Comparing Performance of Preprocessing Techniques for Traffic Sign Recognition Using a HOG-SVM

2025/04/13 by Vieira, Luis · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2504.09424

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.

Citations

• The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale
• Distinctive Image Features from Scale-Invariant Keypoints
• THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS

Related

• Enhancing Traffic Sign Recognition with Tailored Data Augmentation: Addressing Class Imbalance and Instance Scarcity
• Efficient Traffic-Sign Recognition with Scale-aware CNN
• Traffic Sign Recognition Dataset and Data Augmentation
• Comparing the Machine Readability of Traffic Sign Pictograms in Austria and Germany
• A novel pLSA based Traffic Signs Classification System