Summary

In this chapter, you learned how an Automatic Plate License Recognition program works and its two important steps: plate localization and plate recognition.

In the first step, you learned how to segment an image looking for patches where we can have a plate, and use a simple heuristics and SVM algorithm to make a binary classification for patches with plates and no plates.

In the second step, you learned how to segment with the Find Contours algorithm, extract feature vector from each character, and use an ANN to classify each feature in a character class.

You also learned how to evaluate a machine algorithm with training with random samples, and using different parameters and features.

In the next chapter, you will learn how to create a face-recognition application using eigenfaces.