+ All Categories
Home > Documents > Summer Training Baljeet

Summer Training Baljeet

Date post: 07-Apr-2018
Category:
Upload: kartikay-kulshrestha
View: 234 times
Download: 0 times
Share this document with a friend

of 28

Transcript
  • 8/4/2019 Summer Training Baljeet

    1/28

    SUMMER TRAINING REPORT

    (13th June to 12th July 2011)

    ON

    IMPLEMENTATION OF PLATEAU

    HISTOGRAM EQUALIZATION ALGOROTHIM

    FOR IMAGE ENHANCEMENT USING

    MATLAB

    Training undertaken at:Training undertaken at:

    Instruments Research and Development EstablishmentInstruments Research and Development Establishment

    DRDO, MINISTRY OF DEFENCEDRDO, MINISTRY OF DEFENCE

    GOVERNMENT OF INDIAGOVERNMENT OF INDIA

    Raipur RoadRaipur Road, Dehradun, Dehradun

    Submitted by:

    Ravi Singh

    B.Tech 3rd yr, Electronic & Communication Engg.

    Graphic Era University

    (Dehradun)

  • 8/4/2019 Summer Training Baljeet

    2/28

    ACKNOWLEDGEMENT

    First of all I would like to express my sincere gratitude to Shri S.S.

    SUNDARAM, DIRECTOR IRDE, Dehradun, for giving me the

    opportunity of working in this esteemed organization.

    I would also like to thank Dr. S.S. NEGI, ASSOCIATE

    DIRECTOR TIS division, for giving me the opportunity to work in

    THERMAL IMAGING SYSTEM DIVISION (TIS) and also, for helping

    me in selecting the right environment for working and allowing me the

    project IMPLEMENTATION OF CENTROID ALGORITHM FOR

    TARGET TRACKING.

    This acknowledgement would be incomplete without mentioning the

    name of Mr. Dinesh Chander Singh, Sc. C, who not only guided methroughout the research work, but also provided the inspiration to try and

    accomplish the task assigned.

    I would also like to present my sincerest thanks to all the members,

    staff and officers of the TIS DIVISION for providing a helping hand at the

    time of need.

    Date: (ravi Singh)

  • 8/4/2019 Summer Training Baljeet

    3/28

    CERTIFICATE

    This is to certify that Mr.ravi Singh, student ofELECTRONIC &

    COMMUNICATION ENGINEERING, B.TECH IIIrd YEAR,

    GRAPHIC ERA UNIVERSITY, has undergone training at TIS Division of

    I.R.D.E., Dehradun from 13th June to 12th July 2011 .During this period, he

    was assigned the work IMPLEMENTATION OF PLATEAU

    HISTOGRAM EQUALIZATION ALGOROTHIM FOR

    IMAGE ENHANCEMENT USING MATLAB. He has

    completed his work and his work has been satisfactory during training.

    We wish him a prosperous career and success in life.

    (Dinesh Chander Singh) (Dr S.S. Negi)

    Scientist C Associate Director

    TIS Division TIS DivisionIRDE Dehradun IRDE Dehradun

  • 8/4/2019 Summer Training Baljeet

    4/28

    CONTENTS

    INTRODUCTION TO IRDE

    PRINCIPLE OF THERMAL IMAGING SYSTEM

    ELEMENTS OF THERMAL IMAGING SYSTEM

    MATLAB OVERVIEW

    DIGITAL IMAGE PROCESSING

    IMAGE HISTOGRAM

    PLATEAU HISTOGRAM EQILIZATIONALGORITHM

    MATLAB CODE

    RESULT AND ANALYSIS

    CONCLUSION

    REFERENCES

  • 8/4/2019 Summer Training Baljeet

    5/28

    INTRODUCTION TO IRDE

    Instruments Research and Development Establishment (IRDE), a major

    equipment oriented establishment within Defence Research and Developmentorganization, came into existence in its present form as an institute devoted

    exclusively to research and development in the field of instrumentation for the

    services on 1st December 1961. It, however, has an earlier history as a

    composite establishment performing dual role of R&D and inspection.

    1. Its origin can be traced back to the year 1939, when inspectorate of

    scientific stores was formed at Rawalpindi for the inspection of

    telecommunication equipments, used by Indian Army.

    2. It underwent changes taking the shape of Technical Development

    Establishment (Instruments and Electronics). With the increase in tempo

    of R&D work the responsibility to meet over increasing and exacting

    requirements of services in the respect of more and more advanced and

    sophisticated equipment, the establishment was upgraded to I.R.D.E. in

    February 1960.

    CHARTER OF WORK

    R&D, Design and Technology in the fields of Optical, Electro-

    Optical & Optronic Instrumentation, Fire Control Systems, Infrared search

    and Track and Stand Alone Surveillance Systems.

    R&D in applied optics including Optics Design, Optics

    Technology, Thin Films, Night Vision, Fiber Optics, Integrated & Non-

    Linear Optics, Holography and Optical signal processing etc.

  • 8/4/2019 Summer Training Baljeet

    6/28

    MAJOR AREAS OF ACTIVITIES

    Technology and product development:

    1. Thermal Imaging

    2. Night Vision Instrumentation3. Laser Ranging & Instrumentation

    4. Servo-stabilization Systems

    5. Fire Control Systems

    6. Software and Microprocessors

    7. Photonics and its Applications

    SPECIALIZED TECHNOLOGY SUPPORT

    1. Optics Design and Fabrication

    2. Thin Film Technology

    3. Precision Mechanism

    A large number of instruments for use by services have been designed &

    developed by the establishment and most of them are now in regular production

    with Ordnance Factories and other production agencies.

    Specialized groups of laboratories have been created in the establishment,

    which is devoted to the design and development of various types of instruments

    for application like sighting, vision, ranging and engagement etc.

    Though essentially equipment oriented laboratory I.R.D.E. has to its

    credit significant contribution in the fields of basic research in different areas of

    optical & theoretical research, studies conducted in holography, fiber optics,

    optical-imagery and spectroscopic study of materials in optical and infrared

    regions.

  • 8/4/2019 Summer Training Baljeet

    7/28

    Apart from normal R&D work connected with design and development

    of equipment for services use and development of allied and associated

    technologies, the establishment also has the role of undertaking investigation on

    major modification either with a view to extending the role of instruments of

    enhancing their useful life, prepare manufacturing particulars and assist the

    services in evolution of foreign equipment pertaining to its field of activity.

    The establishment is also responsible for the transfer of technology to

    firms both in public and private sectors for creating production base in country

    for sophisticated instruments developed by it. For this purpose a Technology

    Transfer Center (TTC) has been set up at the establishment for smooth transfer

    of new technologies evolved in the field of electro-optical instrumentation to

    concerned production engineer.

    ORGANIZATIONAL SETUP

    Theestablishment has been organized into 10 technical divisions and 8

    independent groups, directly responsible to the director apart from

    administrative, financial and security aspects.

    INFRASTRUTURE

    The establishment has well equipped laboratories looking after the development

    of optical instruments, night vision equipments, holographic systems, thermal

    imaging systems etc. All these laboratories are equipped with sophisticated and

    modern test equipments and devices.

    LIBRARY & DOCUMENTATION SERVICE

    The establishment has well-equipped reprographic section to look after printing

    and reproduction work of technical documents and drawing. It also has a well-

    stocked technical laboratory.

  • 8/4/2019 Summer Training Baljeet

    8/28

    PRINCIPLE OF THERMAL IMGING SYSTEM

    Thermal imaging system as mentioned earlier picks up the IR radiation emitted

    by the objects, which are at temperature above zero Kelvin and also due to

    background temperature and emissivity differences. IR radiations are a part of

    the electromagnetic spectrum pertaining to the IR region and that the spectral

    radiant emittance curves in accordance with the Plancks black body law, it may

    be observed that targets at ambient temperature of 300K emit maximum amount

    of radiation at 10m, whereas the hotter targets like jet exhausts at 700K have

    peak spectral emission at around 4m.

    At wavelengths other than those of atmospheric windows i.e. between 2

    to 20 m the water vapor and CO2 molecules present in the atmosphere

    strongly absorb the IR radiation. A thermal sight employing IR detectors

    sensitive in the spectral bands convert the IR radiation emitted by the target into

    electrical signals. The detector output after suitable processing is again

    converted into a visible image either using a CRT displays or LED display.

  • 8/4/2019 Summer Training Baljeet

    9/28

    ELEMENTS OF THERMAL IMAGING SYSTEM

    1. Sources of Thermal Radiations

    Thermal imaging uses long mid and long wavelength IR because these

    occur naturally and are readily transmitted through the atmosphere. The objects

    in the scene are themselves the sources of radiations making up the image. It

    relies on the observed phenomenon that an objects glows when hot.

    Also when the temperatures of these objects fall, the range of wavelength of

    the objects shifts towards the red and of the spectrum. With optics and detectors

    that work into the IR we would continue to see the element low even as it is

    cooled to the room temperature and it is in this property that true benefits of the

    Thermal Imaging are realized. Objects at normal temperature glow even viewed

    in the infrared and so without the need for external illumination, glow shows

    even in dark.

    2. Optics

    Optical system is required to produce a focused image of a distant scene

    while eliminating radiations from sources outside the scene. Baffles are used to

    eliminate stray radiation inside the optical system and because the system is a

    thermal imager it is necessary to fully absorb the stray radiations. Lenses may

    be used to collect and focus the radiation from the sources. Typically a multi

    element design is required so that optical aberration can be minimized.

  • 8/4/2019 Summer Training Baljeet

    10/28

    3. Detectors

    They have a simple function i.e. to absorb the thermal radiations from the

    part of scene and convert it to the electrical signal. The strength of the signal is

    then the measure of the temperature of that part of the scene. By compiling the

    outputs from many detectors, or moving the scene across the detectors, a

    complete image of the scene is obtained.

    4. Cooling

    It is necessary to dissipate the heat of the detector array, which may get

    heated due to the incident infrared radiations. The cooling may be obtained byeither of the following methods

    Pettier cooling

    Joule cooling

    Stirling cooling

    Most commonly the stirling cooling is adopted in the Thermal Imaging

    systems.

    5. Signal processor and display

    In signal processor electrical signals, form IR detector is signal

    conditioned, digitized and process to form real time image. The display is

    generally the CRT display. The amplified signal form the detector array is

    multiplexed to get single line video, which can, then be fed, into the CRT to get

    IR image of the scene in the CRT. Video can also be made compatible to TV

    using a digital scan converter and displayed onto a standard monitor.

  • 8/4/2019 Summer Training Baljeet

    11/28

    MATLAB OVERVIEW

    MATLAB is a high-performance tool for technical computing. It

    integrates computation, visualization, and programming in an easy-to-use

    environment where problems and solutions are expressed in familiar

    mathematical notation. Typical uses include:

    1. Math and computation

    2. Algorithm development

    3. Data acquisition

    4. Modeling, simulation, and prototyping

    5. Data analysis, exploration, and visualization

    6. Scientific and engineering graphics

    7. Application development, including graphical user interface building

    MATLAB is an interactive tool whose basic data element is an array that does

    not require dimensioning. This allows you to solve many technical computing

    problems, especially those with matrix and vector formulations, in a fraction of

    the time it would take to write a program in a scalar non-interactive language

    such as C orFORTRAN.

    The name MATLAB stands for Matrix Laboratory. MATLAB was originally

    written to provide easy access to matrix software developed by the LINPACK

    and EISPACK projects, which together represent the state-of- the art in

    software for matrix computation.

  • 8/4/2019 Summer Training Baljeet

    12/28

    MATLAB has evolved over a period of years with input from many

    users. In university environments, it is the standard instructional tool for

    introductory and advanced courses in mathematics, engineering, and science. In

    industry, MATLAB is the tool of choice for high-productivity research,

    development, and analysis.

    MATLAB features a family of application-specific solutions called

    toolboxes. Very important to most users ofMATLAB, toolboxes allow you to

    learn and apply specialized technology. Toolboxes are comprehensive

    collections of MATLAB functions (M-files) that extend the MATLAB

    environment to solve particular classes of problems. Areas in which toolboxes

    are available include signal processing, control systems, neural networks, fuzzy

    logic, wavelets, simulation, and many others.

    The MATLAB System

    The MATLAB system consists of five main parts:-

    1. Desktop Tools and Development Environment:

    This is the set of tools and facilities that help you use MATLAB functions and

    files. Many of these tools are graphical user interfaces. It includes the

    MATLAB desktop and Command Window, a command history, an editor and

    debugger, and browsers for viewing help, the workspace, files, and the search

    path.

    2. The MATLAB Mathematical Function Library:

    This is a vast collection of computational algorithms ranging from elementary

    functions like sum, sine, cosine, and complex arithmetic, to more sophisticated

    functions like matrix inverse, matrix eigenvalues, Bessel functions, and fast

    Fourier transforms.

    3. The MATLAB Language:

  • 8/4/2019 Summer Training Baljeet

    13/28

    This is a high-level matrix/array language with control flow statements,

    functions, data structures, input/output, and object-oriented programming

    features. It allows both "programming in the small" to rapidly create quick and

    dirty throw-away programs, and "programming in the large" to create complete

    large and complex application programs.

    4. Graphics:

    MATLAB has extensive facilities for displaying vectors and matrices as graphs,

    as well as annotating and printing these graphs. It includes high-level functions

    for two-dimensional and three-dimensional data visualization, image

    processing, animation, and presentation graphics. It also includes low-level

    functions that allow you to fully customize the appearance of graphics as well

    as to build complete graphical user interfaces on your MATLAB applications.

    5. The MATLAB Application Program Interface (API):

    This is a library that allows you to write C and FORTRAN programs that

    interact with MATLAB. It includes facilities for calling routines from

    MATLAB (dynamic linking), calling MATLAB as a computational engine, and

    for reading and writing MAT-files. In the case of tracking, here we use image-

    processing toolbox of MATLAB where there are many functions that will help

    us during programming.

  • 8/4/2019 Summer Training Baljeet

    14/28

    DIGITAL IMAGE PROCESSING

    A thermal image is a continuously varying array of gray shades; shades

    vary from light to dark. All images are made of gray shades ranging from black

    to white.

    A digital image is composed of discreet points of gray tone or brightness, rather

    than continuously varying levels. Gray value of each pixel along a line is

    summed together & accumulated sum is subtracted from the previously

    accumulated sum of the same image.

    In a digital image, each pixel has a brightness value. To make a digital image

    from a continuous image, it must be divided into individual points of

    brightness. Each point of brightness must be described by a digital data value.The process of breaking up a continuous image & determining digital

    brightness values are referred to assampling& quantization respectively.

  • 8/4/2019 Summer Training Baljeet

    15/28

    The sampling process samples the intensity of a continuous image at

    specific locations. The quantization process determines the digital brightness

    values of each sample, ranging from black, through gray scales to white.

    A quantized sample is referred to as a picture element, or pixel because it

    represents a discreet digital element of digital image. The combination of

    sampling & quantization process is referred to as image digitization.

    An image is generally sampled into a rectangular array of pixels. Each pixel has

    an (x,y) coordinates that corresponds to its location with in the image. The x-

    coordinate is pixels horizontal location; the y- coordinate is its vertical

    location. The pixel with coordinate (0,0) is the upper left corner of the image.

    We have used 8- bit image, i.e. it contains 256 gray levels (0 to 25An in-

    focused image consists of sharp images, which contains rapid brightness

    transitions. Slowly varying brightness transitions represent out-of-focused

    image.

    Pictures are the most common and convenient means of conveying and

    transmitting information. Pictures concisely convey information about position,

    sizes and inter relationships between objects. Human beings are good at

    deriving information from such images because of our innate visual and mental

    abilities. About 75% of information received by human is in pictorial form. In

    the present context, the analysis of pictures that employ an overhead

    perspective, including the radiation not visible to human eye are considered.

    Thus, the focus will be on analysis of remotely sensed images. These images

    are represented in digital form. When represented as numbers brightness can be

    added, subtracted, multiplied, divided and, in general, subjected to statistical

  • 8/4/2019 Summer Training Baljeet

    16/28

    manipulations that are not possible if an image is presented only as a

    photograph.

    An image may be defined as two dimensional function, f(x, y ), where x & y

    are spatial co-ordinates, and the amplitude of f at any pair of co-ordinate is

    called the intensity or gray level of the image at that point. When x, y, and the

    amplitude values of f are finite, discrete quantities, we call the image a digital

    image.

    A digital image is composed of finite number of elements, each of which has a

    particular location and value. These elements are referred to as picture

    elements, image elements and pixels. Pixel is a term most widely used to denote

    the elements of digital image. Digital image processing refers to processing

    digital images by means of a digital computer.

    There are three types of computerized processes: low, mid and high level.

    Low-level processes involve primitive operations such as image pre-

    processing to reduce noise, contrast enhancement and image sharpening.

    Its inputs as well as outputs are both images.

    Mid-level processes on images involve tasks such as image segmentation.

    It is characterized by the fact that its inputs generally are images but its

    outputs are attributes extracted from those images. Higher level processing involves making sense of an ensemble of

    recognized objects.

  • 8/4/2019 Summer Training Baljeet

    17/28

    FUNDAMENTAL CLASSES OF DIGITAL IMAGE PROCESSING

    Digital image processing operations can be grouped into five fundamental

    classes:

    1. Image enhancement

    2. Image restoration

    3. Image analysis

    4. Image compression

    5. Image synthesis

    IMAGE HISTOGRAM

    An image histogram is a type ofhistogram that acts as a graphical

    representation of the tonal distribution in a digital image. It plots the number

    ofpixels for each tonal value. By looking at the histogram for a specific image

    a viewer will be able to judge the entire tonal distribution at a glance.

    Image histograms are present on many modern digital cameras. Photographers

    can use them as an aid to show the distribution of tones captured, and whether

    image detail has been lost to blown-out highlights or blacked-out shadows.[2]

    The horizontal axis of the graph represents the tonal variations, while

    the vertical axis represents the number of pixels in that particular tone.[1] The

    left side of the horizontal axis represents the black and dark areas, the middle

    http://en.wikipedia.org/wiki/Histogramhttp://en.wikipedia.org/wiki/Graphical_representationhttp://en.wikipedia.org/wiki/Graphical_representationhttp://en.wikipedia.org/wiki/Lightness_(color)http://en.wikipedia.org/wiki/Digital_imagehttp://en.wikipedia.org/wiki/Pixelshttp://en.wikipedia.org/wiki/Digital_camerashttp://en.wikipedia.org/wiki/Image_histogram#cite_note-1http://en.wikipedia.org/wiki/Horizontal_axishttp://en.wikipedia.org/wiki/Graphicshttp://en.wikipedia.org/wiki/Vertical_axishttp://en.wikipedia.org/wiki/Image_histogram#cite_note-sutton-0http://en.wikipedia.org/wiki/Histogramhttp://en.wikipedia.org/wiki/Graphical_representationhttp://en.wikipedia.org/wiki/Graphical_representationhttp://en.wikipedia.org/wiki/Lightness_(color)http://en.wikipedia.org/wiki/Digital_imagehttp://en.wikipedia.org/wiki/Pixelshttp://en.wikipedia.org/wiki/Digital_camerashttp://en.wikipedia.org/wiki/Image_histogram#cite_note-1http://en.wikipedia.org/wiki/Horizontal_axishttp://en.wikipedia.org/wiki/Graphicshttp://en.wikipedia.org/wiki/Vertical_axishttp://en.wikipedia.org/wiki/Image_histogram#cite_note-sutton-0
  • 8/4/2019 Summer Training Baljeet

    18/28

    represents medium grey and the right hand side represents light and pure white

    areas. The vertical axis represents the size of the area that is captured in each

    one of these zones. Thus, the histogram for a very bright image with few dark

    areas and/or shadows will have most of its data points on the right side and

    center of the graph. Conversely, the histogram for a very dark image will have

    the majority of its data points on the left side and center of the graph.

    Image enhancement using plateau histogram equalization

    algorithm

    This self-adaptive contrast enhancement algorithm is based on plateau

    histogram equalization for infrared images. By analyzing the histogram of

    image, the threshold value is got self-adaptively. This new algorithm can

    enhance the contrast of targets in most infrared images greatly. The new

    algorithm has very small computational complexity while still produces highcontrast output images, which makes it ideal to be implemented byFPGA (Field

    Programmable Gate Array) for real-time image process. This paper describes a

    simple and effective implementation of the proposed algorithm, including its

    threshold value calculation, by using pipeline and parallel computation

    architecture. The proposed algorithm is used to enhance the contrast of infrared

  • 8/4/2019 Summer Training Baljeet

    19/28

    images generated from an infrared focal plane array system and image contrast

    is improved significantly. Theoretical analysis and other experimental results

    also show that it is a very effective enhancement algorithm for most infrared

    images.

    An infrared image is created from infrared radiation of objects and their

    backgrounds. Generally the temperature difference between target objects and

    their background is small, and the temperature of background is high, which

    result in the fact that most infrared images have highly bright back-ground and

    low contrast between background and targets. In order to recognize targets

    correctly from these images, good enhancement algorithms must be applied

    firstly. Gray stretch, histogram equalization are general image enhancement

    algorithms. And histogram equalization is a widely used enhancement

    algorithm, in which the contrast of an image is enhanced by adjusting gray

    levels according to its cumulative histogram. But histogram equalization

    algorithm is not applicable to many infrared images, because the algorithm

    often mainly enhances image background instead of targets. In an effort to

    overcome this problem, Virgil E. Vichers and Silverman, proposed two new

    histogram-based algorithms:

    plateau histogram equalizationand

    histogram projection

    Plateau histogram equalization has been proven to be more effective, which

    suppresses the enhancement of background by using a plateau threshold value.

    But the plateau threshold value is an empirical value in general which limits the

    algorithms practical usage. A modification is made to plateau histogram

  • 8/4/2019 Summer Training Baljeet

    20/28

    equalization. By analyzing the histogram of infrared images, an estimated value

    of plateau threshold value is got self-adaptively. This modified algorithm is able

    to enhance the contrast of target objects in most infrared images more

    effectively than the original algorithm. It has very small computational

    complexity while still produces high contrast output images, which makes it

    ideal to be implemented by FPGA for real-time imaging applications. This

    describes an implementation of our proposed algorithm, including its plateau

    threshold value calculation by using pipeline and parallel computation

    architecture. The proposed algorithm has been used to enhance infrared images

    generated from an infrared focal plane array system and the contrast of image

    has been improved significantly.

    The principles of self-adaptive plateau Histogram

    equalization

    Plateau histogram equalization

    Plateau histogram equalization is a modification of histogram equalization,

    proposed by Virgil. Vichers and Silverman. An appropriate thresh-old value is

    selected firstly, which is represented as

  • 8/4/2019 Summer Training Baljeet

    21/28

    Selection of self-adaptive plateau threshold Value

    Selection of plateau threshold value is very important in the infrared image

    enhancement algorithm of plateau histogram equalization. It would have effect

    on the contrast enhancement of images. Appropriate plateau threshold value

    would greatly enhance the contrast of image. In addition, some plateau value

    would be appropriate to some infrared images, but not appropriate to others. As

    a result, the plateau threshold value would be selected self-adaptively according

    to different infrared images in the process of image enhancement.

    MATLAB CODE

    PROGRAM FOR ALGORITHM

    Clear all

  • 8/4/2019 Summer Training Baljeet

    22/28

    P=100; % set the pixel parameter from 1 to (n1*n2)

    A=imread (c:\image\256_256bmp);

    B=rgb2gray(a);

    Figure (1);

    imshow(b);

    b=double(b);

    [n1,n2] = size(b); % read the size of b

    For j= 1:256

    k(i)=0;

    c(i)=0;

    d(i)=0;

    ds(i)=0;

    end

    for i = 1:n1

    each

    For j=1:n2

    d=b(i,j);

    k(:,d+1)=k(:,d+1)+1; % count the no of pixel level(intensity)

    end

    end

    figure(2);

    plot(k); %plot the histogram

    xlabel(GRAYSCALE VALUES);

  • 8/4/2019 Summer Training Baljeet

    23/28

    ylabel(NUMBER OF PIXEL);

    for i =1:256

    c(i)=main(k(i),P);

    end

    figure(4);

    plot(c);

    for i =1:256

    sum=0;

    for j=1:i

    sum = sum+c(j);

    end

    d(i)=sum;

    end

    for i=1:256

    ds(i)=floor((256*d(i)/d(256));

    end

    for i=1:n1

    for J=1:n2

    kk=b(i,j);

    c(i,j)=ds(:,k+1)

    end

    end

    figure(3);

    imshow(c,[]);

  • 8/4/2019 Summer Training Baljeet

    24/28

    Results and analysis

    In this Algorithm, images are enhanced by histogram equalization, self-

    adaptive plateau histogram equalization respectively. Then a comparison is

    made between the original image and the enhanced image.

    The original histogram has three peaks that respectively represent the

    background, the upper part and the nether part of the glass. And it is compact

    and only occupies a fraction of the whole gray levels.

  • 8/4/2019 Summer Training Baljeet

    25/28

    So the image enhanced by self plateau histogram equalization is better than the

    image enhanced by equalization histogram.

    It is compact and only occupies a fraction of the whole gray space. Fig(b) is the

    enhanced image by histogram equalization. The ship is too brightened the

    background of the sea surface and the sky are greatly enhanced. And they made

    one uncomfortable. Fig. (e) is the histogram of image (b). In Fig. (e), the first

    peak correspond to back-grounds occupy approximately the whole gray levels,

    and the last peak in Fig. (c) disappeared in Fig. (e). So the backgrounds are

    mainly enhanced by histogram equalization .Fig. (c) is the enhanced image by

    self-adaptive plateau histogram equalization.

  • 8/4/2019 Summer Training Baljeet

    26/28

    Conclusion

    Infrared images can be enhanced effectively by the proposed algorithm. It

    has advantages over histogram equalization. And the plateau threshold value

    can be self-adaptive selected in this algorithm. By using pipeline and parallel

    computation architecture, the system can process25 frames of 128 128 8 bits

  • 8/4/2019 Summer Training Baljeet

    27/28

    infrared images in every second. And the experimental results show that the

    quality of enhanced image by self-adaptive plateau histogram equalization is

    better than the quality of enhanced image by histogram equalization. It works

    well in the infrared image process system.

    REFERENCES

    Image processing using MATLAB by C.Gonzalez

  • 8/4/2019 Summer Training Baljeet

    28/28

    Electro optical tracking systems considerationsA.George

    Downey, SPIE volume 1111, Acquisition, tracking and pointing

    part 3rd .

    www.wikipedia.com

    http://www.octec.co.uk/index.html

    http://kdl.cs.umass.edu/prox_overview/documentation/tutorial/in

    dex.html

    www.sciencedirect.co.in

    http://www.wikipedia.com/http://www.octec.co.uk/index.htmlhttp://kdl.cs.umass.edu/prox_overview/documentation/tutorial/index.htmlhttp://kdl.cs.umass.edu/prox_overview/documentation/tutorial/index.htmlhttp://www.wikipedia.com/http://www.octec.co.uk/index.htmlhttp://kdl.cs.umass.edu/prox_overview/documentation/tutorial/index.htmlhttp://kdl.cs.umass.edu/prox_overview/documentation/tutorial/index.html

Recommended