An experimental webGPU glyph compositor demonstration in Futhark

An interpretable region-based pattern mining system that incrementally maps LHS feature space to RHS distributions via grid partitioning, clustering, and boundary co-optimization.

Semantic Boundary Detection

This is a MATLAB demo to elaborate the idea of boundary tracing objects in image using directional gradients

A hands-on playground for Pattern Recognition — exploring edges, boundaries, and dimensions with Python. From Canny curves to PCA plots, this repo turns theory into experiments you can see.

Python API & command-line tool to easily transcribe speech-based video files into clean text

Extract boundary of 2D grids

A C-based algorithmic tool that renders a hollow triangular pattern by calculating boundary coordinates and managing dynamic internal void spacing.

image segmentation workflow for Phenome Force 2021

Boundary detection using Probability of Boundary || Implementation and analysis of deep learning architectures such as ResNet, DenseNet, etc.

Official implementation of Dense Prediction with Attentive Feature Aggregation, WACV 2023

Projects developed as a part of Computer Vision and Image Processing

This project involves developing a simplified boundary detection algorithm that combines texture, brightness, and color gradients with classical edge detection methods like Sobel and Canny. The final boundary map is generated by fusing these feature gradients with traditional edge detection methods for more robust and accurate edge detection.

Boundary detection for self-driving cars using U-Net

PyTorch boundary detection

This Repository consists of implementation of probability based boundary detection algorithm which gives more accurate results than canny edge detection.

A fast, unsupervised video segmentation tool using PyTorch. It detects action boundaries via feature similarity and refines segments with clustering, requiring no training or labels.

LDC: Lightweight Dense CNN for Edge DetectionのPythonでのONNX推論サンプル

🔍 Visualize React's `'use client'` boundaries with clear indicators, enhancing your code clarity and improving your development workflow.