Scribd Logo
Upload

Welcome to Scribd!

  • 251 views

    Image Classification Report

    Uploaded by

    ali.nabeel246230
    This report summarizes an image classification task that classified images of mobile phones into categories like keypad phones and Android phones using MATLAB. Statistical features were extracted from preprocessed images and a support vector machine classifier was trained on the dataset and tested on a separate set of images. The results showed promising performance of the model with room for improvement, particularly in recognizing keypad phones. Future work proposed expanding the dataset and exploring deep learning techniques.

    Copyright:

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

    Image Classification Report

    Uploaded by

    ali.nabeel246230
    251 views7 pages
    This report summarizes an image classification task that classified images of mobile phones into categories like keypad phones and Android phones using MATLAB. Statistical features were extracted from preprocessed images and a support vector machine classifier was trained on the dataset and tested on a separate set of images. The results showed promising performance of the model with room for improvement, particularly in recognizing keypad phones. Future work proposed expanding the dataset and exploring deep learning techniques.

    Original Title

    image classification report

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This report summarizes an image classification task that classified images of mobile phones into categories like keypad phones and Android phones using MATLAB. Statistical features were extracted from preprocessed images and a support vector machine classifier was trained on the dataset and tested on a separate set of images. The results showed promising performance of the model with room for improvement, particularly in recognizing keypad phones. Future work proposed expanding the dataset and exploring deep learning techniques.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    251 views7 pages

    Image Classification Report

    Uploaded by

    ali.nabeel246230
    This report summarizes an image classification task that classified images of mobile phones into categories like keypad phones and Android phones using MATLAB. Statistical features were extracted from preprocessed images and a support vector machine classifier was trained on the dataset and tested on a separate set of images. The results showed promising performance of the model with room for improvement, particularly in recognizing keypad phones. Future work proposed expanding the dataset and exploring deep learning techniques.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 7

    MACHINE LEARNING REPORT

    Machine Learning

    Assingment #01

    Submitted by: Elen201101014

    Nabeel Murtaza
    MACHINE LEARNING REPORT

    Image Classification Using MATLAB


    List of equipment/Software

    1) MATLAB
    2) Computer

    Abstract:

    This report provides an overview of a task in which images of different things such as mobile
    phones, including keypad phones, and Android phones were classified using MATLAB. The
    report outlines the methods used, results obtained, and key observations.

    1. Introduction:
    This task involved classifying images into different categories: keypad phones, Android phones,
    childrens, youngers, and iPhones, using MATLAB.

    2. Data Collection and Preprocessing:


    Images of mobile phones,childerns were collected and organized into the specified classes.
    Preprocessing steps, including resizing and normalization, were applied to ensure uniformity in
    the dataset.

    3. Feature Extraction:
    Statistical features, such as mean and standard deviation, were extracted from the images to
    represent their characteristics.

    4. Model Training:
    A support vector machine (SVM) classifier was employed to train the model. The dataset was
    split into training and validation sets, and hyperparameters were tuned for optimal performance.

    1
    MACHINE LEARNING REPORT

    Fig.1. Train code

    5. Testing Procedure:
    The testing procedure involved the following steps:

    • A separate set of images was used for testing.


    • The trained model was applied to classify the test images into one of the three specified
    classes.
    • Classification results, including accuracy, precision, recall, and F1-score, were recorded.
    • A confusion matrix was generated to visualize the performance of the model.

    2
    MACHINE LEARNING REPORT

    Test code

    6. Results:
    Column1 Column2 Column3
    0.1609211 0.2218517
    4 5 1
    0.3160854 0.0333267
    4 5 1
    0.9698728 0.1341516
    1 8 1
    0.4147555 0.1811637
    6 9 2
    0.8644938 0.2013803
    3 9 2
    0.0812164 0.0894070
    6 1 3
    0.7291456 0.1434445
    8 1 3

    3
    MACHINE LEARNING REPORT

    0.1609211 0.2218517
    4 5 1
    0.7997218 0.1026130
    1 2 1
    0.6233333 0.1857759
    3 9 2
    0.3895901
    2 0.1651969 2
    0.0812164 0.0894070
    6 1 3
    0.7291456 0.1434445
    8 1 3
    0.7263806 0.1935324
    7 1 4
    0.1721317
    0.5487426 7 4
    0.3315323 0.1462842
    7 4 4

    7. Conclusion:
    In conclusion, this task successfully classified images of mobile phones into specified categories
    using MATLAB. The model's performance during testing is promising, with room for
    enhancement, particularly in recognizing keypad phones.

    8. Future Work:
    Future work may include dataset expansion, model fine-tuning, and exploration of deep learning
    techniques for improved classification accuracy.

    9. Test results:

    4
    MACHINE LEARNING REPORT

    5
    MACHINE LEARNING REPORT

    References:
    • IMAGE CLASSIFICATION LINK

    • CODE SOURCE

    You might also like