PST or Phase Stretch Transform is an operator that finds features in an image. PST implemented using MATLAB here, takes an intensity image I as its input, and returns a binary image out of the same size as I, with 1's where the function finds sharp transitions in I and 0's elsewhere.

PyTextureAnalysis is a Python package for analyzing the texture of images. It includes functions for calculating local orientation, degree of coherence, and structure tensor of an image. This package is built using NumPy, SciPy and OpenCV.

Texture Analysis test tool for PET images

This repository includes all Basic Algorithms related to image Processing, these are almost without Build-in Functions

Course Project for the course CS 736

Repo for generating a SVM model using a GLCM, Haralick features

Calculate 43 texture features of a 2D or 3D image

Repo for PyPi package

Radiomics Signatures of Cardiovascular Risk Factors in Cardiac MRI: Results From the UK Biobank

A hybrid-feature melanoma detection pipeline combining advanced image preprocessing, handcrafted features, and multiple machine learning classifiers. Designed to deliver accurate and efficient skin cancer recognition.

Library for diffraction specific calculations and for analyzing residual stresses and pole figure plots for P61A beamline at PETRAIII, DESY.

Make your potato GPU render nice graphics using smart resolution reduction

CerviScan is a machine learning project for early detection of cervical pre-cancer using color moments and texture features extracted from post-VIA colposcopy images. This research evaluates multiple color spaces, feature fusion strategies, and traditional ML classifiers such as XGBoost and AdaBoost to improve diagnostic performance.

Real-time face liveness detection using Python, OpenCV, and MediaPipe. Detects blinks, smiles, head depth, and texture (LBP & Laplacian) to classify faces as real or spoof. Ideal for basic anti-spoofing using webcam input.

Foreco project which include efforts to define and analyse relationships between Forest structure and forest disturbance like Bark Beetle, storm and drought dynamics.

Gram-GAN bridges pixel-based and GAN SR methods, generating sharp and realistic textures by explicitly matching generated patches to real HR textures via a Gram-based patch database. It ensures stable training, better generalization, and texture-aware outputs—ideal for satellite, medical, art, and fashion super-resolution tasks.