Scribd Logo
Upload

Welcome to Scribd!

  • 256 views

    1 PPT Glucoma Detection

    Uploaded by

    Naveen Kumar
    The document proposes a Convolutional Neural Network system for early detection of glaucoma from eye images. It aims to provide a better and faster solution than existing graph tracer and support vector machine algorithms. The system initially pre-processes eye images through techniques like Gaussian blurring and median filtering. It then trains a CNN on the pre-processed images to classify new inputs as normal or glaucoma based on extracted features. The system is implemented using MATLAB and divided into modules for input/pre-processing, feature extraction/training, and output classification.

    Copyright:

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

    1 PPT Glucoma Detection

    Uploaded by

    Naveen Kumar
    256 views19 pages
    The document proposes a Convolutional Neural Network system for early detection of glaucoma from eye images. It aims to provide a better and faster solution than existing graph tracer and support vector machine algorithms. The system initially pre-processes eye images through techniques like Gaussian blurring and median filtering. It then trains a CNN on the pre-processed images to classify new inputs as normal or glaucoma based on extracted features. The system is implemented using MATLAB and divided into modules for input/pre-processing, feature extraction/training, and output classification.

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document proposes a Convolutional Neural Network system for early detection of glaucoma from eye images. It aims to provide a better and faster solution than existing graph tracer and support vector machine algorithms. The system initially pre-processes eye images through techniques like Gaussian blurring and median filtering. It then trains a CNN on the pre-processed images to classify new inputs as normal or glaucoma based on extracted features. The system is implemented using MATLAB and divided into modules for input/pre-processing, feature extraction/training, and output classification.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    256 views19 pages

    1 PPT Glucoma Detection

    Uploaded by

    Naveen Kumar
    The document proposes a Convolutional Neural Network system for early detection of glaucoma from eye images. It aims to provide a better and faster solution than existing graph tracer and support vector machine algorithms. The system initially pre-processes eye images through techniques like Gaussian blurring and median filtering. It then trains a CNN on the pre-processed images to classify new inputs as normal or glaucoma based on extracted features. The system is implemented using MATLAB and divided into modules for input/pre-processing, feature extraction/training, and output classification.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 19

    Objective

    • The main objective is designed and


    implemented the project using Convolutional
    Neural Network.
    • Our system will provide a better solution for
    detecting Glaucoma in the earlier phase in less
    time which will save the vision of many
    people.
    Abstract
    • Glaucoma is a group of related eye disorders that cause damage to the
    optic nerve that carries information from the eye to the brain which can
    get worse over time and lead to blindness.
    • It is very important that glaucoma is detected as early as possible for
    proper treatment.
    • In this project, we have proposed a Convolutional Neural Network (CNN)
    system for early detection of Glaucoma.
    • Initially, eye images are augmented to generate data for Deep learning.
    • The eye images are then pre- processed to remove noise using Gaussian
    Blur technique and make the image suitable for further processing.
    • The system is trained using the pre-processed images and when new
    input images are given to the system it classifies them as normal eye or
    glaucoma eye based on the features extracted during training.
    Existing System

    • Graph tracer algorithm: It is applied to the


    detection of the ocular fundus vessels
    • Based on vessels tracking, Cross over and
    Bifurcation are measured
    • Support vector machine algorithm is
    implemented to classify the retinal diseases
    Disadvantages

    • Wrong identification of diseases


    • Only classify vessels and non-vessels

    • Confusion can be occurred at the time of identify


    crossovers
    • Accuracy is less for predicting diseases
    • Can’t be implemented in real time
    Proposed System
    • Extracting green channel of retinal images

    • Implement singular spectrum analysis and CNN classification


    predict glaucoma detection
    • Median filter approach is used to eliminate noises in retinal
    images
    • Neural network is used to segment blood vessels with classify
    artery and vein values
    • Implement Optic disc and cup segmentation to predict the
    Glaucoma diseases
    Proposed Block Diagram
    Advantages

    • Correctly classify the retinal pixels from


    retinal images
    • Provide better accuracy

    • Simple way to predict all diseases


    • Vessel tracking includes all blood vessels
    Tools Used
    • Operating System : Windows 10
    • Software Tool : MATLAB R2014A
    • Processor : Any Intel x64 processor
    • CPU Speed : 2.2 GHz min
    • RAM : 4GB recommended
    • Disk Space : 30 GB for a typical installation
    • Display Resolution : 1024×768 or higher at normal size
    Three Modules
    On First Review On Second Review On Third Review

    Input Image and Pre- Feature Extraction and Output Classification


    Processing Module Training with CNN Module

    Software Requirements Develop and test with Complete the software


    confirmation and Installing project codes and simulation and test. Try
    software and check the algorithms with different images and
    codes. outputs.
    Collect the existing project Preparing the coding and Report and Technical
    information for documentation Documentation
    documentation
    First Module Implementation
    • Image Preprocessing
    • The aim of pre-processing is to improve the quality
    of the image so that we can analyze it in a better
    way.
    • By preprocessing we can suppress undesired
    distortions and enhance some features which are
    necessary for the particular application we are
    working for.
    • Those features might vary for different applications.
    Input Image
    • An image can be represented as a 2D function F(x,y) where x and y are spatial
    coordinates.
    • The amplitude of F at a particular value of x,y is known as the intensity of an image at
    that point.
    • If x,y, and the amplitude value is finite then we call it a digital image.
    • It is an array of pixels arranged in columns and rows. Pixels are the elements of an
    image that contain information about intensity and color.
    • An image can also be represented in 3D where x,y, and z become spatial coordinates.
    Pixels are arranged in the form of a matrix. This is known as an RGB image.
    • Gray scale conversion:

    – Gray scale image = 0.21 R + 0.72 G + 0.07 B.

    – R – Red, G- Green, B- Blue


    • When converting an RGB image to grayscale, we have to take the RGB values for
    each pixel and make as output a single value reflecting the brightness of that pixel.
    • Median Filtering:
    References
    1. Ahmad, Hafsah, et al. "Detection of glaucoma using retinal fundus
    images." 2014 International conference on robotics and emerging allied
    technologies in engineering (iCREATE). IEEE, 2014.
    2. Atheesan, S., and S. Yashothara. "Automatic glaucoma detection by using
    funduscopic images." 2016 International Conference on Wireless
    Communications, Signal Processing and Networking (WiSPNET). IEEE, 2016.
    3. Sengar, Namita, et al. "Automated detection of suspected glaucoma in digital
    fundus images." 2017 40th International Conference on Telecommunications
    and Signal Processing (TSP). IEEE, 2017.
    4. Almazroa, Ahmed, et al. "An automatic image processing system for glaucoma
    screening." International Journal of Biomedical Imaging 2017 (2017).
    5. Zhou, Wei, et al. "Automatic optic disc detection in color retinal images by
    local feature spectrum analysis." Computational and mathematical methods
    in medicine 2018 (2018).

    You might also like