tesseract
5.0.0-alpha-619-ge9db
cjkpitch.h
Go to the documentation of this file.
1
// File: cjkpitch.h
3
// Description: Code to determine fixed pitchness and the pitch if fixed,
4
// for CJK text.
5
// Copyright 2011 Google Inc. All Rights Reserved.
6
// Author: takenaka@google.com (Hiroshi Takenaka)
7
// Created: Mon Jun 27 12:48:35 JST 2011
8
//
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
//
20
#ifndef CJKPITCH_H_
21
#define CJKPITCH_H_
22
23
#include "
blobbox.h
"
24
25
// Function to test "fixed-pitchness" of the input text and estimating
26
// character pitch parameters for it, based on CJK fixed-pitch layout
27
// model.
28
//
29
// This function assumes that a fixed-pitch CJK text has following
30
// characteristics:
31
//
32
// - Most glyphs are designed to fit within the same sized square
33
// (imaginary body). Also they are aligned to the center of their
34
// imaginary bodies.
35
// - The imaginary body is always a regular rectangle.
36
// - There may be some extra space between character bodies
37
// (tracking).
38
// - There may be some extra space after punctuations.
39
// - The text is *not* space-delimited. Thus spaces are rare.
40
// - Character may consists of multiple unconnected blobs.
41
//
42
// And the function works in two passes. On pass 1, it looks for such
43
// "good" blobs that has the pitch same pitch on the both side and
44
// looks like a complete CJK character. Then estimates the character
45
// pitch for every row, based on those good blobs. If we couldn't find
46
// enough good blobs for a row, then the pitch is estimated from other
47
// rows with similar character height instead.
48
//
49
// Pass 2 is an iterative process to fit the blobs into fixed-pitch
50
// character cells. Once we have estimated the character pitch, blobs
51
// that are almost as large as the pitch can be considered to be
52
// complete characters. And once we know that some characters are
53
// complete characters, we can estimate the region occupied by its
54
// neighbors. And so on.
55
//
56
// We repeat the process until all ambiguities are resolved. Then make
57
// the final decision about fixed-pitchness of each row and compute
58
// pitch and spacing parameters.
59
//
60
// (If a row is considered to be proportional, pitch_decision for the
61
// row is set to PITCH_CORR_PROP and the later phase
62
// (i.e. Textord::to_spacing()) should determine its spacing
63
// parameters)
64
//
65
// This function doesn't provide all information required by
66
// fixed_pitch_words() and the rows need to be processed with
67
// make_prop_words() even if they are fixed pitched.
68
void
compute_fixed_pitch_cjk
(
ICOORD
page_tr,
// top right
69
TO_BLOCK_LIST *port_blocks);
// input list
70
71
#endif // CJKPITCH_H_
blobbox.h
ICOORD
integer coordinate
Definition:
points.h:30
compute_fixed_pitch_cjk
void compute_fixed_pitch_cjk(ICOORD page_tr, TO_BLOCK_LIST *port_blocks)
Definition:
cjkpitch.cpp:1040
src
textord
cjkpitch.h
Generated on Thu Jan 30 2020 14:22:21 for tesseract by
1.8.16