recognizer

• Pre-built binaries
• Building
• Testing
  • Usage
  • Examples

This application is a reference implementation for developers to show how to use the Java API and could be used to easily check the accuracy. The Java API is a wrapper around the C++ API defined at https://www.doubango.org/SDKs/micr/docs/cpp-api.html.

The application accepts path to a JPEG/PNG/BMP file as input. This is not the recommended way to use the API. We recommend reading the data directly from the camera and feeding the SDK with the uncompressed YUV data without saving it to a file or converting it to RGB.

If you don't want to build this sample and is looking for a quick way to check the accuracy then, try our cloud-based solution at https://www.doubango.org/webapps/micr/.

This sample is open source and doesn't require registration or license key.

Pre-built binaries

If you don't want to build this sample by yourself then, use the pre-built C++ versions:

• Windows: recognizer.exe under binaries/windows/x86_64
• Linux: recognizer under binaries/linux/x86_64. Built on Ubuntu 18. You'll need to download libtensorflow.so as explained here
• Raspberry Pi: recognizer under binaries/raspbian/armv7l
• Android: check android folder
• iOS: check ios folder

On Windows, the easiest way to try this sample is to navigate to binaries/windows/x86_64 and run binaries/windows/x86_64/recognizer.bat. You can edit these files to use your own images and configuration options.

Building

This sample contains a single Java source file.

You have to navigate to the current folder (ultimateMICR-SDK/samples/java/recognizer ) before trying the next commands:

cd ultimateMICR-SDK/samples/java/recognizer

Here is how to build the file using javac:

javac @sources.txt -d .

Usage

Recognizer is a command line application with the following usage:

Recognizer \
      --image <path-to-image-with-micr-to-process> \
      [--assets <path-to-assets-folder>] \
      [--format <format-for-dtection:e13b/cmc7/e13b+cmc7>] \
      [--tokenfile <path-to-license-token-file>] \
      [--tokendata <base64-license-token-data>]

Options surrounded with [] are optional.

• --image Path to the image(JPEG/PNG/BMP) to process. You can use default image at ../../../assets/images/e13b_1280x720.jpg.
• --assets Path to the assets folder containing the configuration files and models. Default value is the current folder.
• --format Defines the MICR format to enable for the detection. Use e13b to look for E-13B lines only and cmc7 for CMC-7 lines only. To look for both, use e13b+cmc7. For performance reasons you should not use e13b+cmc7 unless you really expect the document to contain both E-13B and CMC7 lines. Default: e13b+cmc7.
• --tokenfile Path to the file containing the base64 license token if you have one. If not provided then, the application will act like a trial version. Default: null.
• --tokendata Base64 license token if you have one. If not provided then, the application will act like a trial version. Default: null.

Examples

You'll need to build the sample as explained above.

You have to navigate to the current folder (ultimateMICR-SDK/samples/java/recognizer ) before trying the next commands:

cd ultimateMICR-SDK/samples/java/recognizer

• For example, on Raspberry Pi you may call the recognizer application using the following command:

LD_LIBRARY_PATH=../../../binaries/raspbian/armv7l:$LD_LIBRARY_PATH \
java Recognizer --image ../../../assets/images/e13b_1280x720.jpg --format e13b --assets ../../../assets

• On Linux x86_64, you may use the next command:

LD_LIBRARY_PATH=../../../binaries/linux/x86_64:$LD_LIBRARY_PATH \
java Recognizer --image ../../../assets/images/e13b_1280x720.jpg --format e13b --assets ../../../assets

Before trying to run the program you'll need to download libtensorflow.so as explained here

• On Windows x86_64, you may use the next command:

setlocal
set PATH=%PATH%;../../../binaries/windows/x86_64
java Recognizer --image ../../../assets/images/e13b_1280x720.jpg --format e13b --assets ../../../assets
endlocal

Please note that if you're cross compiling the application then you've to make sure to copy the application and both the assets and binaries folders to the target device.