opencv

opencv / PerspectiveTransform / 0.2.2

README.md

1. Introduction

Transform pictures of rectangular documents to horizontally align with the x axis. For the photos that are taken at an angle, this algorithm adjusts the viewing angle so that the writings are perpendicular to the horizontal axis. The letters are not slanted and straight. This algorithm is very useful for OCR, performs well on receipts, business cards, printed documents.

Input:

  • (Required): Image Data API Url, Web (http/https) Url, binary image or a base64 encoded image.
  • (Optional): Output image location.

Output:

  • Output image location.

2. Examples

Example 1.

  • Parameter 1: Data API Url
{
  "image": "data://opencv/cards/sample_card.jpg"
}

Output

{
  "output": "data://.algo/temp/sample_card.png"
}

Example 2.

  • Parameter 1: HTTP Url
{
  "image": "https://s3.amazonaws.com/algorithmia-assets/algo_desc_images/opencv_PerspectiveTransform/sample_card.jpg"
}

Output:

{
  "output": "data://.algo/temp/sample_card.png"
}

Example 3.

  • Parameter 1: Base64 Image
{
  "image": "data:image/png;base64...."
}

Output:

{
  "output": "data://.algo/temp/output.png"
}

Example 4.

  • Parameter 1: HTTP Url
  • Parameter 2: Output file save location.
{
  "image": "https://s3.amazonaws.com/algorithmia-assets/algo_desc_images/opencv_PerspectiveTransform/sample_card.jpg",
  "location": "data://.algo/temp/test.png"
}

Output:

{
  "output": "data://.algo/temp/test.png"
}

3. Credits

For more information please refer to: http://opencv.org/