *blob_text) {
37 std::unique_ptr<CHAR_DESC_STRUCT> CharDesc(new CHAR_DESC_STRUCT(feature_defs_));
38 CharDesc->FeatureSets[0] = ExtractMicros(blob, cn_denorm);
39 CharDesc->FeatureSets[1] = ExtractCharNormFeatures(fx_info);
40 CharDesc->FeatureSets[2] = ExtractIntCNFeatures(*blob, fx_info);
41 CharDesc->FeatureSets[3] = ExtractIntGeoFeatures(*blob, fx_info);
42
43 if (ValidCharDescription(feature_defs_, CharDesc.get())) {
44 // Label the features with a class name and font name.
45 tr_file_data_ += "\n";
46 tr_file_data_ += fontname;
47 tr_file_data_ += " ";
48 tr_file_data_ += blob_text;
49 tr_file_data_ += "\n";
50
51 // write micro-features to file and clean up
52 WriteCharDescription(feature_defs_, CharDesc.get(), tr_file_data_);
53 } else {
54 tprintf("Blob learned was invalid!\n");
55 }
56 } // LearnBlob
57
58 // Writes stored training data to a .tr file based on the given filename.
59 // Returns false on error.
60 bool Classify::WriteTRFile(const char *filename) {
61 bool result = false;
62 std::string tr_filename = filename;
63 tr_filename += ".tr";
64 FILE *fp = fopen(tr_filename.c_str(), "wb");
65 if (fp) {
66 result = tesseract::Serialize(fp, &tr_file_data_[0], tr_file_data_.length());
67 fclose(fp);
68 }
69 tr_file_data_.resize(0);
70 return result;
71 }
72
73 } // namespace tesseract