Image to Text Scanner – Quick Start Guide

A quick start guide in order to help you to familiar with Image to Text Scanner mobile application from NewAI.

Get it on Google Play
Get it on Google Play

Outline

  1. Android Version
  2. iOS Version

I. Android Version

Note application language will depend on the current system language.

  1. To switch between screens just dragging from the left edge of the phone, the menu will appear.

    • The Gallery screen shows the captured images in your phone, in case of need to take a new photo press the camera button at the bottom right corner. In order to refresh the list just pull it down, the photo grid will automatically updates the photos you just took. Click on the image to switch to image preview screen.
    • The PDF Browser screen displays all PDF files that are in your device, click on a file to inform the the application to execute the extract processing.
    Menu
    Figure 1a: Menu

    Gallery screen
    Figure 1b: Gallery screen

    PDF Browser screen
    Figure 1c: PDF Browser screen

  2. On the photo preview screen, you can zoom-in and out to see more detailed images. To go to previous or next photo, just drag the screen to the left or right.

    Touch the screen lightly to hide the function buttons, touching again to show. The buttons function as follows:

    • The return button at the top left corner helps you go back to the Gallery screen.
    • The submit button at the bottom right corner to handle text extraction from the image.
    Photo preview screen
    Figure 2: Photo preview screen
  3. For the first time, the application will ask for an email address to receive the results. On the Settings screen there are the following items:

    • Email address: User email address to receive OCR results.
    • OCR Language: The language will be extracted from the text on the photo. Vietnamese is the default language.
    • Output Format: Our application supports format HTML (most optimized), Microsoft Word and Microsoft Excel formats. HTML is the default format.
    • Original Format: Formatting such as indent, end-line will stay the same. HTML is currently the only format that supports this functionality; by default this functionality is disabled as it is in the development, user can enable it to try out this feature. Note that since the phone browser is not supported as a computer, the original format only work on computer web browser.
    Settings screen
    Figure 3: Settings screen
  4. After the necessary information is set up in the Settings, the photo will be posted to the server to extract the content. The result will be returned via user email address.

    OCR result
    Figure 4: OCR result

II. iOS Version

Note on iOS application language is Vietnamese.

  1. To switch between screens just dragging from the left edge of the phone, the menu will appear.

    • The Gallery screen shows the captured images in your phone, in case of need to take a new photo press the camera button at the bottom right corner. In order to refresh the list just pull it down, the photo grid will automatically updates the photos you just took. Click on the image to switch to image preview screen.
    • The iOS version will not have a PDF Browser screen, as the operating system does not yet support file access.
    Menu
    Figure 1a: Menu

    Gallery screen
    Figure 1b: Gallery screen

  2. On the photo preview screen, touch the screen lightly to hide the function buttons, touching again to show. The buttons function as follows:

    • The return button at the top left corner helps you go back to the Gallery screen.
    • The submit button at the bottom right corner to handle text extraction from the image.
    Photo preview screen
    Figure 2: Photo preview screen
  3. For the first time, the application will ask for an email address to receive the results, default output format is HTML. On the Settings screen there are the following items:

    • Email address: User email address to receive OCR results.
    • OCR Language: The language will be extracted from the text on the photo. Vietnamese is the default language.
    Settings screen
    Figure 3: Settings screen
  4. After the necessary information is set up in the Settings, the photo will be posted to the server to extract the content. The result will be returned via user email address.

    OCR result
    Figure 4: OCR result