Comparing Performance of Preprocessing Techniques for Traffic Sign Recognition Using a HOG-SVM
This work addresses traffic sign recognition for autonomous driving systems, but it is incremental as it applies existing methods to a standard dataset.
This study tackled the problem of improving traffic sign recognition by comparing preprocessing techniques like CLAHE, HUE, and YUV on the GTSRB dataset using a HOG-SVM classifier, resulting in an accuracy increase from 89.65% to 91.25% with YUV.
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.