Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/textord/ccnontextdetect.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 // File: ccnontextdetect.h
3 // Description: Connected-Component-based non-text detection.
4 // Copyright 2011 Google Inc. All Rights Reserved.
5 // Author: rays@google.com (Ray Smith)
6 // Created: Sat Jun 11 09:52:01 PST 2011
7 //
8 // Licensed under the Apache License, Version 2.0 (the "License");
9 // you may not use this file except in compliance with the License.
10 // You may obtain a copy of the License at
11 // http://www.apache.org/licenses/LICENSE-2.0
12 // Unless required by applicable law or agreed to in writing, software
13 // distributed under the License is distributed on an "AS IS" BASIS,
14 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 // See the License for the specific language governing permissions and
16 // limitations under the License.
17 //
18 ///////////////////////////////////////////////////////////////////////
19
20 #ifndef TESSERACT_TEXTORD_CCPHOTODETECT_H_
21 #define TESSERACT_TEXTORD_CCPHOTODETECT_H_
22
23 #include "blobgrid.h"
24 #include "scrollview.h"
25
26 namespace tesseract {
27
28 // The CCNonTextDetect class contains grid-based operations on blobs to create
29 // a full-resolution image mask analogous yet complementary to
30 // pixGenHalftoneMask as it is better at line-drawings, graphs and charts.
31 class CCNonTextDetect : public BlobGrid {
32 public:
33 CCNonTextDetect(int gridsize, const ICOORD &bleft, const ICOORD &tright);
34 ~CCNonTextDetect() override;
35
36 // Creates and returns a Pix with the same resolution as the original
37 // in which 1 (black) pixels represent likely non text (photo, line drawing)
38 // areas of the page, deleting from the blob_block the blobs that were
39 // determined to be non-text.
40 // The photo_map (binary image mask) is used to bias the decision towards
41 // non-text, rather than supplying a definite decision.
42 // The blob_block is the usual result of connected component analysis,
43 // holding the detected blobs.
44 // The returned Pix should be PixDestroyed after use.
45 Image ComputeNonTextMask(bool debug, Image photo_map, TO_BLOCK *blob_block);
46
47 private:
48 // Computes and returns the noise_density IntGrid, at the same gridsize as
49 // this by summing the number of small elements in a 3x3 neighbourhood of
50 // each grid cell. good_grid is filled with blobs that are considered most
51 // likely good text, and this is filled with small and medium blobs that are
52 // more likely non-text.
53 // The photo_map is used to bias the decision towards non-text, rather than
54 // supplying definite decision.
55 IntGrid *ComputeNoiseDensity(bool debug, Image photo_map, BlobGrid *good_grid);
56
57 // Tests each blob in the list to see if it is certain non-text using 2
58 // conditions:
59 // 1. blob overlaps a cell with high value in noise_density_ (previously set
60 // by ComputeNoiseDensity).
61 // OR 2. The blob overlaps more than max_blob_overlaps in *this grid. This
62 // condition is disabled with max_blob_overlaps == -1.
63 // If it does, the blob is declared non-text, and is used to mark up the
64 // nontext_mask. Such blobs are fully deleted, and non-noise blobs have their
65 // neighbours reset, as they may now point to deleted data.
66 // WARNING: The blobs list blobs may be in the *this grid, but they are
67 // not removed. If any deleted blobs might be in *this, then this must be
68 // Clear()ed immediately after MarkAndDeleteNonTextBlobs is called.
69 // If the win is not nullptr, deleted blobs are drawn on it in red, and kept
70 void MarkAndDeleteNonTextBlobs(BLOBNBOX_LIST *blobs, int max_blob_overlaps, ScrollView *win,
71 ScrollView::Color ok_color, Image nontext_mask);
72 // Returns true if the given blob overlaps more than max_overlaps blobs
73 // in the current grid.
74 bool BlobOverlapsTooMuch(BLOBNBOX *blob, int max_overlaps);
75
76 // Max entry in noise_density_ before the cell is declared noisy.
77 int max_noise_count_;
78 // Completed noise density map, which we keep around to use for secondary
79 // noise detection.
80 IntGrid *noise_density_;
81 };
82
83 } // namespace tesseract.
84
85 #endif // TESSERACT_TEXTORD_CCPHOTODETECT_H_