A perceptual hash is a fingerprint of a multimedia file derived from various features from its content. Unlike cryptographic hash functions which rely on the avalanche effect of small changes in input leading to drastic changes in the output, perceptual hashes are "close" to one another if the features are similar.

Image Similarity search build on Milvus

This repository is part of a blog post that guides users through creating a visual search application using Amazon SageMaker and Amazon Elasticsearch service

Repo for the final project of "Numerical Methods for Algorithmic Systems and NeuralNetworks"

Find similar images in dataset for a new image using Resnet50+KNN. In order to solve curse of dimensionality using PCA to reduce the dimensionality of features.

This project uses a Siamese Neural Network with shared weights to compare image pairs. It’s trained with a contrastive loss function to learn feature embeddings that bring similar images closer and push dissimilar ones apart.

Image Similarity System with Deep Autoencoders

A Python package to detect and extract the changed parts & coordinates of those parts from the images if any.

Implemented an image search feature on the website to improve the experience of 35% of customers dissatisfied with keyword searches. This enhancement incorporated the CNN model with 95% accuracy for image classification and the Siamese model for the top 5 similar products, leveraging the data set of 24,000+ images across 10 different classes.