Recognition of traffic signs is a challenging real-world problem of high industrial relevance. Although commercial systems have reached the market and several studies on this topic have been published, systematic unbiased comparisons of different approaches are missing and comprehensive benchmark datasets are not freely available.
Traffic sign recognition is a multi-class classification problem with unbalanced class frequencies. Traffic signs can provide a wide range of variations between classes in terms of color, shape, and the presence of pictograms or text. However, there exist subsets of classes (e. g., speed limit signs) that are very similar to each other.
The classifier has to cope with large variations in visual appearances due to illumination changes, partial occlusions, rotations, weather conditions, etc.
Humans are capable of recognizing the large variety of existing road signs with close to 100% correctness. This does not only apply to real-world driving, which provides both context and multiple views of a single traffic sign, but also to the recognition from single images.
It's a great dataset for multi-class image classification problem.
Update: If you have downloaded the data before 4/14/2020, please re-download the data. The labels in the new dataset are now one-hot encoded