A New De-blurring Technique for License Plate Images with Robust Length Estimation
This addresses the problem of identifying vehicles from blurred surveillance images for law enforcement or security applications, but it is incremental as it builds on existing de-blurring methods with a focus on kernel length estimation.
The paper tackled the problem of de-blurring license plate images from surveillance cameras by proposing a new technique that parametrically estimates the blur kernel, focusing on accurate length estimation using a novel cepstral transform approach. The result showed that the scheme can remove large blurs to recover semantic information, with comparisons indicating it outperforms other recent blind de-blurring techniques.
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.