json2mask

tomni.transformers.json2mask(json_objects: list, img_shape: tuple, minimum_size_contours: int = 3) → numpy.ndarray

Convert a list of JSON objects in standard AxionBio format to a binary mask.

Parameters

• json_objects (list) – A list of JSON objects with annotations in the standard AxionBio format.

• img_shape (tuple) – The dimensions (height, width) of the mask.

• minimum_size_contours (int, optional) – The minimum number of points a contour should have to be included. Defaults to 3. Set to 0 to include all contours regardless of size.

Returns

A binary mask as a NumPy array.

Return type

np.ndarray

Raises

TypeError – If a JSON object of an unsupported type is encountered.

Example:

json_objects = [
    {
        "type": "polygon",
        "points": [
            {"x": 0, "y": 0},
            {"x": 0, "y": 5},
            {"x": 5, "y": 5},
            {"x": 5, "y": 0},
        ],
    }
]
img_shape = (10, 10)
minimum_size_contours = 3
result = json2mask(json_objects, img_shape, minimum_size_contours)
print(result)
[[1 1 1 1 1 0 0 0 0 0]
 [1 1 1 1 1 0 0 0 0 0]
 [1 1 1 1 1 0 0 0 0 0]
 [1 1 1 1 1 0 0 0 0 0]
 [1 1 1 1 1 0 0 0 0 0]
 [0 0 0 0 0 0 0 0 0 0]
 [0 0 0 0 0 0 0 0 0 0]
 [0 0 0 0 0 0 0 0 0 0]
 [0 0 0 0 0 0 0 0 0 0]
 [0 0 0 0 0 0 0 0 0 0]]