April 2017
Beginner to intermediate
250 pages
6h 28m
English
The next step for each segmented character is to extract the features for training and classify the Artificial Neural Network algorithm.
Unlike plate detection, the feature extraction step used in SVM doesn't use all of the image pixels. We will apply more common features used in OCR that contain horizontal and vertical accumulation histograms and low-resolution image samples. We can see this feature more graphically in the next image, as each image has a low resolution 5x5 image and the histogram accumulations:

For each character, we will count the number of pixels in a row or column with a nonzero value using the countNonZero ...
Read now
Unlock full access