[ICRA 2023] Official Pytorch implementation for HFT

Take any phone-taken picture and turn it into a document scan.

Lightweight, High-Performance and easy-to-use library for performing Affine, Projective or Piecewise Affine transformations over any Image or HTMLElement from only a set of reference points. In Javascript.

This repository illustrates all of the progress in my internship program at UniCloud Group. Thanks to my leader, namely Kieu-Anh NT, and AI team members, I definitely complete my project with the state-of-the-art methods, and help eKYC services that can be updated a new function for users in banking application.

A python script to get Perspective Transformed(birds eye view) version of an input image using OpenCV. This is analogous to the CamScanner select region feature.

Extract Aadhaar card details using Tesseract OCR

Advanced Lanes Detection using camera calibration, gradient/colour thresholding, a bird's-eye view perspective transform, a sliding window search and quadratic polynomial fits

Detected highway lane boundaries on a video stream with OpenCV image analysis techniques, including camera calibration matrix, distortion correction, color transforms, gradients, etc., to create a thresholded binary image, a perspective transform to rectify binary image ("birds-eye view"). Detected lane pixels and fit to find the lane boundary, …

A sudoku solver web application based on image processing techniques.

Image processing pipeline for detecting highway lane in a video

This project was created on Modern OpenGL . It simulates randomly falling particles (here leafs) . Simulation is free from any repetitive patterns

image warp in c function

Collection of notebooks for image segmentation tasks.

Ionic React Document Scanner using Dynamsoft Document Viewer and Dynamsoft Document Normalizer

Perspective CSS Project

Python, Camera calibration and undistortion, Color and Gradient threshold, Warping and unwarping functions

Applied signal processing to dash-cam video feed to detect lane lines on the road and used numerical methods to derive approximate real-world measurements of the lane lines.

A cv2-based implementation of a self-driving car module responsible for lane lines detection under different lighting conditions, pavement textures and curves.

CarND Advanced Lane Detection. See my demo at https://www.youtube.com/watch?v=ItwgPuQojds&feature=youtu.be

image rectification, thresholding, perspective transform and sliding-window search implementation for lane lines