Scribd Logo
Upload

Welcome to Scribd!

  • 2 views

    Bai04 KNN

    Uploaded by

    22520793
    CS231_bai04

    Copyright:

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

    Bai04 KNN

    Uploaded by

    22520793
    2 views87 pages
    CS231_bai04

    Original Title

    Bai04_KNN

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    CS231_bai04

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    2 views87 pages

    Bai04 KNN

    Uploaded by

    22520793
    CS231_bai04

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 87

    TRƯỜNG ĐẠI HỌC CÔNG NGHỆ THÔNG TIN

    KHOA KHOA HỌC MÁY TÍNH

    CS231. Nhập môn Thị giác máy tính

    Machine Learning Image


    Classification

    Mai Tiến Dũng


    Content

    1. Introduction to image classification


    2. Image classification with KNN
    3. Image feature

    2
    1. Introduction to Image Classification

    • What is image classification


    • Challenges of image classification

    3
    What is image classification

    • Process of taking an image or picture

    Cat

    98%

    4
    Use of image classification

    5
    Targets:

    6
    7
    8
    9
    10
    11
    12
    Challenges of image
    classification

    13
    Challenges: change in viewpoint

    14
    Challenges: Illumination

    15
    Challenges: deformation

    16
    Challenges: occlusion

    17
    Challenges: background clutter

    18
    Image Classification with KNN

    19
    Image Classification with KNN

    20
    Image Classification with KNN

    21
    Image Classification with KNN

    22
    Image Classification with KNN

    23
    Image Classification with KNN

    24
    Image Classification with KNN

    25
    Image Classification with KNN

    26
    27
    Image Classification with KNN

    28
    Image Classification with KNN

    29
    Image Classification with KNN

    30
    Image Classification with KNN

    31
    Image Classification with KNN

    32
    Image Classification with KNN

    33
    Image Classification with KNN

    34
    Image Classification with KNN

    35
    Image Classification with KNN

    36
    Image Classification with KNN

    37
    Image Classification with KNN

    38
    Image Classification with KNN

    39
    Image Classification with KNN

    40
    Image Classification with KNN

    41
    Image Classification with KNN

    42
    Image Classification with KNN

    43
    Image Classification with KNN

    44
    Image Classification with KNN

    45
    Image Classification with KNN

    46
    Image Classification with KNN

    47
    Image Classification with KNN

    48
    Image Classification with KNN

    49
    Image Classification with KNN

    Cat

    50
    Image Classification with KNN

    51
    Image Classification with KNN

    52
    Image Features

    53
    Image Features

    54
    Image Features

    55
    Image Features

    56
    Image Features

    57
    Image Features

    58
    Image Features

    59
    Image Features

    60
    Image Features

    61
    Image Features

    62
    Image Features

    63
    Image Features

    64
    Image Features

    65
    Image Features

    66
    Image Features

    67
    Image Features

    68
    Image Features

    69
    Image Features

    70
    Image Features

    71
    Image Features

    72
    Image Features

    73
    Image Features

    74
    Image Features

    75
    Image Features

    76
    Image Features

    77
    Image Features

    78
    Image Features

    79
    Tài liệu tham khảo

    • https://www.coursera.org/learn/introduction-
    computer-vision-watson-opencv

    80
    Thực hành

    81
    Yêu cầu

    • Phân lớp ảnh: dogs vs cats


    • Phương pháp: KNN
    • Features: histogram
    • Color: grayscale

    82
    Project structure

    CS231.
    ├──Dataset
    │ └──dogscats_small
    │ ├──train
    │ └──test
    ├──Baitap3
    │ └──MSSV.ipynb

    83
    Tính histogram cho ảnh

    #Hàm tính histogram

    def TinhHist(pathfilename):
    img = cv.imread(pathfilename,0)
    hist = cv.calcHist([img],[0],None,
    [256],[0,256])
    size = img.shape[0]*img.shape[1]
    hist = hist / size
    return hist
    84
    Code: gợi ý

    def ReadData(path_to_files):
    for file_name in os.listdir(path_to_files):
    # Lấy label của ảnh
    # -> Thêm vào danh sách labels
    # Tính đặc trưng của ảnh
    # -> Thêm vào danh sách features
    return features, labels

    85
    Code: gợi ý

    • os.listdir(path_to_files)  đọc tất cả file trong thư


    mục path_to_files

    • Sorted (list_files)  sắp xếp danh sách list_files


    theo thứ tự tăng dần

    86
    Code: gợi ý

    from sklearn.neighbors import KNeighborsClassifier

    ---
    label = imagePath.split(os.path.sep)[-1].split(".")[0]

    ----
    features = np.array(features)
    labels = np.array(labels)

    ---
    model = KNeighborsClassifier(n_neighbors=1)
    model.fit(features, labels)
    acc = model.score(test_features, test_labels)
    87

    You might also like