Vehicle License Plate Detection Using Only Block Partitioning Structure of the High Efficiency Video Coding (HEVC)

Abstract

In this study, the data which is compressed by the most recent video compression standard HEVC (High Efficient Video Coding) has been analyzed and shown that vehicle license plate can be detected without a need to full decode process. An image has been created that represents HEVC block partitioning structure which is available at the beginning of a compression process. A convolutional neural network, using these kind of images, is trained to find the corresponding number plate regions. For comparison; a second convolutional neural network is trained in pixel domain and the obtained results are given.