Scribd Logo
Upload

Welcome to Scribd!

  • 37 views

    Image Enhancement Under Improper Lightning Condition: A Project Review On

    Uploaded by

    Sai Kumar
    IMAGE ENHANCEMENT UNDER IMPROPER LIGHTNING CONDITION

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Image Enhancement Under Improper Lightning Condition: A Project Review On

    Uploaded by

    Sai Kumar
    37 views27 pages
    IMAGE ENHANCEMENT UNDER IMPROPER LIGHTNING CONDITION

    Original Title

    A15 BATCH

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    IMAGE ENHANCEMENT UNDER IMPROPER LIGHTNING CONDITION

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    37 views27 pages

    Image Enhancement Under Improper Lightning Condition: A Project Review On

    Uploaded by

    Sai Kumar
    IMAGE ENHANCEMENT UNDER IMPROPER LIGHTNING CONDITION

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 27

    A project review on

    IMAGE ENHANCEMENT UNDER IMPROPER LIGHTNING


    CONDITION

    Under the esteemed Guidance of


    Supervisor Name : Mr. P.SATISH BABU, M.tech
    Designation : Asst.Professor
    Department of ECE, RCEE
    Batch:A-15
    Project Area : Image and signal processing
    J.Sai Teja :15ME1A0458
    B.Rama Krishna :15ME1A0421
    B.Yugandhar :15ME1A0417
    G.Hema :15ME1A0447
    OVERVIEW OF THE PROJECT

     Abstract
     Introduction
     Objective of the project
     Scope of the project
     Literature survey
     Problem Definition (Existing, Limitations)
     Proposed model
     Block diagram
     Software Modules
     Methodology
     Working Procedure/Flow Chart
     Simulation Results
     Spatial domain
     Comparative Results
     Applications, Advantages
     Conclusion
     Future Scope
     References
    ABSTRACT
     A new wavelet-based image enhancement algorithm is
    proposed to improve performance of face detection in non-
    uniform lighting environment with high dynamic or
    decomposition range
     In this wavelet transform is used for dimension reduction
     We also use local contrast enhancement and hyperbolic sine
    curve which are used for further image compression and
    enhancement
     Histogram equalization is also used for better enhance ment
    INTRODUCTION

     It is well known that human eyes perform much better than cameras when
    imaging real world scenes having high dynamic range that can span more than six
    orders of magnitude.
     Currently available imaging devices can measure only about three orders of
    magnitude.
     As a result the images captured in scenes with high dynamic range commonly
    suffer from poor visibility due to either overexposure causing saturation or
    underexposure resulting in low contrast dark images.
     This leads to poor representation of some of the important features in resulting
    images there by making it difficult to pick those by human eye or by computer
    vision algorithms.
    OBJECTIVE

     The main objective of this project is a new method proposed to solve the
    problem of blur, resolution, noise and contrast changes by using wavelet-
    based dynamic range compression for image quality enhancement.
    SCOPE OF THE PROJECT

     In this project to enhance an image from different types of noises and other problems of
    blur, resolution and contrast changes with support of spatial enhancement techniques.
     It follows that image can be segmented into patches by using Wavelet-based Dynamic
    Range Compression(WDRC) then proceeding with local enhancement with spatial
    enhancement techniques(histogram processing).
    LITERATURE SURVEY

     (2013) created a first of a kind blind IQA model that assesses image
    quality without knowledge of anticipated distortions or human opinions
    of them. The quality of the distorted image is expressed as a simple
    distance metric between the model statistics and those of the distorted
    image. The new model outperforms FR IQA models and competes with
    top performing NR IQA trained on human judgments of known
    distorted images. Such a model has great potential to be applied in
    unconstained environments.
     (2017) classical image processing limits by combining semantic patches
    and registration methods for visual image enhancement. We
    demonstrate our method for the problem of cellular photography
    enhancement of dark facial images. Given today’s easily available
    photography devices, our model assumes that high-quality personal
    EXISTING SYSTEM

     In the past decades, handling common image flaws has gradually


    improved with the use of more sophisticated image priors and models.
     Early methods used pixel-based statistics, such as smoothness,
    piecewise smoothness, total-variation, pixel correlation, or wavelet
    decompositon for image reconstruction.
     In recent years, using generic image priors has started to reach an
    optimally bound;e.g., for super resolution and de noising.
    LIMITATIONS

     Its simplistic model which can address only frontal images with little
    expression variations and large non-facial regions.
     Using LR patches.
     Using very large HR dataset(thousands of images).
     Small in size.
    PROPOSED MODEL
     Relying on the conncept of non-rigid semantic patches of personal priors,
    we present an end-to-end application which approximates this concept for
    semantically-aware. illustration of an eye afinity space, constructed based
    on the Demon based affinity measure.
     Quality enhancement of facial images, using a nearest neighbor search.
    Block diagram represents the proposed method.
    Block diagram
    SOFTWARE MODULES

     Tool -MATLAB R2017a


     Operating system -Windows Xp,10
    MATLAB

     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.
     MATLAB® is a high-performance language 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.
    WINDOWS(OS)

     Microsoft windows is an operating system for computers which is made


    by Microsoft, a company from the United States.
     Microsoft has made several advancements and changes that have made
    it easier operating system.
     Because of the large amount of microsoft windows users there is a
    much larger selection of available software programs, utilities, and
    games for windows.
    METHODOLOGY

     Wavelet transform is used for dimension reduction such that a dynamic range
    compression with local contrast enhancement algorithm is applied only to the
    approximation coefficients
     The normalized approximation coefficients are transformed using a hyperbolic
    sine curve and the contrast enhancement is realized by tuning the magnitude of
    each coefficient with respect to its surrounding coefficients.
     The transformed coefficients are then de-normalized to their original range.
    The detail coefficients are also modified using the ratio between the original
    and enhanced approximation coefficients, followed by the inverse wavelet
    transform resulting in a low dynamic range and contrast enhanced intensity
    image.
    WORKING PROCEDURE

     In this process consists of a collection of techniques that seek to


    improve the visual appearance of an image or to convert the image to
    a form better suited for analysis by a human or machine.
     To modify attributes of an image to make it more suitable for a given
    task and a specific observer.
     It improves the quality of the image for a specific application..
    Working procedure
    SIMULATION RESULTS
    Spatial domain

     A digital image is a grid of pixels. A pixel is the smallest element in an image.


    Each pixel corresponds to any one value called pixel intensity. Now the
    intensity of an image varies with the location of a pixel. Let I be an image and
    (x,y) is the location (or coordinate) of any pixel then the image is represented
    as a function of location : I(x,y), where x and y are integers. Thus an image
    I(x,y) is a matrix of pixels.

     The term spatial refers to space. In an image, this space is a 2D plane (xy-
    plane). So, the spatial domain refers to the image plane itself and methods in
    spatial domain are based on directly modifying the value of the pixels. Spatial
    domain processes are represented as

     I1(x,y)=T[I(x,y)]

    COMPARATIVE RESULTS
    APPLICATIONS

     Audio/image/video processing tasks(compression, denoising,


    deblurring, inpainting and superresolution).
     Image retrieval.
     Medical imaging and analysis.
     Quality control.
    ADVANTAGES

     Minimizes the errors.


     Improves quality & productivity.
     Smoothening or denoising data.
     Less time taking process.
     Faster in speed.
    CONCLUSION

     A wavelet based fast image enhancement algorithm which provides dynamic


    range compression preserving the local contrast and tonal rendition has been
    developed to improve the visual quality of the digital images.
     Experiments conducted for evaluating the improvement in face detection
    showed that proposed technique is more suitable as a preprocessor in face
    detection schemes when compared with MSRCR and IRME.
    FUTURE SCOPE

     This work can be extended further by applying modified WRDC to real


    time video streaming for enhancing video quality.
    REFERENCES

     Hait, Ester, and Guy Gilboa. “Blind Facial Image Quality Enhancement
    using Non-Rigid Semantic Patches.” IEEE Transactions on Image
    Processing 26.6 (2017): 2705.
     J-P Thirion. Image matching as a dilusion process: an analogy with
    maxwell’s demons. Medical image analysis, 2(3):243-260, 1998.
     Anish Mittal, Ravi Soundararajan, and Alan C Bovik. Making a
    “completely blind” image quality analyzer. Signal Processing Letters,
    IEEE, 20(3):209-212, 2013.
     Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, and Karen
    Egiazarian. Color image denoising via sparse 3d collaborative filtering
    with grouping constraint in luminance-chrominance space. In Image
    Processing, 2007. ICIP 2007. IEEE International Conference on,

    You might also like