Hi everyone,

I recently released imgfprint, a Rust crate for generating deterministic image fingerprints and computing similarity between images.

The goal of the crate is to provide a small SDK for image deduplication and similarity detection, without bundling indexing or database components.

GitHub

Crate
https://crates.io/crates/imgfprint

Features

• perceptual hashing for visual similarity detection
• exact hashing for byte-level identity checks
• optional semantic embeddings (CLIP)
• deterministic fingerprints suitable for large-scale pipelines

Example

use imgfprint::ImageFingerprinter;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let img1 = std::fs::read("photo1.jpg")?;
    let img2 = std::fs::read("photo2.jpg")?;

    let fp1 = ImageFingerprinter::fingerprint(&img1)?;
    let fp2 = ImageFingerprinter::fingerprint(&img2)?;

    let sim = ImageFingerprinter::compare(&fp1, &fp2);

    println!("Similarity: {:.2}", sim.score);
    println!("Exact match: {}", sim.exact_match);

    if sim.score > 0.8 {
        println!("Images are perceptually similar");
    }

    Ok(())
}

The library is intended for applications like dataset deduplication, media similarity search, and preprocessing pipelines.

Feedback and suggestions are welcome.

1 post - 1 participant

Read full topic