Robust Blur Kernel Estimation for License Plate Images From Fast Moving Vehicles

ABSTRACT:

As the unique identification of a vehicle, license plate is a key clue to uncover over-speed vehicles or the ones involved in hit-and-run accidents. However, the snapshot of over speed vehicle captured by surveillance camera is frequently blurred due to fast motion, which is even unrecognizable by human. Those observed plate images are usually in low resolution and suffer severe loss of edge information, which cast great challenge to existing blind deblurring methods. For license plate image blurring caused by fast motion, the blur kernel can be viewed as linear uniform convolution and parametrically modeled with angle and length. In this paper, we propose a novel scheme based on sparse representation to identify the blur kernel. By analyzing the sparse representation coefficients of the recovered image, we determine the angle of the kernel based on the observation that the recovered image has the most sparse representation when the kernel angle corresponds to the genuine motion angle. Then, we estimate the length of the motion kernel with Radon transform in Fourier domain. Our scheme can well handle large motion blur even when the license plate is unrecognizable by human. We evaluate our approach on real-world images and compare with several popular state-of-the-art blind image deblurring algorithms. Experimental results demonstrate the superiority of our proposed approach in terms of effectiveness and robustness.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

• In existing system Motion deblurring can be cast as the deconvolution of an image that has been convolved with either a global motion point spread function (PSF) or a spatially varying PSF.

• The problem is inherently ill-posed as there are a number of unblurred images that can produce the same blurred image after convolution. Nonetheless, this problem is well studied given its utility in photography and video capture. The following describes several related works.

• The majority of related work lies in traditional blind deconvolution approaches that simultaneously estimate a global motion PSF and the deblurred image. A recent trend in motion deblurring is to either constrain the solution of the deblurred image or to use auxiliary information to aid in either the PSF estimation or the deconvolution itself (or both).

DISADVANTAGES OF EXISTING SYSTEM:

• Imaging sensor to capture low resolution imagery for the purpose of computing optical flow and estimating and the image are blurred to be produced on the camera .

• That will be blurred and noisy so we not find properly for the text format in the plate image .

PROPOSED SYSTEM:

• We propose a novel kernel parameter estimation algorithm for license plate from fast-moving vehicles. Under some very weak assumptions, the license plate deblurring problem can be reduced to a parameter estimation problem.

• An interesting quasi-convex property of sparse representation coefficients with kernel parameter (angle) is uncovered and exploited. This property leads us to design a coarse-to-fine algorithm to estimate the angle efficiently. The length estimation is completed by exploring the well-used power-spectrum character of natural image.

• Our goal is to recover a sharp license plate with confidence that the restored license plate image can be recognized by human effortlessly. Generally speaking, the blur kernel is dominated by the relative motion between the moving car and static surveillance camera, which can be modeled as a projection transform. However, the kernel can be approximated by linear uniform motion blur kernel.

• Once the angle is determined, on the direction parallel to the motion, the power spectrum of blurred image is obviously affected by the linear kernel based on which the spectrum is a sinc-like function, and the distance between its two adjacent zero-crossings in frequency domain is determined by the length of kernel.

• In order to reduce the effect of noise and improve the robustness of length estimation, we utilize the Radon transform in frequency domain. After kernel estimation, we obtain the final deblurring result with a very simple NBID algorithm.

ADVANTAGES OF PROPOSED SYSTEM:

• Our algorithm is that our model can handle very large blur kernel.

• Our scheme is more robust. very simple

• Naïve NBID algorithm method is that the proposed scheme can handle large motion blur even when the license plate is unrecognizable by human, which makes our approach promising in real applications.

MODULES:

1. Blur kernel method

2. Gray Image

3. Fourier transform

4. Radon transform

5. Morphological operation

6. Monte-Carlo method

7. De convolution method

MODULES DESCRIPTION:

Blur kernel method:

In image processing, a kernel, convolution matrix, or mask is a small matrix useful for blurring, sharpening, embossing, edge detection, and more. This is accomplished by means of convolution between a kernel and an image. The origin is the position of the kernel which is above (conceptually) the current output pixel. This could be outside of the actual kernel, though usually it corresponds to one of the kernel elements. For a symmetric kernel, the origin is usually the center element.

Gray Scale:

In some cases, rather than using the RGB or CMY color models to define grayscale, three other parameters are defined. These are hue, saturation and brightness. In a grayscale image, the hue (apparent color shade) and saturation (apparent color intensity) of each pixel is equal to 0. Conversion of a color image to grayscale is not unique; different weighting of the color channels effectively represents the effect of shooting black-and-white film with different-colored photographic filters on the cameras.

Fourier Transform:

The Fourier Transform is an important image processing tool which is used to decompose an image into its sine and cosine components. The output of the transformation represents the image in the Fourier or frequency domain, while the input image is the spatial domain equivalent. The DFT is the sampled Fourier Transform and therefore does not contain all frequencies forming an image, but only a set of samples which is large enough to fully describe the spatial domain image. The number of frequencies corresponds to the number of pixels in the spatial domain image, i.e. the image in the spatial and Fourier domain are of the same size.

Radon transformation:

In mathematics, the Radon transform is the integral transform which takes a function f defined on the plane to a function Rf defined on the (two-dimensional) space of lines in the plane, whose value at a particular line is equal to the line integral of the function over that line. The transform was introduced also provided a formula for the inverse transform. Radon further included formulas for the transform in three dimensions, in which the integral is taken over planes. It was later generalised to higher-dimensional Euclidean spaces, and more broadly in the context of integral geometry. The complex analog of the Radon transform is known as the Penrose transform. The Radon transform is widely applicable to tomography, the creation of an image from the projection data associated with cross-sectional scans of an object.

MORPHOLOGICAL OPERATION:

Morphological image processing is a collection of non-linear operations related to the shape or morphology of features in an image morphological operations rely only on the relative ordering of pixel values, not on their numerical values, and therefore are especially suited to the processing of binary images. Morphological operations can also be applied to grayscale images such that their light transfer functions are unknown and therefore their absolute pixel values are of no or minor interest. morphological operations rely only on the relative ordering of pixel values, not on their numerical values, and therefore are especially suited to the processing of binary images. Morphological operations can also be applied to greyscale images such that their light transfer functions are unknown and therefore their absolute pixel values are of no or minor interest.

Monte Carlo method:

Monte Carlo methods (or Monte Carlo experiments) are a broad class of computational algorithms that rely on repeated random sampling to obtain numerical results. Their essential idea is using randomness to solve problems that might be deterministic in principle. They are often used in physical and mathematical problems and are most useful when it is difficult or impossible to use other approaches. Monte Carlo methods are mainly used in three distinct problem classes: optimization, numerical integration, and generating draws from a probability distribution.

In physics-related problems, Monte Carlo methods are quite useful for simulating systems with many coupled degrees of freedom, such as fluids, disordered materials, strongly coupled solids, and cellular structures (see cellular Potts model, interacting particle systems, McKean-Vlasov processes, kinetic models of gases). Other examples include modeling phenomena with significant uncertainty in inputs such as the calculation of risk in business and, in math, evaluation of multidimensional definite integrals with complicated boundary conditions. In application to space and oil exploration problems, Monte Carlo–based predictions of failure, cost overruns and schedule overruns are routinely better than human intuition or alternative “soft” methods.

De convolution method:

In mathematics, de convolution is an algorithm-based process used to reverse the effects of convolution on recorded data. The concept of de convolution is widely used in the techniques of signal processing and image processing. Because these techniques are in turn widely used in many scientific and engineering disciplines, de convolution finds many applications.

In electrical engineering and applied mathematics, blind de convolution is de convolution without explicit knowledge of the impulse response function used in the convolution. In microscopy the term is used to describe de convolution without knowledge of the microscopes point spread function. This is usually achieved by making appropriate assumptions of the input to estimate the impulse response by analyzing the output.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System            : Pentium Dual Core.

• Hard Disk       : 120 GB.

• Monitor           : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB

• Tool                       : MATLAB R2013A

REFERENCE:

Qingbo Lu, Wengang Zhou, Lu Fang, and Houqiang Li, Senior Member, IEEE, “Robust Blur Kernel Estimation for License Plate Images From Fast Moving Vehicles”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 5, MAY 2016.