Similarity between faces: One person resembles another person to a large degree. This can lead to many problems facing security surveillance systems. Facial recognition systems have difficulty distinguishing between the main person and other people who are highly similar in terms of features.

FeatTS is a Semi-Supervised Clustering method that leverages features extracted from the raw time series to create clusters that reflect the original time series.

🔉 spafe: Simplified Python Audio Features Extraction

Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API

[CVPR] MARLIN: Masked Autoencoder for facial video Representation LearnINg

Python Open-source package for medical images processing and radiomics features extraction.

Conversion of depth data to derived images that allow classical feature detection. My master thesis.

Ce projet a pour but de réaliser une extraction de features, suivie d'une PCA sur des données volumineuses à l'aide de Spark dans le cloud.

Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.

machine learning

A Python library that allows easy extraction of a variety of text units within texts...

Analysis of public audio datasets and audio datasets of my making

This repository contains all the code developed with the aim of training a machine learning model useful for recognizing whether a fingerprint image is a spoofed or original one.

Benchmarks on various datasets for music analysis of symbolic scores

LibSA4Py: Light-weight static analysis for extracting type hints and features

FeatVIS: High dimensional feature space visualization

This sentiment analysis project extracts features such as content length, tokens, hashtags, bad words, and various emojis. It also includes word features. Preprocessing steps include removing stop words, non-Arabic characters, consecutive redundant characters, and stemming to improve the models' accuracy in classifying the tweets. Max accuracy 88%.

SURF (Speeded Up Robust Features)

Using features-matching algorithm for tracking object