Crate is_photo

Source
Expand description

§is-photo

crates.io Documentation MIT/Apache-2 licensed

Utility to determine if an image is likely a photograph or a 2D graphic, such as a logo, illustration, or digital art.

It does this by taking various statistics from the image and running them through a pre-trained logistic regression model, along with a few sure-fire heuristics.

On my test set of around 1500 images, it has a 94% accuracy rate. Feel free to submit links to additional image sets to train on in an issue!

§Example

let img = image::open("test.jpg")?;

let analysis = is_photo::analyze(&img).expect("Failed to analyze image");

let is_photo = analysis.is_photo(&is_photo::STANDARD_MODEL);

Future work may include training on a larger dataset, and possibly using a full neural network instead of logistic regression.

Modules§

  • Logistic Regression model for classification and training

Structs§

  • Image analysis results, most of which are used as features for the regression model to classify images as photos or vectors.

Constants§

  • Pre-trained regression model with about 94% accuracy on my test set of 1500 images.

Functions§

  • Analyze an image and return the results.