'프로그램 사용' 카테고리의 글 목록 (16 Page)

'프로그램 사용'에 해당되는 글 2290건

2023.12.27 tesseract 학습 데이터
2023.12.26 tesseract on arm
2023.12.21 ROS rviz
2023.12.21 tesseract ocr
2023.12.20 nnstreamer
2023.12.06 gst-device-monitor-1.0
2023.10.24 minicom에서 stty로 터미널 폭 조절하기
2023.10.20 BGE / UPBGE(Blender game engine)
2023.10.11 libreoffice hwp 확장
2023.09.21 fft 결과에 N(입력 샘플 갯수)로 나누는 이유

tesseract 학습 데이터

strace로 추적해보니 신기한(?) 파일 발견

eng는 그냥 data인데

osd.traineddata는 Matlab v4 mat-file로 나온다. 맞나.. 우연인가?

$ ls -alh /usr/share/tesseract-ocr/4.00/tessdata
합계 15M
drwxr-xr-x 4 root root 4.0K 12월 21 10:48 .
drwxr-xr-x 3 root root 4.0K  5월 30  2023 ..
drwxr-xr-x 2 root root 4.0K  5월 30  2023 configs
-rw-r--r-- 1 root root 4.0M  9월 16  2017 eng.traineddata
-rw-r--r-- 1 root root  11M  9월 16  2017 osd.traineddata
-rw-r--r-- 1 root root  572  2월  9  2022 pdf.ttf
drwxr-xr-x 2 root root 4.0K  5월 30  2023 tessconfigs

$ file *.traineddata
eng.traineddata: data
osd.traineddata: Matlab v4 mat-file (little endian) , text, rows 4294967295, columns 4294967295, imaginary

$ tree /usr/share/tesseract-ocr/4.00/tessdata
.
├── configs
│   ├── alto
│   ├── ambigs.train
│   ├── api_config
│   ├── bigram
│   ├── box.train
│   ├── box.train.stderr
│   ├── digits
│   ├── get.images
│   ├── hocr
│   ├── inter
│   ├── kannada
│   ├── linebox
│   ├── logfile
│   ├── lstm.train
│   ├── lstmbox
│   ├── lstmdebug
│   ├── makebox
│   ├── pdf
│   ├── quiet
│   ├── rebox
│   ├── strokewidth
│   ├── tsv
│   ├── txt
│   ├── unlv
│   └── wordstrbox
├── eng.traineddata
├── osd.traineddata
├── pdf.ttf
└── tessconfigs
    ├── batch
    ├── batch.nochop
    ├── matdemo
    ├── msdemo
    ├── nobatch
    └── segdemo

2 directories, 34 files

kor 은 15메가

[링크 : https://github.com/tesseract-ocr/tessdata]

+

실행하니 당연히(?) tesseract용 데이터가 없다고 오류가 발생한다.

혹시나 해서 변수는 확인해도 비어있고

pc에서 복사해서 설정해주니 ok

~/tesseract-main/build/bin# ./tesseract /home/root/a.png -
Error in pixReadMemTiff: function not present
Error in pixReadMem: tiff: no pix returned
Error in pixaGenerateFontFromString: pix not made
Error in bmfCreate: font pixa not made
Error opening data file ./eng.traineddata
Please make sure the TESSDATA_PREFIX environment variable is set to your "tessdata" directory.
Failed loading language 'eng'
Tesseract couldn't load any languages!
Could not initialize tesseract.
root@imx8mpevk:~/tesseract-main/build/bin# echo $TESSDATA_PREFIX

# export TESSDATA_PREFIX=/home/root/tessdata

아래 이미지를 인식시킴(pc는 dpi가 이상하다고 인식을 못함)

의외로 잘 인식한다.

그런데 pc 에서는 인식을 이상하게 했지만 0.2초

i.mx8 에서는 인식을 잘했지만 1.6초. 흐음.. 실시간으로 돌리기에는 무리군..

# time ./tesseract /home/root/a.png -
Error in pixReadMemTiff: function not present
Error in pixReadMem: tiff: no pix returned
Error in pixaGenerateFontFromString: pix not made
Error in bmfCreate: font pixa not made
Estimating resolution as 132
Warning:guessing pitch as xheight on row 1, block 1
1.MX8MP Evaluation Kit

.MxeMP 1.50 GHz

2020-06-07 2848 MB RAM

> Console Options wait, 65535 means
Select Language <Standard English> Reset

> Device Manager
> Boot Manager
> Boot Maintenance Manager

Continue
Reset

ay=Move Highlight <Enter>=Select Entry

real 0m1.646s
user 0m1.578s
sys 0m0.060s

저작자표시

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

tesseract 버전별 차이? (0)	2023.12.27
tesseract on arm (0)	2023.12.26
tesseract ocr (0)	2023.12.21
번호판 인식(tesseract) (0)	2021.10.14

Posted by 구차니

tesseract on arm

빌드 하려고 해도 빡세다

tesseact 빌드 하려니 leptonica라는게 필요하다고 에러나고

# cmake ..
-- Configuring tesseract version 5.3.3...
-- IPO / LTO not supported: <Change Dir: /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin

Run Build Command(s):/usr/bin/make -f Makefile && /usr/bin/cmake -S/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/src -B/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin --check-build-system CMakeFiles/Makefile.cmake 0
/usr/bin/cmake -E cmake_progress_start /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin/CMakeFiles /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin//CMakeFiles/progress.marks
/usr/bin/make  -f CMakeFiles/Makefile2 all
make[1]: Entering directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
/usr/bin/make  -f CMakeFiles/foo.dir/build.make CMakeFiles/foo.dir/depend
make[2]: Entering directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
cd /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin && /usr/bin/cmake -E cmake_depends "Unix Makefiles" /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/src /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/src /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin/CMakeFiles/foo.dir/DependInfo.cmake
make[2]: Leaving directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
/usr/bin/make  -f CMakeFiles/foo.dir/build.make CMakeFiles/foo.dir/build
make[2]: Entering directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
[ 25%] Building CXX object CMakeFiles/foo.dir/foo.cpp.o
/usr/bin/c++   -flto=auto -fno-fat-lto-objects -o CMakeFiles/foo.dir/foo.cpp.o -c /home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/src/foo.cpp
[ 50%] Linking CXX static library libfoo.a
/usr/bin/cmake -P CMakeFiles/foo.dir/cmake_clean_target.cmake
/usr/bin/cmake -E cmake_link_script CMakeFiles/foo.dir/link.txt --verbose=1
"CMAKE_CXX_COMPILER_AR-NOTFOUND" cr libfoo.a CMakeFiles/foo.dir/foo.cpp.o
Error running link command: No such file or directory
make[2]: *** [CMakeFiles/foo.dir/build.make:100: libfoo.a] Error 2
make[2]: Leaving directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
make[1]: *** [CMakeFiles/Makefile2:88: CMakeFiles/foo.dir/all] Error 2
make[1]: Leaving directory '/home/root/tesseract-main/build/CMakeFiles/_CMakeLTOTest-CXX/bin'
make: *** [Makefile:94: all] Error 2

>
-- CMAKE_SYSTEM_PROCESSOR=<aarch64>
-- LTO build is not supported on arm/RBPi.
-- Could NOT find Leptonica (missing: Leptonica_DIR)
-- Checking for module 'lept>=1.74'
--   No package 'lept' found
CMake Error at CMakeLists.txt:404 (message):
  Cannot find required library Leptonica.  Quitting!

-- Configuring incomplete, errors occurred!
See also "/home/root/tesseract-main/build/CMakeFiles/CMakeOutput.log".
See also "/home/root/tesseract-main/build/CMakeFiles/CMakeError.log".

[링크 : https://github.com/tesseract-ocr/tesseract]

leptonica 라는거 빌드하려니 이젠 openjp2가 없다고 -_-

# cmake ..
-- Could NOT find GIF (missing: GIF_LIBRARY GIF_INCLUDE_DIR) (Required is at least version "5")
-- Could NOT find TIFF (missing: TIFF_LIBRARY TIFF_INCLUDE_DIR)
-- Could NOT find WebP (missing: WebP_DIR)
-- WebP_INCLUDE_DIR : WebP_INCLUDE_DIR-NOTFOUND
WebP_MUX_INCLUDE_DIR: WebP_MUX_INCLUDE_DIR-NOTFOUND
WebP_LIBRARY: WebP_LIBRARY-NOTFOUND
WebP_MUX_LIBRARY: WebP_MUX_LIBRARY-NOTFOUND
CMake Error at /usr/lib/openjpeg-2.5/OpenJPEGTargets.cmake:95 (message):
  The imported target "openjp2_static" references the file

     "/usr/lib/libopenjp2.a"

  but this file does not exist.  Possible reasons include:

  * The file was deleted, renamed, or moved to another location.

  * An install or uninstall procedure did not complete successfully.

  * The installation package was faulty and contained

     "/usr/lib/openjpeg-2.5/OpenJPEGTargets.cmake"

  but not all the files it references.

Call Stack (most recent call first):
  /usr/lib/openjpeg-2.5/OpenJPEGConfig.cmake:28 (include)
  CMakeLists.txt:186 (find_package)

-- Configuring incomplete, errors occurred!
See also "/home/root/leptonica-master/build/CMakeFiles/CMakeOutput.log".

귀찮으니(!) 걍 주석으로 막고 인자가 3개인 녀석으로 강제 빌드!

//#if OPJ_VERSION_MINOR == 0
//    opj_stream_set_user_data(l_stream, fp);
//#else
    opj_stream_set_user_data(l_stream, fp,
                             (opj_stream_free_user_data_fn)NULL);
//#endif

[링크 : https://github.com/danbloomberg/leptonica]

[링크 : http://www.leptonica.org/]

openjpeg는 별다른 에러없이 빌드 완료

[링크 : https://github.com/uclouvain/openjpeg]

leptonica 에서

src/jp2kio.c 에서 아래의 부분에서 MINOR가 0으로 되면서 구버전(?) 소스를 호출하는지 함수의 형태가 달라서 에러난다.

/home/root/leptonica-master/src/jp2kio.c: In function 'opjCreateStream':
/home/root/leptonica-master/src/jp2kio.c:938:5: error: too few arguments to function 'opj_stream_set_user_data'
938 | opj_stream_set_user_data(l_stream, fp);
| ^~~~~~~~~~~~~~~~~~~~~~~~

tesseract 다시 하려니 pangocairo 패키지가 없다고 에러.. 젠장.. 이거 이전에 weston 할때

개고생(?) 시키던 이름이 악몽으로 떠오르는데?

-- No package 'pangocairo' found

meson 깔고

# pip3 install meson
Collecting meson
Downloading meson-1.3.0-py3-none-any.whl (976 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 976.4/976.4 kB 3.5 MB/s eta 0:00:00
Installing collected packages: meson
Successfully installed meson-1.3.0

pango 빌드 하려는데 git 필요하대서 git 깔고

WARNING: CMake Toolchain: Failed to determine CMake compilers state
Run-time dependency fribidi found: NO (tried pkgconfig and cmake)
Looking for a fallback subproject for the dependency fribidi

../meson.build:218:14: ERROR: Git program not found, cannot download fribidi.wrap via git.

아래 링크에서 받아서 빌드..

$ wget https://www.kernel.org/pub/software/scm/git/git-2.43.0.tar.gz

pango 다시 빌드하는데 ninja 없으면 배쨈! 시전하고

$ mkdir build
$ cd build
$ meson ..
ERROR: Could not detect Ninja v1.8.2 or newer

ninja 빌드하고 설치하려는데 또 백태클 -_-

그러니 cmake를 멀리하고

12%] Building CXX object CMakeFiles/libninja.dir/src/dyndep_parser.cc.o
In file included from /home/root/ninja-master/build/_deps/googletest-src/googletest/src/gtest-all.cc:42:
/home/root/ninja-master/build/_deps/googletest-src/googletest/src/gtest-death-test.cc: In function 'bool testing::internal::StackGrowsDown()':
/home/root/ninja-master/build/_deps/googletest-src/googletest/src/gtest-death-test.cc:1301:24: error: 'dummy' may be used uninitialized [-Werror=maybe-uninitialized]
1301 | StackLowerThanAddress(&dummy, &result);
| ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~

파이썬으로 빌드하는게 낫....

# python3 configure.py --bootstrap

[링크 : https://github.com/ninja-build/ninja]

다시 pango으로 돌아와서

$ meson ..
Found ninja-1.12.0.git at /usr/bin/ninja
WARNING: Running the setup command as `meson [options]` instead of `meson setup [options]` is ambiguous and deprecated.

build 안에서 ninja 치니 알아서 빌드. + 설치

~/pango-main/build# ninja
~/pango-main/build# ninja install

pango도 했는데 tesseract 다시 빌드 하려니 안된다 -_-

그냥 설치하는게 아니라 패키지로 만들어서 했어야 했나?

-- Checking for modules 'pango>=1.38.0;cairo;pangoft2;pangocairo;fontconfig'
--   No package 'pango' found
--   No package 'pangoft2' found
--   No package 'pangocairo' found

귀찮으니(!) cmake에서 패키지 확인하지 않도록 수정

~/tesseract-main/build# vi ../src/training/CMakeLists.txt
  if(PKG_CONFIG_FOUND OR SW_BUILD)

    if(PKG_CONFIG_FOUND)
      pkg_check_modules(
        PANGO
        REQUIRED
        IMPORTED_TARGET
#        pango>=1.38.0
#        cairo
#        pangoft2
#        pangocairo
        fontconfig)
    endif()

[ 95%] Building CXX object src/training/CMakeFiles/pango_training.dir/pango/ligature_table.cpp.o
In file included from /home/root/tesseract-main/src/training/pango/ligature_table.cpp:24:
/home/root/tesseract-main/src/training/pango/pango_font_info.h:27:10: fatal error: pango/pango-font.h: No such file or directory
   27 | #include "pango/pango-font.h"
      |          ^~~~~~~~~~~~~~~~~~~~

[ 96%] Building CXX object src/training/CMakeFiles/pango_training.dir/pango/tlog.cpp.o
In file included from /home/root/tesseract-main/src/training/pango/stringrenderer.cpp:20:
/home/root/tesseract-main/src/training/pango/stringrenderer.h:33:10: fatal error: pango/pango-layout.h: No such file or directory
   33 | #include "pango/pango-layout.h"
      |          ^~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:118: src/training/CMakeFiles/pango_training.dir/pango/stringrenderer.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
In file included from /home/root/tesseract-main/src/training/pango/ligature_table.cpp:24:
/home/root/tesseract-main/src/training/pango/pango_font_info.h:27:10: fatal error: pango/pango-font.h: No such file or directory
   27 | #include <pango/pango-font.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:90: src/training/CMakeFiles/pango_training.dir/pango/ligature_table.cpp.o] Error 1
In file included from /home/root/tesseract-main/src/training/pango/pango_font_info.cpp:32:
/home/root/tesseract-main/src/training/pango/pango_font_info.h:27:10: fatal error: pango/pango-font.h: No such file or directory
   27 | #include <pango/pango-font.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.

아마 패키지에서 배째는거 같은데 수작업으로 변경.. -_-

#include "pango/pango-font.h"
#include "pango/pango.h"
#include "pango/pangocairo.h"

#include <pango/pango-font.h>
#include <pango/pango.h>
#include <pango/pangocairo.h>

밑도 끝도 없네 -_-

[ 96%] Building CXX object src/training/CMakeFiles/pango_training.dir/pango/pango_font_info.cpp.o
In file included from /usr/local/include/pango/pango-font.h:25,
                 from /usr/local/include/pango/pango-attributes.h:25,
                 from /usr/local/include/pango/pango-layout.h:25,
                 from /home/root/tesseract-main/src/training/pango/stringrenderer.h:33,
                 from /home/root/tesseract-main/src/training/pango/stringrenderer.cpp:20:
/usr/local/include/pango/pango-coverage.h:25:10: fatal error: glib-object.h: No such file or directory
   25 | #include <glib-object.h>
      |          ^~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:118: src/training/CMakeFiles/pango_training.dir/pango/stringrenderer.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
In file included from /usr/local/include/pango/pango-font.h:25,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.h:27,
                 from /home/root/tesseract-main/src/training/pango/ligature_table.cpp:24:
/usr/local/include/pango/pango-coverage.h:25:10: fatal error: glib-object.h: No such file or directory
   25 | #include <glib-object.h>
      |          ^~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:90: src/training/CMakeFiles/pango_training.dir/pango/ligature_table.cpp.o] Error 1
In file included from /usr/local/include/pango/pango-font.h:25,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.h:27,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.cpp:32:
/usr/local/include/pango/pango-coverage.h:25:10: fatal error: glib-object.h: No such file or directory
   25 | #include <glib-object.h>
      |          ^~~~~~~~~~~~~~~
compilation terminated.

[ 96%] Building CXX object src/training/CMakeFiles/pango_training.dir/pango/stringrenderer.cpp.o
In file included from /usr/local/include/pango/pango-coverage.h:25,
                 from /usr/local/include/pango/pango-font.h:25,
                 from /usr/local/include/pango/pango-attributes.h:25,
                 from /usr/local/include/pango/pango-layout.h:25,
                 from /home/root/tesseract-main/src/training/pango/stringrenderer.h:33,
                 from /home/root/tesseract-main/src/training/pango/stringrenderer.cpp:20:
/usr/include/glib-2.0/glib-object.h:24:10: fatal error: gobject/gbinding.h: No such file or directory
   24 | #include <gobject/gbinding.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:118: src/training/CMakeFiles/pango_training.dir/pango/stringrenderer.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
In file included from /usr/local/include/pango/pango-coverage.h:25,
                 from /usr/local/include/pango/pango-font.h:25,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.h:27,
                 from /home/root/tesseract-main/src/training/pango/ligature_table.cpp:24:
/usr/include/glib-2.0/glib-object.h:24:10: fatal error: gobject/gbinding.h: No such file or directory
   24 | #include <gobject/gbinding.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.
make[2]: *** [src/training/CMakeFiles/pango_training.dir/build.make:90: src/training/CMakeFiles/pango_training.dir/pango/ligature_table.cpp.o] Error 1
In file included from /usr/local/include/pango/pango-coverage.h:25,
                 from /usr/local/include/pango/pango-font.h:25,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.h:27,
                 from /home/root/tesseract-main/src/training/pango/pango_font_info.cpp:32:
/usr/include/glib-2.0/glib-object.h:24:10: fatal error: gobject/gbinding.h: No such file or directory
   24 | #include <gobject/gbinding.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.

inclue path를 찾는데 Makefile에 없어서 뒤져보니.. 저게 맞길..

# grep -rn "\-I" .
./CMakeFiles/libtesseract.dir/flags.make:7:CXX_INCLUDES = -I/home/root/tesseract-main/include -I/home/root/tesseract-main/src/arch -I/home/root/tesseract-main/src/ccmain -I/home/root/tesseract-main/src/ccstruct -I/home/root/tesseract-main/src/ccutil -I/home/root/tesseract-main/src/classify -I/home/root/tesseract-main/src/cutil -I/home/root/tesseract-main/src/dict -I/home/root/tesseract-main/src/lstm -I/home/root/tesseract-main/src/opencl -I/home/root/tesseract-main/src/textord -I/home/root/tesseract-main/src/viewer -I/home/root/tesseract-main/src/wordrec -I/home/root/tesseract-main/src/training -I/home/root/tesseract-main/src -I/usr/local/include/leptonica -I/home/root/tesseract-main/build -I/home/root/tesseract-main/build/include
./CMakeFiles/tesseract.dir/flags.make:7:CXX_INCLUDES = -I/usr/local/include/leptonica -I/home/root/tesseract-main/build -I/home/root/tesseract-main/build/include -I/home/root/tesseract-main/include -I/home/root/tesseract-main/src/arch -I/home/root/tesseract-main/src/ccmain -I/home/root/tesseract-main/src/ccstruct -I/home/root/tesseract-main/src/ccutil -I/home/root/tesseract-main/src/classify -I/home/root/tesseract-main/src/cutil -I/home/root/tesseract-main/src/dict -I/home/root/tesseract-main/src/lstm -I/home/root/tesseract-main/src/opencl -I/home/root/tesseract-main/src/textord -I/home/root/tesseract-main/src/viewer -I/home/root/tesseract-main/src/wordrec -I/home/root/tesseract-main/src/training

저작자표시

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

tesseract 버전별 차이? (0)	2023.12.27
tesseract 학습 데이터 (0)	2023.12.27
tesseract ocr (0)	2023.12.21
번호판 인식(tesseract) (0)	2021.10.14

Posted by 구차니

ROS rviz

로봇 암 시뮬레이션해볼 수 있다고 해서 찾아보는 중

[링크 : https://pinkwink.kr/903]

[링크 : https://docs.elephantrobotics.com/docs/mycobot-pi-en/2-serialproduct/2.1-280/2.1.5.4-DevelopmentEnvironmentAndConstruction.html]

저작자표시

Posted by 구차니

tesseract ocr

오픈소스 OCR로 우분투에 패키지로 설치가 가능하고

gimagereader 라는 frontend도 있으니 참고를..

[링크 : https://sourceforge.net/projects/gimagereader/]

간단한 사용법은 아래와 같이 파일명 - -l eng 해주면 되는데, 아마 -를 넣어서 stdout으로 출력하라는걸지도?

$ tesseract images/eurotext.png - -l eng

[링크 : https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html]

psm은 어떤식으로 읽을지 모드를 설정해주는데 OSD(Orientation and Script Detection) 이라는게

있냐 없냐로, 2문자 까지 인식하게 할 순 있다(--psm 1)

+

psm 10으로 하면 단문자도 인식하게 설정이 가능하다

$ tesseract --help-extra
Usage:
  tesseract --help | --help-extra | --help-psm | --help-oem | --version
  tesseract --list-langs [--tessdata-dir PATH]
  tesseract --print-parameters [options...] [configfile...]
  tesseract imagename|imagelist|stdin outputbase|stdout [options...] [configfile...]

OCR options:
  --tessdata-dir PATH   Specify the location of tessdata path.
  --user-words PATH     Specify the location of user words file.
  --user-patterns PATH  Specify the location of user patterns file.
  --dpi VALUE           Specify DPI for input image.
  -l LANG[+LANG]        Specify language(s) used for OCR.
  -c VAR=VALUE          Set value for config variables.
                        Multiple -c arguments are allowed.
  --psm NUM             Specify page segmentation mode.
  --oem NUM             Specify OCR Engine mode.
NOTE: These options must occur before any configfile.

Page segmentation modes:
  0    Orientation and script detection (OSD) only.
  1    Automatic page segmentation with OSD.
  2    Automatic page segmentation, but no OSD, or OCR. (not implemented)
  3    Fully automatic page segmentation, but no OSD. (Default)
  4    Assume a single column of text of variable sizes.
  5    Assume a single uniform block of vertically aligned text.
  6    Assume a single uniform block of text.
  7    Treat the image as a single text line.
  8    Treat the image as a single word.
  9    Treat the image as a single word in a circle.
10    Treat the image as a single character.
11    Sparse text. Find as much text as possible in no particular order.
12    Sparse text with OSD.
13    Raw line. Treat the image as a single text line,
       bypassing hacks that are Tesseract-specific.

OCR Engine modes: (see https://github.com/tesseract-ocr/tesseract/wiki#linux)
  0    Legacy engine only.
  1    Neural nets LSTM engine only.
  2    Legacy + LSTM engines.
  3    Default, based on what is available.

Single options:
  -h, --help            Show minimal help message.
  --help-extra          Show extra help for advanced users.
  --help-psm            Show page segmentation modes.
  --help-oem            Show OCR Engine modes.
  -v, --version         Show version information.
  --list-langs          List available languages for tesseract engine.
  --print-parameters    Print tesseract parameters.

[링크 : https://kokokorin-bigbox.tistory.com/53]

테스트 해보니 1 문자는 어떻게 하든 안되는 것 같은데 회피가 가능하려나?

$ tesseract a5.png - --psm 3
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 406
ak

$ tesseract a5.png - --psm 2
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 406
Orientation: 0
WritingDirection: 0
TextlineOrder: 2
Deskew angle: 0.0000

$ tesseract a5.png - --psm 1
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 406
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 2 blob text block, but using orientation anyway: 0
ak

$ tesseract a5.png - --psm 0
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 406
Too few characters. Skipping this page
Warning. Invalid resolution 0 dpi. Using 70 instead.
Too few characters. Skipping this page
Error during processing.

$ tesseract a6.png - --psm 0
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 294
Too few characters. Skipping this page
Warning. Invalid resolution 0 dpi. Using 70 instead.
Too few characters. Skipping this page
Error during processing.

$ tesseract a6.png - --psm 1
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 294
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 1 blob text block, but using orientation anyway: 0
Empty page!!
Estimating resolution as 294
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 1 blob text block, but using orientation anyway: 0
Empty page!!

$ tesseract a6.png - --psm 2
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 294
Empty page!!

$ tesseract a6.png - --psm 3
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 294
Empty page!!
Estimating resolution as 294
Empty page!!

저작자표시

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

tesseract 버전별 차이? (0)	2023.12.27
tesseract 학습 데이터 (0)	2023.12.27
tesseract on arm (0)	2023.12.26
번호판 인식(tesseract) (0)	2021.10.14

Posted by 구차니

nnstreamer

Neural Network gstreamer인가?

NNStreamer provides a set of GStreamer plugins so developers may apply neural networks, attach related frameworks (including ROS, IIO, FlatBuffers, and Protocol Buffers), and manipulate tensor data streams in GStreamer pipelines easily and execute such pipelines efficiently

[링크 : https://nnstreamer.ai/#get-started]

저작자표시

'프로그램 사용 > gstreamer' 카테고리의 다른 글

gstreamer parse_launch (0)	2024.01.11
gst-device-monitor-1.0 (0)	2023.12.06
gstremaer videobox + videomixer (0)	2023.04.10
gst-inspector.c (0)	2023.04.06
gstreamer videomixer 반쪽 성공 (0)	2023.03.27

Posted by 구차니

gst-device-monitor-1.0

v4l2src 관련해서 기존에 웹캠에서 지원하는 모드들 찾는다고 고생했는데 간단한 유틸리티를 알게 됨 -_-

$ man gst-device-monitor-1.0
SYNOPSIS
gst-device-monitor-1.0 [DEVICE_CLASSES[:FILTER_CAPS]] [DEVICE_CLASSES[:FILTER_CAPS]]

$ gst-device-monitor-1.0 Video/Source
Probing devices...

Device found:

name  : 720p HD Camera
class : Video/Source
caps  : image/jpeg, width=1280, height=720, framerate=30/1
        image/jpeg, width=640, height=480, framerate=30/1
        image/jpeg, width=640, height=360, framerate=30/1
        image/jpeg, width=352, height=288, framerate=30/1
        image/jpeg, width=320, height=240, framerate=30/1
        image/jpeg, width=160, height=120, framerate=30/1
        video/x-raw, format=YUY2, width=1280, height=720, framerate=10/1
        video/x-raw, format=YUY2, width=640, height=480, framerate=30/1
        video/x-raw, format=YUY2, width=640, height=360, framerate=30/1
        video/x-raw, format=YUY2, width=352, height=288, framerate=30/1
        video/x-raw, format=YUY2, width=320, height=240, framerate=30/1
        video/x-raw, format=YUY2, width=160, height=120, framerate=30/1
properties:
object.path = v4l2:/dev/video0
device.api = v4l2
media.class = Video/Source
device.product.id = 308
device.vendor.id = 11134
api.v4l2.path = /dev/video0
api.v4l2.cap.driver = uvcvideo
api.v4l2.cap.card = "720p\ HD\ Camera:\ 720p\ HD\ Camera"
api.v4l2.cap.bus_info = usb-0000:00:14.0-6
api.v4l2.cap.version = 6.2.16
api.v4l2.cap.capabilities = 84a00001
api.v4l2.cap.device-caps = 04200001
device.id = 33
node.name = v4l2_input.pci-0000_00_14.0-usb-0_6_1.0
node.description = "720p\ HD\ Camera"
factory.name = api.v4l2.source
node.pause-on-idle = false
factory.id = 10
client.id = 32
clock.quantum-limit = 8192
media.role = Camera
node.driver = true
object.id = 35
object.serial = 35
gst-launch-1.0 pipewiresrc path=35 ! ...

저작자표시

'프로그램 사용 > gstreamer' 카테고리의 다른 글

gstreamer parse_launch (0)	2024.01.11
nnstreamer (0)	2023.12.20
gstremaer videobox + videomixer (0)	2023.04.10
gst-inspector.c (0)	2023.04.06
gstreamer videomixer 반쪽 성공 (0)	2023.03.27

Posted by 구차니

minicom에서 stty로 터미널 폭 조절하기

minicom으로 통신을 하는데(시리얼)

창을 넓혀도 top 등을 실행할때 창의 폭이 넓어지지 않을때

아래의 명령을 넣어주면 폭이 조절된다.

$ stty columns 150

[링크 : https://acet.pe.kr/17]

posix 표준은 아니지만 columns N 하면 된다.

# stty --help
Usage: stty [-F DEVICE | --file=DEVICE] [SETTING]...
  or:  stty [-F DEVICE | --file=DEVICE] [-a|--all]
  or:  stty [-F DEVICE | --file=DEVICE] [-g|--save]
Print or change terminal characteristics.

Mandatory arguments to long options are mandatory for short options too.
  -a, --all          print all current settings in human-readable form
  -g, --save         print all current settings in a stty-readable form
  -F, --file=DEVICE  open and use the specified DEVICE instead of stdin
      --help     이 도움말을 표시하고 끝냅니다
      --version  버전 정보를 출력하고 끝냅니다

Optional - before SETTING indicates negation.  An * marks non-POSIX
settings.  The underlying system defines which settings are available.

Special characters:
* discard CHAR  CHAR will toggle discarding of output
   eof CHAR      CHAR will send an end of file (terminate the input)
   eol CHAR      CHAR will end the line
* eol2 CHAR     alternate CHAR for ending the line
   erase CHAR    CHAR will erase the last character typed
   intr CHAR     CHAR will send an interrupt signal
   kill CHAR     CHAR will erase the current line
* lnext CHAR    CHAR will enter the next character quoted
   quit CHAR     CHAR will send a quit signal
* rprnt CHAR    CHAR will redraw the current line
   start CHAR    CHAR will restart the output after stopping it
   stop CHAR     CHAR will stop the output
   susp CHAR     CHAR will send a terminal stop signal
* swtch CHAR    CHAR will switch to a different shell layer
* werase CHAR   CHAR will erase the last word typed

Special settings:
   N             set the input and output speeds to N bauds
* cols N        tell the kernel that the terminal has N columns
* columns N     same as cols N
* [-]drain      wait for transmission before applying settings (on by default)
   ispeed N      set the input speed to N
* line N        use line discipline N
   min N         with -icanon, set N characters minimum for a completed read
   ospeed N      set the output speed to N
* rows N        tell the kernel that the terminal has N rows
* size          print the number of rows and columns according to the kernel
   speed         print the terminal speed
   time N        with -icanon, set read timeout of N tenths of a second

저작자표시

'프로그램 사용 > minicom' 카테고리의 다른 글

minicom color (0)	2024.11.06
minicom lf에 cr 붙이기 (0)	2023.01.05
minicom 16진수로 보기 (0)	2022.08.25
minicom 로그 저장하기 (0)	2021.09.16
minicom timestamp (0)	2021.09.16

Posted by 구차니

BGE / UPBGE(Blender game engine)

2.8에서는 삭제되어 2.79 까지만 남아있는 듯. 현재 3.x대로 이행되었으니 흔적도 없이 사라졌을 것 같다.

Following its removal from the official version of Blender, an unofficial fork of the game engine source code was created, named UPBGE.[4] This was done with the aim of maintaining and modernizing the engine. Since then, UPBGE has been updated with support for Blender's new realtime renderer, Eevee, and runs on top of Blender 3.0 source code.[5]

[링크 : https://en.wikipedia.org/wiki/Blender_Game_Engine]

[링크 : https://upbge.org/#/]

망할(!) GPL 때문에 없어질 수 밖에 없었을 듯.

그래서 unity가 신명나게 욕 먹고 대안으로 떠오르는게 BGE가 아니라 godot 게임엔진이 뜨는 듯

내장된 'Game engine save as runtime' 애드온을 사용하면 Windows용으로 빌드할 수 있다.

애드온으로 실행 파일을 만든 때에 GPL 라이선스에 따라 소스 코드를 무조건 까야 한다. BGE 라이센스 참고(영문). 요약하자면, 소프트웨어 및 소스 코드는 GNU GPL에 결합되어 있지만, 블렌더 파일(모델, 텍스처, 소리)은 그렇지 않다.

게임을 구성하는 파이썬 스크립트의 경우 개발자의 지적 재산은 맞지만 내부 에드온으로 빌드하면 GPL 소스 코드와 섞이기 때문에 그 권리가 모호해지는 문제가 있다. 즉, 빌드된 게임 프로그램이 GPL이 되어 버린다.

[링크 : https://namu.wiki/w/BGE]

The Godot Engine is a free, all-in-one, cross-platform game engine that makes it easy for you to create 2D and 3D games.

[링크 : https://godotengine.org/]

저작자표시

'프로그램 사용 > Blender' 카테고리의 다른 글

blender cad (0)	2024.05.07
blender render node (0)	2024.03.20
blender on macos (0)	2022.05.24
big bunny blender project file (0)	2022.05.22
블렌더 강좌? (유료) (0)	2021.08.07

Posted by 구차니

libreoffice hwp 확장

한동안 신경끄고 살았는데

hwpx라는 사악한(!) 확장자도 추가되었다는걸 새삼 알게됨 -_-

[링크 : https://extensions.libreoffice.org/en/extensions/show/27504]

+

23.10.24

다운받아서 설치하니 java 11 없다고 배짼다. 깔아야 하나 -_-

openjsdk-11 으로는 안되니 패스~

$ sudo apt-get install openjdk-11-jdk

[링크 : https://codechacha.com/ko/ubuntu-install-open-jdk11/]

libreoffice-java-common 이라는 패키지로 별도의 java가 제공된다고.. 뭥미

$ sudo apt install libreoffice-java-common

[링크 : https://forums.zotero.org/discussion/97427/issue-with-libre-office-plugin-on-ubuntu-22-04]

저작자표시

'프로그램 사용 > openoffice' 카테고리의 다른 글

libreoffice calc 빈 열 삭제하기 (0)	2024.08.02
libreoffice에서 italic으로 자동 변환 막기 (0)	2024.02.13
libreoffice calc 중복제거 (0)	2023.08.05
libreoffice OpenCL 적용하기 (0)	2023.08.04
리브레 오피스 Calc 중복제거 (0)	2020.11.05

Posted by 구차니

fft 결과에 N(입력 샘플 갯수)로 나누는 이유

실험적으로 나온 결과를 N으로 나눠줘서 쓰고 있었는데

퍼시발의 규칙에 의해 개별 주파수의 진폭은 N개의 샘플에 의해 영향을 받게되고

진폭을 N으로 나누어 평준화해야 한다고 하는데 솔찍히 확 와닫는 소리는 아니다 -_ㅠ

[링크 : https://stackoverflow.com/questions/63211851/why-divide-the-output-of-numpy-fft-by-n]

[링크 : https://stackoverflow.com/questions/4855958/normalising-fft-data-fftw]

+

2024.08.01

[링크 : https://dsp.stackexchange.com/questions/75749/how-to-use-pffft-fft-library]

저작자표시

'프로그램 사용 > fft, fftw' 카테고리의 다른 글

pffft fft / ifft 테스트 (0)	2024.08.01
FFT RBW (0)	2023.09.19
tek.com fft 관련 문서 (0)	2023.07.19
sfft (0)	2023.07.12
fft window type과 진폭 보정계수 (0)	2023.07.04

Posted by 구차니

구차니의 잡동사니 모음

'프로그램 사용'에 해당되는 글 2290건

tesseract 학습 데이터

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

tesseract on arm

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

ROS rviz

tesseract ocr

'프로그램 사용 > tesseract ocr' 카테고리의 다른 글

nnstreamer

'프로그램 사용 > gstreamer' 카테고리의 다른 글

gst-device-monitor-1.0

'프로그램 사용 > gstreamer' 카테고리의 다른 글

minicom에서 stty로 터미널 폭 조절하기

'프로그램 사용 > minicom' 카테고리의 다른 글

BGE / UPBGE(Blender game engine)

'프로그램 사용 > Blender' 카테고리의 다른 글

libreoffice hwp 확장

'프로그램 사용 > openoffice' 카테고리의 다른 글

fft 결과에 N(입력 샘플 갯수)로 나누는 이유

'프로그램 사용 > fft, fftw' 카테고리의 다른 글

카테고리

공지사항

태그목록

최근에 올라온 글

최근에 달린 댓글

티스토리툴바