A New De-blurring Technique for License Plate Images with Robust Length Estimation

TL;DR

This paper introduces a novel de-blurring method for license plate images that accurately estimates motion blur parameters, especially length, using Hough transform and cepstral analysis, improving recognition in surveillance scenarios.

Contribution

The paper presents a new parametric de-blurring technique focusing on precise kernel length estimation using cepstral transform, enhancing license plate image clarity.

Findings

Effective removal of large motion blur from license plate images

Improved license plate recognition accuracy in surveillance images

Outperforms recent blind de-blurring methods

Abstract

Recognizing a license plate clearly while seeing a surveillance camera snapshot is often important in cases where the troublemaker vehicle(s) have to be identified. In many real world situations, these images are blurred due to fast motion of the vehicle and cannot be recognized by the human eye. For this kind of blurring, the kernel involved can be said to be a linear uniform convolution described by its angle and length. We propose a new de-blurring technique in this paper to parametrically estimate the kernel as accurately as possible with emphasis on the length estimation process. We use a technique which employs Hough transform in estimating the kernel angle. To accurately estimate the kernel length, a novel approach using the cepstral transform is introduced. We compare the de-blurred results obtained using our scheme with those of other recently introduced blind de-blurring techniques. The comparisons corroborate that our scheme can remove a large blur from the image captured by the camera to recover vital semantic information about the license plate.