Skip to content

Computer Vision coding implementation projects in C++

Notifications You must be signed in to change notification settings

LupraV/Computer_Vision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Computer_Vision

CV coding implementation projects in C++ for 159731 Studies in Computer Vision (Massey University)

Projects

  • Kuwahara filter (not perfect around the border)
  • QR code secret message decoder (over-engineered to account for 2D rotations, heavy noise and color distortions)
  • Final project: GTSRB traffic sign classification

Comparing Performance of Preprocessing Techniques for Traffic Sign Recognition (GTSRB) Using a HOG-SVM (Final Project)

Abstract

This study compares the performance of various preprocessing techniques for Traffic Sign Recognition (TSR) using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. Techniques such as CLAHE, HUE, and YUV were evaluated for their impact on classification accuracy. Results indicate that YUV in particular significantly enhance the performance of the HOG-SVM classifier (improving accuracy from 89.65% to 91.25%), providing insights into improvements for preprocessing pipeline of TSR applications.

Keywords: SVM; TSR; GTSRB; HOG; Road Signs Recognition; Traffic Signs; Classification.

License

This project is licensed under the Apache License 2.0.

About

Computer Vision coding implementation projects in C++

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published