1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
|
// (C) Copyright 2017, Google Inc.
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
#include <allheaders.h>
#include <tesseract/baseapi.h>
#include <filesystem>
#include <string>
#include "helpers.h"
#include "include_gunit.h"
#include "image.h"
#include "log.h"
namespace tesseract {
// The fixture for testing Tesseract.
class PageSegModeTest : public testing::Test {
protected:
PageSegModeTest() = default;
~PageSegModeTest() override {
src_pix_.destroy();
}
void SetUp() override {
static std::locale system_locale("");
std::locale::global(system_locale);
}
void SetImage(const char *filename) {
src_pix_.destroy();
src_pix_ = pixRead(filename);
api_.Init(TESSDATA_DIR, "eng", tesseract::OEM_TESSERACT_ONLY);
api_.SetImage(src_pix_);
}
// Tests that the given rectangle produces exactly the given text in the
// given segmentation mode (after chopping off the last 2 newlines.)
void VerifyRectText(tesseract::PageSegMode mode, const char *str, int left, int top, int width,
int height) {
api_.SetPageSegMode(mode);
api_.SetRectangle(left, top, width, height);
char *result = api_.GetUTF8Text();
chomp_string(result);
chomp_string(result);
EXPECT_STREQ(str, result);
delete[] result;
}
// Tests that the given rectangle does NOT produce the given text in the
// given segmentation mode.
void NotRectText(tesseract::PageSegMode mode, const char *str, int left, int top, int width,
int height) {
api_.SetPageSegMode(mode);
api_.SetRectangle(left, top, width, height);
char *result = api_.GetUTF8Text();
EXPECT_STRNE(str, result);
delete[] result;
}
Image src_pix_ = nullptr;
std::string ocr_text_;
tesseract::TessBaseAPI api_;
};
// Tests the single-word segmentation mode, and that it performs correctly
// and differently to line and block mode.
TEST_F(PageSegModeTest, WordTest) {
std::string filename = file::JoinPath(TESTING_DIR, "segmodeimg.tif");
if (!std::filesystem::exists(filename)) {
LOG(INFO) << "Skip test because of missing " << filename << '\n';
GTEST_SKIP();
} else {
SetImage(filename.c_str());
// Test various rectangles around the inverse page number.
VerifyRectText(tesseract::PSM_SINGLE_WORD, "183", 1419, 264, 69, 34);
VerifyRectText(tesseract::PSM_SINGLE_WORD, "183", 1411, 252, 78, 62);
VerifyRectText(tesseract::PSM_SINGLE_WORD, "183", 1396, 218, 114, 102);
// Test a random pair of words as a line
VerifyRectText(tesseract::PSM_SINGLE_LINE, "What should", 237, 393, 256, 36);
#ifdef DISABLED_LEGACY_ENGINE
// Skip check as LSTM mode adds a space.
LOG(INFO) << "Skip `Whatshould` test in LSTM Mode\n";
#else
// Test a random pair of words as a word
VerifyRectText(tesseract::PSM_SINGLE_WORD, "Whatshould", 237, 393, 256, 36);
#endif
// Test single block mode.
VerifyRectText(tesseract::PSM_SINGLE_BLOCK, "both the\nfrom the", 237, 450, 172, 94);
// But doesn't work in line or word mode.
NotRectText(tesseract::PSM_SINGLE_LINE, "both the\nfrom the", 237, 450, 172, 94);
NotRectText(tesseract::PSM_SINGLE_WORD, "both the\nfrom the", 237, 450, 172, 94);
}
}
} // namespace tesseract
|
