Skip to content

Binarization & Thresholding Methods

Binarizer component

BinarizerImage

BinarizerImage class

Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
class BinarizerImage:
    """BinarizerImage class"""

    def __init__(self, base: BaseImage) -> None:
        self.base = base

    def threshold_simple(self, thresh: int) -> None:
        """Compute the image thesholded by a single value T.
        All pixels with value v <= T are turned black and those with value v > T are
        turned white.

        Args:
            thresh (int): value to separate the black from the white pixels.
        """
        self.base.as_grayscale()
        self.base.asarray = np.array((self.base.asarray > thresh) * 255, dtype=np.uint8)

    def threshold_adaptative(self) -> None:
        """Apply adaptive thresholding.
        This is a local thresholding method that computes the threshold for a pixel
        based on a small region around it.

        A gaussian blur is applied before for better thresholding results.
        See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

        As the input image must be a grayscale before applying any thresholding
        methods we convert the image to grayscale.
        """
        self.base.as_grayscale()
        binary = cv2.adaptiveThreshold(
            self.base.asarray,
            255,
            cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
            cv2.THRESH_BINARY,
            11,
            2,
        )
        self.base.asarray = binary

    def threshold_otsu(self) -> None:
        """Apply Ostu thresholding.
        This is a global thresholding method that automatically determines
        an optimal threshold value from the image histogram.

        Comes from the article "A Threshold Selection Method from Gray-Level
        Histograms" by Nobuyuki Otsu, 31 January 1979. Link to article:
        https://ieeexplore.ieee.org/document/4310076

        Consider applying a gaussian blur before for better thresholding results.
        See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

        As the input image must be a grayscale before applying any thresholding
        methods we convert the image to grayscale.
        """
        self.base.as_grayscale()
        _, img_thresholded = cv2.threshold(
            self.base.asarray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU
        )
        self.base.asarray = img_thresholded

    def threshold_sauvola(
        self, window_size: int = 15, k: float = 0.2, r: float = 128.0
    ) -> None:
        """Apply Sauvola thresholding.
        This is a local thresholding method that computes the threshold for a pixel
        based on a small region around it.

        Comes from the article "Adaptive Document Image Binarization" by
        J. Sauvola and M. Pietikainen. Link to article:
        https://www.researchgate.net/publication/3710586_Adaptive_Document_Binarization

        See https://scikit-image.org/docs/stable/auto_examples/segmentation/\
                plot_niblack_sauvola.html.

        As the input image must be a grayscale before applying any thresholding
        methods we convert the image to grayscale.

        Args:
            window_size (int, optional): sauvola window size to apply on the
                image. Defaults to 15.
            k (float, optional): sauvola k factor to apply to regulate the impact
                of the std. Defaults to 0.2.
            r (float, optional): sauvola r value. Defaults to 128.
        """
        self.base.as_grayscale()
        self.base.asarray = threshold_niblack_like(
            img=self.base.asarray, method="sauvola", window_size=window_size, k=k, r=r
        )[1]

    def threshold_niblack(self, window_size: int = 15, k: float = 0.2) -> None:
        """Apply Niblack thresholding.
        This is a local thresholding method that computes the threshold for a pixel
        based on a small region around it.

        See https://scikit-image.org/docs/stable/auto_examples/segmentation/\
                plot_niblack_sauvola.html

        As the input image must be a grayscale before applying any thresholding
        methods we convert the image to grayscale.

        Args:
            window_size (int, optional): apply on the
                image. Defaults to 15.
            k (float, optional): factor to apply to regulate the impact
                of the std. Defaults to 0.2.
        """
        self.base.as_grayscale()
        self.base.asarray = threshold_niblack_like(
            img=self.base.asarray, method="niblack", window_size=window_size, k=k
        )[1]

    def binary(self, method: BinarizationMethods = "sauvola") -> NDArray:
        """Binary representation of the image with values that can be only 0 or 1.
        The value 0 is now 0 and value of 255 are now 1. Black is 0 and white is 1.
        We can also talk about the mask of the image to refer to the binary
        representation of it.

        The sauvola is generally the best binarization method however it is
        way slower than the others methods. The adaptative or otsu method are the best
        method in terms of speed and quality.

        Args:
            method (str, optional): the binarization method to apply.
                Must be in ["adaptative", "otsu", "sauvola", "niblack", "nick", "wolf"].
                Defaults to "sauvola".

        Returns:
            NDArray: array where its inner values are 0 or 1
        """
        if method not in list(get_args(BinarizationMethods)):
            raise ValueError(
                f"Invalid binarization method {method}. "
                f"Must be in {BinarizationMethods}"
            )
        getattr(self, f"threshold_{method}")()
        return self.base.asarray_binary

    def binaryrev(self, method: BinarizationMethods = "sauvola") -> NDArray:
        """Reversed binary representation of the image.
        The value 0 is now 1 and value of 255 are now 0. Black is 1 and white is 0.
        This is why it is called the "binary rev" or "binary reversed".

        Args:
            method (str, optional): the binarization method to apply.
                Defaults to "adaptative".

        Returns:
            NDArray: array where its inner values are 0 or 1
        """
        return 1 - self.binary(method=method)

binary(method='sauvola')

Binary representation of the image with values that can be only 0 or 1. The value 0 is now 0 and value of 255 are now 1. Black is 0 and white is 1. We can also talk about the mask of the image to refer to the binary representation of it.

The sauvola is generally the best binarization method however it is way slower than the others methods. The adaptative or otsu method are the best method in terms of speed and quality.

Parameters:

Name Type Description Default
method str

the binarization method to apply. Must be in ["adaptative", "otsu", "sauvola", "niblack", "nick", "wolf"]. Defaults to "sauvola".

 'sauvola'

Returns:

Name Type Description
NDArray NDArray

array where its inner values are 0 or 1
Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
def binary(self, method: BinarizationMethods = "sauvola") -> NDArray:
    """Binary representation of the image with values that can be only 0 or 1.
    The value 0 is now 0 and value of 255 are now 1. Black is 0 and white is 1.
    We can also talk about the mask of the image to refer to the binary
    representation of it.

    The sauvola is generally the best binarization method however it is
    way slower than the others methods. The adaptative or otsu method are the best
    method in terms of speed and quality.

    Args:
        method (str, optional): the binarization method to apply.
            Must be in ["adaptative", "otsu", "sauvola", "niblack", "nick", "wolf"].
            Defaults to "sauvola".

    Returns:
        NDArray: array where its inner values are 0 or 1
    """
    if method not in list(get_args(BinarizationMethods)):
        raise ValueError(
            f"Invalid binarization method {method}. "
            f"Must be in {BinarizationMethods}"
        )
    getattr(self, f"threshold_{method}")()
    return self.base.asarray_binary

binaryrev(method='sauvola')

Reversed binary representation of the image. The value 0 is now 1 and value of 255 are now 0. Black is 1 and white is 0. This is why it is called the "binary rev" or "binary reversed".

Parameters:

Name Type Description Default
method str

the binarization method to apply. Defaults to "adaptative".

 'sauvola'

Returns:

Name Type Description
NDArray NDArray

array where its inner values are 0 or 1
Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
159
160
161
162
163
164
165
166
167
168
169
170
171
def binaryrev(self, method: BinarizationMethods = "sauvola") -> NDArray:
    """Reversed binary representation of the image.
    The value 0 is now 1 and value of 255 are now 0. Black is 1 and white is 0.
    This is why it is called the "binary rev" or "binary reversed".

    Args:
        method (str, optional): the binarization method to apply.
            Defaults to "adaptative".

    Returns:
        NDArray: array where its inner values are 0 or 1
    """
    return 1 - self.binary(method=method)

threshold_adaptative()

Apply adaptive thresholding. This is a local thresholding method that computes the threshold for a pixel based on a small region around it.

A gaussian blur is applied before for better thresholding results. See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

As the input image must be a grayscale before applying any thresholding methods we convert the image to grayscale.

Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
def threshold_adaptative(self) -> None:
    """Apply adaptive thresholding.
    This is a local thresholding method that computes the threshold for a pixel
    based on a small region around it.

    A gaussian blur is applied before for better thresholding results.
    See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

    As the input image must be a grayscale before applying any thresholding
    methods we convert the image to grayscale.
    """
    self.base.as_grayscale()
    binary = cv2.adaptiveThreshold(
        self.base.asarray,
        255,
        cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
        cv2.THRESH_BINARY,
        11,
        2,
    )
    self.base.asarray = binary

threshold_niblack(window_size=15, k=0.2)

Apply Niblack thresholding. This is a local thresholding method that computes the threshold for a pixel based on a small region around it.

See https://scikit-image.org/docs/stable/auto_examples/segmentation/ plot_niblack_sauvola.html

As the input image must be a grayscale before applying any thresholding methods we convert the image to grayscale.

Parameters:

Name Type Description Default
window_size int

apply on the image. Defaults to 15.

 15
k float

factor to apply to regulate the impact of the std. Defaults to 0.2.

 0.2
Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
def threshold_niblack(self, window_size: int = 15, k: float = 0.2) -> None:
    """Apply Niblack thresholding.
    This is a local thresholding method that computes the threshold for a pixel
    based on a small region around it.

    See https://scikit-image.org/docs/stable/auto_examples/segmentation/\
            plot_niblack_sauvola.html

    As the input image must be a grayscale before applying any thresholding
    methods we convert the image to grayscale.

    Args:
        window_size (int, optional): apply on the
            image. Defaults to 15.
        k (float, optional): factor to apply to regulate the impact
            of the std. Defaults to 0.2.
    """
    self.base.as_grayscale()
    self.base.asarray = threshold_niblack_like(
        img=self.base.asarray, method="niblack", window_size=window_size, k=k
    )[1]

threshold_otsu()

Apply Ostu thresholding. This is a global thresholding method that automatically determines an optimal threshold value from the image histogram.

Comes from the article "A Threshold Selection Method from Gray-Level Histograms" by Nobuyuki Otsu, 31 January 1979. Link to article: https://ieeexplore.ieee.org/document/4310076

Consider applying a gaussian blur before for better thresholding results. See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

As the input image must be a grayscale before applying any thresholding methods we convert the image to grayscale.

Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
def threshold_otsu(self) -> None:
    """Apply Ostu thresholding.
    This is a global thresholding method that automatically determines
    an optimal threshold value from the image histogram.

    Comes from the article "A Threshold Selection Method from Gray-Level
    Histograms" by Nobuyuki Otsu, 31 January 1979. Link to article:
    https://ieeexplore.ieee.org/document/4310076

    Consider applying a gaussian blur before for better thresholding results.
    See why in https://docs.opencv.org/4.x/d7/d4d/tutorial_py_thresholding.html.

    As the input image must be a grayscale before applying any thresholding
    methods we convert the image to grayscale.
    """
    self.base.as_grayscale()
    _, img_thresholded = cv2.threshold(
        self.base.asarray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU
    )
    self.base.asarray = img_thresholded

threshold_sauvola(window_size=15, k=0.2, r=128.0)

Apply Sauvola thresholding. This is a local thresholding method that computes the threshold for a pixel based on a small region around it.

Comes from the article "Adaptive Document Image Binarization" by J. Sauvola and M. Pietikainen. Link to article: https://www.researchgate.net/publication/3710586_Adaptive_Document_Binarization

See https://scikit-image.org/docs/stable/auto_examples/segmentation/ plot_niblack_sauvola.html.

As the input image must be a grayscale before applying any thresholding methods we convert the image to grayscale.

Parameters:

Name Type Description Default
window_size int

sauvola window size to apply on the image. Defaults to 15.

 15
k float

sauvola k factor to apply to regulate the impact of the std. Defaults to 0.2.

 0.2
r float

sauvola r value. Defaults to 128.

 128.0
Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
def threshold_sauvola(
    self, window_size: int = 15, k: float = 0.2, r: float = 128.0
) -> None:
    """Apply Sauvola thresholding.
    This is a local thresholding method that computes the threshold for a pixel
    based on a small region around it.

    Comes from the article "Adaptive Document Image Binarization" by
    J. Sauvola and M. Pietikainen. Link to article:
    https://www.researchgate.net/publication/3710586_Adaptive_Document_Binarization

    See https://scikit-image.org/docs/stable/auto_examples/segmentation/\
            plot_niblack_sauvola.html.

    As the input image must be a grayscale before applying any thresholding
    methods we convert the image to grayscale.

    Args:
        window_size (int, optional): sauvola window size to apply on the
            image. Defaults to 15.
        k (float, optional): sauvola k factor to apply to regulate the impact
            of the std. Defaults to 0.2.
        r (float, optional): sauvola r value. Defaults to 128.
    """
    self.base.as_grayscale()
    self.base.asarray = threshold_niblack_like(
        img=self.base.asarray, method="sauvola", window_size=window_size, k=k, r=r
    )[1]

threshold_simple(thresh)

Compute the image thesholded by a single value T. All pixels with value v <= T are turned black and those with value v > T are turned white.

Parameters:

Name Type Description Default
thresh int

value to separate the black from the white pixels.

 required
Source code in otary/image/components/transformer/components/binarizer/binarizer.py 
28
29
30
31
32
33
34
35
36
37
def threshold_simple(self, thresh: int) -> None:
    """Compute the image thesholded by a single value T.
    All pixels with value v <= T are turned black and those with value v > T are
    turned white.

    Args:
        thresh (int): value to separate the black from the white pixels.
    """
    self.base.as_grayscale()
    self.base.asarray = np.array((self.base.asarray > thresh) * 255, dtype=np.uint8)