diff --git a/tesseract/Dockerfile b/tesseract/Dockerfile index ae50743..5ff4071 100644 --- a/tesseract/Dockerfile +++ b/tesseract/Dockerfile @@ -16,4 +16,4 @@ RUN set -xe \ && tesseract --list-langs ENTRYPOINT ["tesseract"] -CMD ["--help"] +CMD ["--help-extra"] diff --git a/tesseract/README.md b/tesseract/README.md index f0c4a35..25c84fa 100644 --- a/tesseract/README.md +++ b/tesseract/README.md @@ -15,8 +15,14 @@ Quick Start ``` $ alias tesseract='docker run --rm -v `pwd`:/data -w /data vimagick/tesseract' + $ tesseract input.png output -l eng --psm 3 $ cat output.txt +The (quick) [brown] {fox} jumps! + +$ tesseract chinese.jpg chinese -l chi_tra --psm 8 --oem 0 +$ cat chinese.txt +學習 ``` [1]: https://github.com/tesseract-ocr/tesseract diff --git a/tesseract/data/chinese.jpg b/tesseract/data/chinese.jpg new file mode 100644 index 0000000..8fa5484 Binary files /dev/null and b/tesseract/data/chinese.jpg differ diff --git a/tesseract/data/input.png b/tesseract/data/input.png new file mode 100644 index 0000000..91f0c18 Binary files /dev/null and b/tesseract/data/input.png differ diff --git a/tesseract/docker-compose.yml b/tesseract/docker-compose.yml new file mode 100644 index 0000000..e2799b0 --- /dev/null +++ b/tesseract/docker-compose.yml @@ -0,0 +1,6 @@ +tesseract: + image: vimagick/tesseract + command: tesseract input.png output -l eng --psm 3 + volumes: + - ./data:/data + working_dir: /data