deeplearning

deeplearning / LargescaleImageMemorability / 0.1.3

README.md

1. Introduction


This algorithm tells you have memorable an image is to humans. The algorithm reaches a rank correlation of 0.64, near human consistency (0.68).

Input:

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

Output:

  • Image memorability

Note: The first call to this algorithm will take a bit longer than sequential calls to due algorithm initialization. All following calls will be significantly faster.

2. Examples

Example 1.

  • Parameter 1: Data API Url
{
    "image": "data://deeplearning/example_data/garden.jpeg"
}

Output

{
  "memorability": 0.6875075697898865
}

Example 2.

  • Parameter 1: HTTP Url
{
    "image": "https://s3.amazonaws.com/algorithmia-assets/algo_desc_images/deeplearning_RealEstateClassifier/beach_house.jpeg"
}

Output:

{
  "memorability": 0.5041214823722839
}

Example 3.

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

Output;

{
  "memorability": 0.3471947391028374
}

3. Credits

for more information, please refer to: http://memorability.csail.mit.edu/ or Understanding and Predicting Image Memorability at a Large Scale A. Khosla, A. S. Raju, A. Torralba and A. Oliva International Conference on Computer Vision (ICCV), 2015 DOI 10.1109/ICCV.2015.275

Demo is was taken from:

https://unsplash.com/photos/oCJuJQqvCzc