Image and Video Enhancement Techniques

Video enhancement is one of the most important and difficult components in video research. The aim of video enhancement is to enhance the visual appearance of the video, or to provide a better transform representation for future automated video processing, such as analysis, detection, identification, recognition, surveillance, traffic, criminal justice systems. Generally we will see the disturbances in the old times where we used to record the video in the VCR in which there will the dots of red, green and blue colour which are the disturbances in the video. We will clear them with the video Enhancement techniques. In this present world Image and Video Enhancement techniques are very important. Here by using Image and Video Enhancement techniques we will improve the quality of the Image and Videos so that we can get a better image. Many images like medical images, satellite images, aerial images and even real life photographs suffer from poor contrast and noise. It is important to enhance the contrast and remove the noise to increase image quality. A standout amongst the most essential stages in medical images detection and analysis is Image Enhancement techniques which improves the quality (clarity) of images for human viewing, remove blur and noises, increase the contrast, and revealing details are examples of enhancement operations. We basically eliminate the noises and disturbances which are occurred while taking the image.

Introduction

Image processing is a strategy to perform a few operations. in order to get an enhanced image. It is a type of signal processing in which input is an image and output will also be an image but the output image will be the clear one without any noises and disturbances. Nowadays, image processing and video enhancement are among rapidly developing innovations. It frames center research area withinRetinex strategy essentially comprises of two stages: estimation and normalization of illumination. Step by step instructions to extricate the background illumination precisely is a key issue. The backgrounds of picture arrangement in video's nearby edges are generally comparative and firmly related. More exact illumination information can be extracted when this attributes of video's photo succession is considered Retinex enhances visual rendering of a picture when lighting conditions are bad. While our eye can see hues effectively when light is low, cameras and video cams can't deal with this well.

The MSRCR i. e MultiScale Retinex with Color Restoration, calculation, which is at the foundation of the Retinex channel, is motivated by the eye natural components to adjust to these conditions. Retinex remains for Retina + cortex. A gray level modification strategy which permits us to enhance the picture contrast and additionally to enhance the homogeneity of the areas in the picture. It depends on optimal classification of the picture gray levels, trailed by a nearby parametric gray level change connected to the got classes. By method for two parameters speaking to, separately a homogenization coefficient (r) and a craved number (n) of classes in the yield picture, Gray-scale modification (called gray level scaling) techniques have a place in the classification of point operations and capacity by changing the pixel's (gray level) values by a mapping equation. The mapping equation is ordinarily straight (nonlinear conditions can be displayed by piecewise linear transformation and maps the original gray level qualities to other, indicated values. Regular applications incorporate contrast enhancement and feature enhancement.

The essential operations connected to the dim size of a picture are to pack or extend it. We ordinarily pack gray level ranges that are of little enthusiasm to us and extend the gray level reaches where we seek more data. On the off chance that the incline of the line is somewhere around zero and one, this is called gray-level compression, while if the slant is more noteworthy than one, it is called gray-level stretching. The first and changed pictures where we can see that extending this range uncovered beforehand concealed visual data. Now and again we might need to extend a particular scope of gray levels, while cutting the qualities at the low.

Now for making a noise free video, we will add the snap shots of infinity loop images which are cleared from using the above filters and the output video will be the disturbance free and the will be adjustments in the contrast and the noise cancelations.

Literature review

Real-time video upgrade is by and large accomplished utilizing exorbitant particular equipment that have specific capacities and yields. Business off-the-rack equipment, for example, desktop PCs with Graphics Processing Units (GPUs), are likewise generally utilized as financially savvy answers for ongoing video handling. Before, the confinements in PC equipment implied that constant video improvement was essentially done on desktop GPUs with insignificant utilization of the Central Processing Unit (CPU). These calculations were basic and effectively parallelizable in nature, which empowered them to accomplish ongoing execution. Be that as it may, complex improvement calculations likewise require the successive preparing of information and this can't be effectively accomplished progressively on a GPU. In this paper, the present advances in portable CPU and GPU equipment are utilized to execute video Improvement calculations recently on a versatile PC. Both the CPU and GPU are utilized adequately to accomplish real time execution for complex picture improvement calculations that require both consecutive and parallel handling operations. Results are exhibited for histogram evening out, neighbourhood versatile histogram balance, contrast improvement utilizing tone mapping and presentation combination of different 8-bit dim scale recordings of size up to 1600×1200 pixels. Unfavourable weather conditions such as snow, mist or overwhelming precipitation incredibly diminish the visual quality of open air observation recordings.

Video quality upgrade can improve the visual quality of reconnaissance recordings giving clearer pictures more subtle Elements. Existing work in this territory for the most part centres on quality enhancement for high determination recordings or still pictures, but few calculations are created for enhancing reconnaissance recordings, which normally have low determination, high noise and pressure antiques. What's more, for snow or rain conditions, the picture quality of close filed perspective is degraded by the obscuration of obvious snowflakes and raindrops, while the quality of far field perspective is degraded by the obscuration of fog-like snowflakes or raindrops. Not very many video quality improvement calculations have been developed to handle both problems.

Research frame

The low light video is connected to the initial step which is pre-processing. Picture pre-handling is the name for operations on pictures at the most minimal level of reflection whose point is a change of the picture information that smother undesired mutilations or upgrades some picture highlights imperative for further preparing. It doesn't build picture data content. Its techniques utilize the extensive excess in pictures.

Noise reduction

Generally noise is the result of errors occurred in image acquisition. Which result in pixel values that do not reflect of real scene. variety types of noises and various noise reduction strategies which are classified into two domains which are spatial domain and frequency domain.

Contrast enhancement

Contrast is defined as the separation between the darkest and brightest areas of the image. Increase contrast and you increase the separation between dark and bright, making shadows darker and highlights brighter. Adding contrast usually adds "pop" and makes an image look more vibrant while decreasing contrast can make an image look duller or Contrast of an image is a measure of its dynamic range, or the "spread" of its histogram.

Denoising

The final step of low light video enhancement we have to apply filtering techniques for smoothing the remaining noise. Most of the noise is removed by the noise reduction techniques, the noise is introduced by contrast enhancement step. The de noising is done by using various filters.

Enhanced video

Output video will be the disturbance free and the will be adjustments in the contrast and the noise cancelations. Finally we get an enhanced video.

Methodlogy

MATLAB provides the necessary functionality for basic video processing using short video clips and a limited number of video formats. Not long ago, the only video container supported by built-in MATLAB functions was the AVI container, through functions such as aviread, avifile, movie2avi, and avi info.

• We will take an original video file as inputaviread: reads an AVI movie and store the frames into a MATLAB movie structure. aviinfo: returns a structure whose fields contain information (e. g. , frame width and height, total number of frames, frame rate, file size, etc. ) about the AVI file passed as a parameter. Mmreader: constructs a multimedia reader object that can read video data from a variety of multimedia file formats.
• Video is divided into individual snapshots. Convert frame to an image using frame2im. Process the image using any technique. Convert the result back into a frame using im2frame.
• Here we are getting using a continuous frame of images.
• If we are having R, G, B values we are using image enhancement function.
• If it is black and white picture we are using gray scale enhancement by using 0 and 1Gray scaleIn photography and computing, a grayscale or greyscale digital image is an image in which the value of each pixel is a single sample, that is, it carries only intensity information. Images of this sort, also known as black-and-white, are composed exclusively of shades of gray, varying from black at the weakest intensity to white at the strongest.

Grayscale images are distinct from one-bit bi-tonal black-and-white images, which in the context of computer imaging are images with only two colors, black and white (also called bit level or binary images). Grayscale images have many shades of gray in between.

Grayscale images are often the result of measuring the intensity of light at each pixel in a single band of the electromagnetic spectrum (e. g. infrared, visible light, ultraviolet, etc. ), and in such cases they are monochromatic proper when only a given frequency is captured. But also they can be synthesized from a full color image; see the section about converting to grayscale.

Numerical representation: The intensity of a pixel is expressed within a given range between a minimum and a maximum, inclusive. This range is represented in an abstract way as a range from 0 (total absence, black) and 1 (total presence, white), with any fractional values in between. This notation is used in academic papers, but this does not define what "black" or "white" is in terms of colorimetry.

Another convention is to employ percentages, so the scale is then from 0% to 100%. This is used for a more intuitive approach, but if only integer values are used, the range encompasses a total of only 101 intensities, which are insufficient to represent a broad gradient of grays. Also, the percentile notation is used in printing to denote how much ink is employed in half toning, but then the scale is reversed, being 0% the paper white (no ink) and 100% a solid black (full ink). In computing, although the grayscale can be computed through rational numbers, image pixels are stored in binary, quantized form. Some early grayscale monitors can only show up to sixteen (4-bit) different shades, but today grayscale images (as photographs) intended for visual display (both on screen and printed) are commonly stored with 8 bits per sampled pixel, which allows 256 different intensities (i. e. , shades of gray) to be recorded, typically on a non-linear scale. The precision provided by this format is barely sufficient to avoid visible banding artifacts, but very convenient for programming because a single pixel then occupies a single byte.

Technical uses (e. g. in medical imaging or remote sensing applications) often require more levels, to make full use of the sensor accuracy (typically 10 or 12 bits per sample) and to guard against round off errors in computations. Sixteen bits per sample (65, 536 levels) is a convenient choice for such uses, as computers manage 16-bit words efficiently. The TIFF and the PNG (among other) image file formats support 16-bit grayscale natively, although browsers and many imaging programs tend to ignore the low order 8 bits of each pixel. No matter what pixel depth is used, the binary representations assume that 0 is black and the maximum value (255 at 8 bpp, 65, 535 at 16 bpp etc. ) is white, if not otherwise noted. F. We will enhance each image by improving the contrast and removing the noisesG. If it is colour image we will divide the current image into R, G, and B values as the original image will be combination of all the three values H. We will apply inverse and Fourier transformation to each R, G, B values.

Fourier tranforms

A transform is a mathematical tool that allows the conversion of a set of values to another set of values, creating, therefore, a new way of representing the same information. In the field of image processing, the original domain is referred to as spatial domain, whereas the results are said to lie in the transform domain. The motivation for using mathematical transforms in image processing stems from the fact that some tasks are best performed by transforming the input images, applying selected algorithms in the transform domain, and eventually applying the inverse transformation to the resultFourier series simply states that, periodic signals can be represented into sum of sines and cosines when multiplied with a certain weight. It further states that periodic signals can be broken down into further signals. Since as we have seen in the frequency domain, that in order to process an image in frequency domain, we need to first convert it using into frequency domain and we have to take inverse of the output to convert it back into spatial domain.

The frequency domain is a space in which each image value at image position F represents the amount that the intensity values in image I vary over a specific distance related to F. In the frequency domain, changes in image position correspond to changes in the spatial frequency, (or the rate at which image intensity values) are changing in the spatial domain image I. The spatial domain is the normal image space, in which a change in position in I directly projects to a change in position in S. Distances in I (in pixels) correspond to real distances in S.

This concept is used most often when discussing the frequency with which image values change, that is, over how many pixels does a cycle of periodically repeating intensity variations occur. One would refer to the number of pixels over which a pattern repeats (its periodicity) in the spatial domain. The 2D FT and its inverse are implemented in MATLAB by functions fft2 and ifft2, respectively. 2D FT results are usually shifted for visualization purposes in such a way as to position the zero-frequency component at the centre of the spectrum. This can be accomplished by function fftshift. These functions are extensively used in the tutorials of this chapter. MATLAB also includes function ifftshift, whose basic function is to undo the results of fftshift.

Conclusion

The above algorithm we applied to the video is retinex algorithm. where we finally get an enhanced video with removing of multiple noises and to enhance low illumination videos so that the luminance and contrast of videos could be improved and the continuity of frames could be guaranteed.