Skip to content

Add support for Tesseract 4 #80

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Geoffrey-A wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Add support for Tesseract 4 #80

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
71a4338
Add support for Tesseract 4: invert images and compile as C++11
Geoffrey-A Jun 20, 2020
6d450d9
Address feedback by @ruediger on PR #75
Geoffrey-A Jun 20, 2020
3aee5bb
Remove unused CMAKE_C_FLAGS
Geoffrey-A Jun 21, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,13 +53,10 @@ include(CheckCXXCompilerFlag)
include(CheckCXXSourceCompiles)
include(CheckCXXSourceRuns)

set(CMAKE_C_FLAGS "-std=gnu99")
set(CMAKE_CXX_FLAGS "-ansi -pedantic -Wall -Wextra -Wno-long-long")
set(CMAKE_CXX_FLAGS "-ansi -pedantic -Wall -Wextra -Wno-long-long -std=gnu++11 -DINVERT_IMAGES")

set(CMAKE_CXX_FLAGS_RELEASE "-O3 -mtune=native -march=native -DNDEBUG -fomit-frame-pointer -ffast-math") # TODO -Ofast GCC 4.6
set(CMAKE_C_FLAGS_RELEASE ${CMAKE_CXX_FLAGS_RELEASE})
set(CMAKE_CXX_FLAGS_DEBUG "-g3 -DDEBUG")
set(CMAKE_C_FLAGS_DEBUG ${CMAKE_CXX_FLAGS_DEBUG})
# TODO RelWithDebInfo MinSizeRel? maybe move -march=native -ffast-math etc. to a different build type

find_package(Threads)
Expand Down
25 changes: 25 additions & 0 deletions src/vobsub2srt.c++
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,19 @@ using namespace tesseract;
#define TESSERACT_DATA_PATH TESSERACT_DEFAULT_PATH
#endif

struct ImageInverter {
ImageInverter(const unsigned char* image, size_t image_size)
: inverted_image(new unsigned char[image_size])
{
for (size_t i = 0; i < image_size; ++i) {
inverted_image[i] = 255 - image[i];
}
}
~ImageInverter() { delete[] inverted_image; }

unsigned char* inverted_image;
};

int main(int argc, char **argv) {
bool dump_images = false;
bool verb = false;
Expand Down Expand Up @@ -265,6 +278,18 @@ int main(int argc, char **argv) {
<< start_pts << ")\n";
}

// While tesseract version 3.05 (and older) handle inverted image (dark
// background and light text) without problem, for 4.x version use dark
// text on light background.
// https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality#inverting-images

#ifdef INVERT_IMAGES

ImageInverter inverter(image, width*height);
image = inverter.inverted_image;

#endif // INVERT_IMAGES

if(dump_images) {
dump_pgm(subname, sub_counter, width, height, stride, image, image_size);
}
Expand Down