Extract individual assets from images as transparent PNGs. Zero ML models, pure classical CV. This is used in pdf2ppt online tool pxGenius.ai
-
Updated
Mar 23, 2026 - Python
Extract individual assets from images as transparent PNGs. Zero ML models, pure classical CV. This is used in pdf2ppt online tool pxGenius.ai
Classical (non-ML) facial landmark detection in C++ using OpenCV. Detects eyes and mouth on face images using four approaches, evaluated on the MTFL dataset with Normalized Mean Error (NME).
Reproducible classical computer-vision pipeline for low-light image enhancement with CLI execution and clean per-run evaluation.
Computer vision framework for multi-temporal Amazon deforestation detection using satellite imagery. Analyzes forest loss patterns, detects acceleration trends, and identifies critical periods. Features 3 detection algorithms, comprehensive testing, and validation with 20 years of real Amazon data.
Classical computer vision approach to lane detection using Canny edge detection and Hough transform
A research-grade masterclass rebuilding the entire Computer Vision stack from first principles. No OpenCV, no PyTorch—just pure math and NumPy. Implements custom convolutions, Canny edge detection, eigenvalue-based Harris corners, Lucas–Kanade optical flow, and a CNN layer with full backward passes from scratch.
Interactive image editing toolkit built with Python and OpenCV, showcasing core classical computer vision operations using real-time trackbars.
Classical machine vision system for automated geometric inspection of gear wheels. Measures 11 parameters from 2 camera views. Built as the Implement phase of a DMAIC noise reduction project for wiper motor manufacturing. Python + OpenCV. No deep learning.
Add a description, image, and links to the classical-cv topic page so that developers can more easily learn about it.
To associate your repository with the classical-cv topic, visit your repo's landing page and select "manage topics."