Skip to content

roi_handler

data.transform.roi.roi_handler

ROICalculator

Bases: ABC

ROI 좌표 계산을 위한 추상 클래스입니다.

set abstractmethod 

set(**kwargs) -> None
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
25
26
27
@abstractmethod
def set(self, **kwargs) -> None:
    pass

__call__ abstractmethod 

__call__(image: Union[Image, ndarray], get_intermediate_results: bool = False, warmup: bool = False, **data) -> Dict
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
29
30
31
32
33
34
35
36
37
@abstractmethod
def __call__(
    self,
    image: Union[Image.Image, np.ndarray],
    get_intermediate_results: bool = False,
    warmup: bool = False,
    **data,
) -> Dict:
    pass

RelativeBoxROI 

RelativeBoxROI(**kwargs)

Bases: ROICalculator

이미지 크기에 비례하는 상대좌표 박스로 ROI를 계산합니다.

Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
43
44
def __init__(self, **kwargs) -> None:
    self.set(**kwargs)

set 

set(left: float, top: float, right: float, bottom: float) -> None
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
46
47
48
49
50
51
52
53
def set(self, left: float, top: float, right: float, bottom: float) -> None:
    if not (0.0 <= left < right <= 1.0) or not (0.0 <= top < bottom <= 1.0):
        raise SimpleROIParameterValueError

    self.left = left
    self.top = top
    self.right = right
    self.bottom = bottom

__call__ 

__call__(image: Union[Image, ndarray], get_intermediate_results: bool = False, warmup: bool = False, **data) -> Dict
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
55
56
57
58
59
60
61
62
63
64
65
66
67
def __call__(
    self,
    image: Union[Image.Image, np.ndarray],
    get_intermediate_results: bool = False,
    warmup: bool = False,
    **data,
) -> Dict:
    w, h = read_image_size(image)
    left = int(self.left * w)
    right = max(int(self.right * w), left + 1)
    top = int(self.top * h)
    bottom = max(int(self.bottom * h), top + 1)
    return {"roi_coordinates": [left, top, right, bottom]}

PixelIntensityROI 

PixelIntensityROI(**kwargs)

Bases: ROICalculator

픽셀값이 intensity 범위에 들어오는 픽셀만 필터링한 뒤, 필터링 된 픽셀들의 컨투어를 찾고, 가장 면적이 큰 컨투어를 감싸는 최소 박스로 ROI를 계산합니다.

Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
74
75
def __init__(self, **kwargs) -> None:
    self.set(**kwargs)

set 

set(intensity: Union[Tuple[int, int], List[int]], expansion: int, inversion: bool, offset_left: float, offset_right: float, offset_top: float, offset_bottom: float) -> None
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
 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
def set(
    self,
    intensity: Union[Tuple[int, int], List[int]],
    expansion: int,
    inversion: bool,
    offset_left: float,
    offset_right: float,
    offset_top: float,
    offset_bottom: float,
) -> None:
    if (
        not len(intensity) == 2
        or not isinstance(intensity[0], int)
        or not isinstance(intensity[1], int)
        or not (0 <= intensity[0] < intensity[1] <= 255)
    ):
        raise AdvancedROIParameterValueError

    if not (-10 <= expansion <= 10):
        raise AdvancedROIParameterValueError

    for offset in (offset_left, offset_right, offset_top, offset_bottom):
        if not (0 <= offset <= 2):
            raise AdvancedROIParameterValueError
    if not (offset_left + offset_right >= 0.1) or not (offset_top + offset_bottom >= 0.1):
        raise AdvancedROIParameterValueError

    self.intensity = intensity
    self.expansion = expansion
    self.inversion = inversion
    self.offset_left = offset_left
    self.offset_right = offset_right
    self.offset_top = offset_top
    self.offset_bottom = offset_bottom

__call__ 

__call__(image: Union[Image, ndarray], get_intermediate_results: bool = False, warmup: bool = False, **data) -> Dict
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
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
172
173
174
175
176
177
def __call__(
    self,
    image: Union[Image.Image, np.ndarray],
    get_intermediate_results: bool = False,
    warmup: bool = False,
    **data,
) -> Dict:
    w, h = read_image_size(image)

    # PixelIntensityROI의 경우 input image size가 같더라도 output image size가 계속해서 달라질 수 있으며,
    # output image size의 최대 값은 input image size이기 때문에, warmup 시에 input image size를 return 함.
    if warmup:
        output = {"roi_coordinates": [0, 0, w, h]}
        return output

    # 후속 연산을 위해 grayscale numpy array 이미지로 변환
    filtered_image = to_numpy(image, copy=False)
    filtered_image = convert_image_mode(filtered_image, "L", copy=False)

    # intensity 범위에 들어오는 픽셀을 찾고, 해당 픽셀들을 expand & inverse
    filtered_image = cv2.inRange(filtered_image, lowerb=self.intensity[0], upperb=self.intensity[1])

    expansion_kernel = cv2.getStructuringElement(shape=cv2.MORPH_RECT, ksize=(3, 3), anchor=(1, 1))
    if self.expansion > 0:
        filtered_image = cv2.dilate(
            filtered_image, kernel=expansion_kernel, anchor=(-1, -1), iterations=2 * self.expansion
        )
    elif self.expansion < 0:
        filtered_image = cv2.erode(
            filtered_image, kernel=expansion_kernel, anchor=(-1, -1), iterations=2 * self.expansion
        )

    if self.inversion:
        filtered_image = cv2.bitwise_not(filtered_image)

    contours, _ = cv2.findContours(
        filtered_image, mode=cv2.RETR_LIST, method=cv2.CHAIN_APPROX_SIMPLE
    )
    if contours:
        # contour 중 면적 가장 큰 것 선택 & bounding box 계산
        contour_areas = list(map(cv2.contourArea, contours))
        max_area_contour = contours[np.argmax(contour_areas)]
        left, top, roi_width, roi_height = cv2.boundingRect(max_area_contour)

        # bounding box에 offset 적용 & 이미지 내부로 clip
        roi_center_x = left + (roi_width / 2)
        roi_center_y = top + (roi_height / 2)

        roi_left = roi_center_x - (self.offset_left * roi_width / 2)
        roi_right = roi_center_x + (self.offset_right * roi_width / 2)
        roi_top = roi_center_y - (self.offset_top * roi_height / 2)
        roi_bottom = roi_center_y + (self.offset_bottom * roi_height / 2)

        roi_left = int(np.clip(roi_left, 0, w - 1))
        roi_right = int(np.clip(roi_right, roi_left + 1, w))
        roi_top = int(np.clip(roi_top, 0, h - 1))
        roi_bottom = int(np.clip(roi_bottom, roi_top + 1, h))

        roi_coordinates = [roi_left, roi_top, roi_right, roi_bottom]
    else:
        roi_coordinates = [0, 0, w, h]

    output = {"roi_coordinates": roi_coordinates}
    if get_intermediate_results:
        output["filtered_image"] = filtered_image // 255
    return output

AutoRelativeBoxROI 

AutoRelativeBoxROI(padding: str = 'medium')

Bases: RelativeBoxROI

RelativeBoxROI class with automatic coordinate calculation.

Monostate pattern applied to prevent ROI coordinate mismatch between train ~ validation dataset.

Attributes:

  • left (float) –

    ROI coordinates.

  • top (float) –

    ROI coordinates.

  • right (float) –

    ROI coordinates.

  • bottom (float) –

    ROI coordinates.

  • is_ready (bol) –

    Whether auto ROI coordinates is set.

  • image_hw (Optional[List[int]]) –

    dataset image size.

  • discard_outer_polygons (bool) –

    Flag for discarding polygons outside of current ROI region.

  • expand_ratio –

    Ratio for expanding ROI region. Larger value means more padding.

Example 
# in dataset building...
@property
def files(self):
    return self._files

@files.setter
def files(self, value):
    self._files = value

    if isinstance(self.transform.roi_handler.roi_calculator, AutoRelativeBoxROI):
        self.transform.roi_handler.roi_calculator.autoupdate_roi_coordinate(self)
                                                                          # self is dataset
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
230
231
232
233
234
235
236
def __init__(self, padding: str = "medium"):
    self.__dict__ = self.__shared_state

    if padding not in self.REGION_EXPAND_RATIO.keys():
        raise AutoROIParameterValueError(f"AutoROI mode {padding} not available.")

    self.expand_ratio = self.REGION_EXPAND_RATIO[padding]

__shared_state class-attribute instance-attribute 

__shared_state = {'_is_ready': False, '_image_hw': None, '_left': -1.0, '_top': -1.0, '_right': -1.0, '_bottom': -1.0}

REGION_EXPAND_RATIO class-attribute instance-attribute 

REGION_EXPAND_RATIO = {'small': 0.05, 'medium': 0.1, 'large': 0.2}

__dict__ instance-attribute 

__dict__ = __shared_state

expand_ratio instance-attribute 

expand_ratio = REGION_EXPAND_RATIO[padding]

is_ready property writable 

is_ready

image_hw property writable 

image_hw

left property writable 

left

top property writable 

top

right property writable 

right

bottom property writable 

bottom

_check_auto_roi_is_ready 

_check_auto_roi_is_ready(function)
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
246
247
248
249
250
251
252
253
254
255
def _check_auto_roi_is_ready(function):
    def wrapper(self, *args, **kwargs):
        if self.is_ready:
            return function(self, *args, **kwargs)
        else:
            raise AutoROIParameterRuntimeError(
                "AutoROI not avaliable. Check log and dataset config."
            )

    return wrapper

__call__ 

__call__(*args, **kwargs)
Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
257
258
259
@_check_auto_roi_is_ready
def __call__(self, *args, **kwargs):
    return super().__call__(*args, **kwargs)

autoupdate_roi_coordinate 

autoupdate_roi_coordinate(dataset: Dataset) -> bool

Automatically update ROI coordinate using dataset information.

Returns success flag.

Source code in SaigeToolkit/data/transform/roi/roi_calculator.py 
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
def autoupdate_roi_coordinate(self, dataset: Dataset) -> bool:
    """Automatically update ROI coordinate using dataset information.

    Returns success flag.
    """

    # XXX: only called once
    if self.is_ready:
        logger.info("ROI coordinate already set. Update only once")
        return True

    marginal_label_region_xyxy = np.array([np.inf, np.inf, 0, 0])

    for data_idx in range(len(dataset)):
        file = dataset.files[data_idx]
        data_dict = dataset.load_image(file)
        data_dict.update(dataset.load_label(file))

        data_image: Union[Image.Image, np.ndarray] = data_dict["image"]
        current_img_hw = list(read_image_size(data_image))[::-1]

        if self.image_hw:
            if self.image_hw != current_img_hw:
                logger.warn("Variation in image size detected.. autoROI update aborted.")
                logger.warn(
                    f"Expected image size: {self.image_hw} / Given image size: {current_img_hw}"
                )
                return False

        self.image_hw = current_img_hw

        for polygon in data_dict["polygons"]:
            x_min, x_max = np.min(polygon[:, 0]), np.max(polygon[:, 0])
            y_min, y_max = np.min(polygon[:, 1]), np.max(polygon[:, 1])

            if x_min < marginal_label_region_xyxy[0]:
                marginal_label_region_xyxy[0] = x_min

            if y_min < marginal_label_region_xyxy[1]:
                marginal_label_region_xyxy[1] = y_min

            if x_max > marginal_label_region_xyxy[2]:
                marginal_label_region_xyxy[2] = x_max

            if y_max > marginal_label_region_xyxy[3]:
                marginal_label_region_xyxy[3] = y_max

    if not _check_region_xyxy_is_valid(marginal_label_region_xyxy):
        logger.warning(
            "AutoROI setting update failed. Needs at least one training data & valid polygon."
        )
        return False

    marginal_label_region_xyxy = _expand_region_xyxy(marginal_label_region_xyxy, self.expand_ratio)
    marginal_label_region_xyxy = _fit_region_into_img_size(
        marginal_label_region_xyxy,
        self.image_hw,
    )

    self.left = marginal_label_region_xyxy[0] / self.image_hw[1]
    self.top = marginal_label_region_xyxy[1] / self.image_hw[0]
    self.right = marginal_label_region_xyxy[2] / self.image_hw[1]
    self.bottom = marginal_label_region_xyxy[3] / self.image_hw[0]

    self.is_ready = True
    marginal_label_region_ratio = [self.left, self.top, self.right, self.bottom]
    logger.info(f"AutoROI setting success. ROI coordinates: {marginal_label_region_ratio}")

    return True

ROIHandler 

ROIHandler(**kwargs)

ROI 기능을 수행합니다. 이미지에 대한 ROI 좌표를 계산해 크롭하고, 크롭된 이미지에 blind_mask를 적용해 마스크 영역의 픽셀 값을 0으로 치환합니다.

Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
27
28
def __init__(self, **kwargs) -> None:
    self.set(**kwargs)

roi_calculator_types class-attribute instance-attribute 

roi_calculator_types = {'simple': RelativeBoxROI, 'advanced': PixelIntensityROI, 'auto': AutoRelativeBoxROI}

roi_calculator instance-attribute 

roi_calculator: ROICalculator

set 

set(mode: str, blind_mask: Union[None, ndarray, str], image_only: bool = False, discard_outer_polygons: bool = False, det_blind_mask_threshold: float = 0.5, **kwargs)
Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
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
def set(
    self,
    mode: str,
    blind_mask: Union[None, np.ndarray, str],
    image_only: bool = False,
    discard_outer_polygons: bool = False,
    det_blind_mask_threshold: float = 0.5,
    **kwargs,
):
    if mode not in self.roi_calculator_types:
        raise ROIModeError

    # mode 변경된 경우 roi_calculator 인스턴스 새로 생성, 그렇지 않은 경우 set 호출
    if not hasattr(self, "mode") or self.mode != mode:
        self.mode = mode
        self.roi_calculator = self.roi_calculator_types[mode](**kwargs)
    else:
        self.roi_calculator.set(**kwargs)

    if isinstance(blind_mask, str):
        blind_mask = np.array(Image.open(blind_mask))
    if blind_mask is not None and (blind_mask.dtype != np.uint8 or blind_mask.ndim != 2):
        raise ROIBlindMaskValueError
    self.blind_mask = blind_mask

    self.image_only = image_only

    self.discard_outer_polygons = discard_outer_polygons

    self.det_blind_mask_threshold = det_blind_mask_threshold

apply_crop 

apply_crop(image: Union[Image, ndarray, List[Union[Image, ndarray]]], return_revert_params: bool = False, warmup: bool = False, **data) -> Union[Dict, Tuple[Dict, Dict]]
Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
 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
def apply_crop(
    self,
    image: Union[Image.Image, np.ndarray, List[Union[Image.Image, np.ndarray]]],
    return_revert_params: bool = False,
    warmup: bool = False,
    **data,
) -> Union[Dict, Tuple[Dict, Dict]]:
    multipage = isinstance(image, list)

    roi_info = self.roi_calculator(
        image=image[0] if multipage else image,
        get_intermediate_results=False,
        warmup=warmup,
        **data,
    )
    roi_coordinates = roi_info["roi_coordinates"]  # [left, top, right, bottom]

    if multipage:
        image_size_before_roi = read_image_size(image[0])
        cropped_image = [crop(image_i, roi_coordinates) for image_i in image]
        image_size_after_roi = read_image_size(cropped_image[0])
    else:
        image_size_before_roi = read_image_size(image)
        cropped_image = crop(image, roi_coordinates)
        image_size_after_roi = read_image_size(cropped_image)

    data["image"] = cropped_image

    revert_params = {
        "image_size_before_roi": image_size_before_roi,
        "roi_coordinates": roi_coordinates,
        "image_size_after_roi": image_size_after_roi,
    }

    if self.image_only:
        return (data, revert_params) if return_revert_params else data

    # 라벨 크롭 & 마스킹
    if "mask" in data:
        data["mask"] = crop(data["mask"], roi_coordinates)

    if "bboxes" in data:
        data["bboxes"] = crop_box(data["bboxes"], roi_coordinates)

    if "polygons" in data:
        # NOTE: polygons에는 blind_mask가 적용되지 않습니다.
        new_polygons = []
        new_data = {key: [] for key in ["strings", "ignore"] if key in data}
        # TODO: add any keys to be updated which should have same length with polygons.

        for idx, polygon in enumerate(data["polygons"]):
            if self.discard_outer_polygons and not self._check_polygon_within_box(
                polygon, roi_coordinates
            ):
                continue

            new_polygons.append(polygon)
            for k, v in new_data.items():
                v.append(data[k][idx])

        new_polygons = translate_polygon(
            polygons=new_polygons,
            offset=roi_coordinates[:2],
        )

        data.update({"polygons": new_polygons, **new_data})

    return (data, revert_params) if return_revert_params else data

apply_mask 

apply_mask(image: Union[Image, ndarray, List], **data)
Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
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
172
173
174
175
176
177
178
def apply_mask(
    self,
    image: Union[Image.Image, np.ndarray, List],
    **data,
):
    if self.blind_mask is None:
        data["image"] = image
        return data

    multipage = isinstance(image, List)

    # cv2 resize: 약간 부정확하지만 빠름. 여기서는 아주 정확할 필요없음.
    image_size = read_image_size(image[0] if multipage else image)
    blind_mask = cv2.resize(self.blind_mask, dsize=image_size, interpolation=cv2.INTER_NEAREST)
    bool_mask = blind_mask > 0

    if multipage:
        data["image"] = [fill_pixels_with_mask(image_i, bool_mask, value=0) for image_i in image]
    else:
        data["image"] = fill_pixels_with_mask(image, bool_mask, value=0)

    if self.image_only:
        return data

    # 라벨 크롭 & 마스킹
    if "mask" in data:
        data["mask"] = fill_pixels_with_mask(data["mask"], bool_mask, value=0)

    if "bboxes" in data:
        indices_alive = []

        if len(data["bboxes"]):
            xyxy_bboxes = data["bboxes"].convert_coordinate("xyxy")

            for i, bbox in enumerate(xyxy_bboxes):
                x0, y0, x1, y1 = bbox

                label_area = (x1 - x0) * (y1 - y0)
                overlapping_area = np.sum(blind_mask[int(y0) : int(y1), int(x0) : int(x1)])

                if overlapping_area / label_area < self.det_blind_mask_threshold:
                    indices_alive.append(i)

        data["bboxes"] = data["bboxes"][indices_alive]

        if "labels" in data:
            data["labels"] = data["labels"][indices_alive]

    return data

__call__ 

__call__(return_revert_params: bool = False, warmup: bool = False, **data) -> Union[Dict, Tuple[Dict, Dict]]
Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def __call__(
    self,
    return_revert_params: bool = False,
    warmup: bool = False,
    **data,
) -> Union[Dict, Tuple[Dict, Dict]]:
    if return_revert_params:
        data, revert_params = self.apply_crop(return_revert_params=True, warmup=warmup, **data)
        data = self.apply_mask(**data)
        return data, revert_params
    else:
        data = self.apply_crop(return_revert_params=False, warmup=warmup, **data)
        data = self.apply_mask(**data)
        return data

_check_polygon_within_box 

_check_polygon_within_box(polygon: List[List[float]], roi_coordinates: List[int]) -> bool
Source code in SaigeToolkit/data/transform/roi/roi_handler.py 
195
196
197
198
199
200
201
202
203
204
205
206
207
208
def _check_polygon_within_box(self, polygon: List[List[float]], roi_coordinates: List[int]) -> bool:
    left, top, right, bottom = roi_coordinates

    def check_x_cord(p):
        return p >= left and p < right

    def check_y_cord(p):
        return p >= top and p < bottom

    def check_point_within_box(point_xy):
        x, y = point_xy
        return check_x_cord(x) and check_y_cord(y)

    return all(check_point_within_box(p) for p in polygon)

crop_box 

crop_box(bboxes: BBoxesType, cropping_box: Union[ndarray, List[int]]) -> BBoxesType

bbox crop. An image is cropped at (new_left, new_top, new_right, new_bottom)

Source code in SaigeToolkit/data/transform/box_function.py 
75
76
77
78
79
80
81
82
83
84
@preserve_coordinates
def crop_box(bboxes: BBoxesType, cropping_box: Union[np.ndarray, List[int]]) -> BBoxesType:
    """bbox crop. An image is cropped at (new_left, new_top, new_right, new_bottom)"""
    dtype = bboxes.dtype
    new_left, new_top, new_right, new_bottom = map(round, cropping_box)
    new_h = new_bottom - new_top
    new_bboxes = bboxes - (new_left, new_top, new_left, new_top)
    new_bboxes[:, [0, 1]] = np.maximum(new_bboxes[:, [0, 1]], 0)
    new_bboxes[:, [2, 3]] = np.minimum(new_bboxes[:, [2, 3]], (new_right - new_left, new_h))
    return new_bboxes.astype(dtype)

translate_polygon 

translate_polygon(polygons: PolygonType, offset: Tuple[int]) -> PolygonType

Translate polyfon from [(x1, y1), ... ] to [(x1 - x_offset), (y1 - y_offset), ...]

Source code in SaigeToolkit/data/transform/polygon_function.py 
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
def translate_polygon(
    polygons: PolygonType,
    offset: Tuple[int],
) -> PolygonType:
    """Translate polyfon from [(x1, y1), ... ] to [(x1 - x_offset), (y1 - y_offset), ...]"""
    if len(polygons) == 0:
        return polygons

    if offset[0] == 0 and offset[1] == 0:
        return polygons

    dtype = polygons[0].dtype

    x_offset, y_offset = np.array(offset).astype(dtype)

    new_polygons = deepcopy(polygons)

    for polygon in new_polygons:
        polygon[:, 0] -= x_offset
        polygon[:, 1] -= y_offset

    return new_polygons

crop 

crop(image: Union[Image, Tensor, ndarray], coordinates: Union[List[int], Tuple[int, int, int, int]]) -> Union[Image, Tensor, ndarray]

이미지의 coordinates 좌표영역을 크롭합니다. coordinates가 이미지를 벗어나는 경우 zero padding 합니다.

Parameters:

  • image (Union[Image, Tensor, ndarray]) –

    image

  • coordinates (Union[List[int], Tuple[int, int, int, int]]) –

    [left, top, right, bottom]

Returns:

  • Union[Image, Tensor, ndarray] –

    Union[Image.Image, torch.Tensor, np.ndarray]: cropped image

Source code in SaigeToolkit/data/transform/image_function.py 
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
def crop(
    image: Union[Image.Image, torch.Tensor, np.ndarray],
    coordinates: Union[List[int], Tuple[int, int, int, int]],
) -> Union[Image.Image, torch.Tensor, np.ndarray]:
    """이미지의 coordinates 좌표영역을 크롭합니다. coordinates가 이미지를 벗어나는 경우 zero padding 합니다.

    Args:
        image (Union[Image.Image, torch.Tensor, np.ndarray]): image
        coordinates (Union[List[int], Tuple[int, int, int, int]]): [left, top, right, bottom]

    Returns:
        Union[Image.Image, torch.Tensor, np.ndarray]: cropped image
    """
    if isinstance(image, Image.Image):
        return image.crop(coordinates)
    else:
        left, top, right, bottom = coordinates
        image_w, image_h = read_image_size(image)
        cropped_shape = (bottom - top, right - left)
        if image.ndim == 3:
            cropped_shape = (*cropped_shape, image.shape[2])
        if isinstance(image, torch.Tensor):
            cropped_image = torch.zeros(*cropped_shape, dtype=image.dtype, device=image.device)
        else:
            cropped_image = np.zeros(cropped_shape, dtype=image.dtype)
        cropped_image[
            np.clip(0, top, bottom) - top : np.clip(image_h, top, bottom) - top,
            np.clip(0, left, right) - left : np.clip(image_w, left, right) - left,
        ] = image[
            np.clip(top, 0, image_h) : np.clip(bottom, 0, image_h),
            np.clip(left, 0, image_w) : np.clip(right, 0, image_w),
        ]
        return cropped_image

read_image_size 

read_image_size(image: Union[Image, Tensor, ndarray]) -> ImageSizeType

image size: (W, H)

Source code in SaigeToolkit/data/transform/image_function.py 
11
12
13
14
15
16
17
18
19
20
def read_image_size(image: Union[Image.Image, torch.Tensor, np.ndarray]) -> ImageSizeType:
    """image size: (W, H)"""
    if isinstance(image, Image.Image):
        return image.size
    elif isinstance(image, torch.Tensor) and image.ndim in (2, 3, 4):  # HW, CHW, BCHW
        return (image.shape[-1], image.shape[-2])
    elif isinstance(image, np.ndarray) and image.ndim in (2, 3):  # HW, HWC
        return (image.shape[1], image.shape[0])
    else:
        raise NotImplementedError

fill_pixels_with_mask 

fill_pixels_with_mask(image: Union[Image, ndarray], bool_mask: ndarray, value: Union[int, float] = 0) -> Union[Image, ndarray]

image 중 bool_mask=True인 픽셀들을 value로 채웁니다.

Parameters:

  • image (Union[Image, ndarray]) –

    image (HW or HWC)

  • bool_mask (ndarray) –

    boolean mask (HW)

  • value (Union[int, float], default: 0 ) –

    . Defaults to 0.

Returns:

  • Union[Image, ndarray] –

    Union[Image.Image, np.ndarray]: 결과 이미지

Note
  • image가 Image.Image인 경우, 결과 이미지도 Image.Image로 반환합니다.
  • image의 값이 inplace로 변경됩니다. 값이 변경되지 않길 원한다면, copy를 해주세요.
Source code in SaigeToolkit/data/transform/image_function.py 
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
def fill_pixels_with_mask(
    image: Union[Image.Image, np.ndarray],
    bool_mask: np.ndarray,
    value: Union[int, float] = 0,
) -> Union[Image.Image, np.ndarray]:
    """image 중 bool_mask=True인 픽셀들을 value로 채웁니다.

    Args:
        image (Union[Image.Image, np.ndarray]): image (HW or HWC)
        bool_mask (np.ndarray): boolean mask (HW)
        value (Union[int, float], optional): . Defaults to 0.

    Returns:
        Union[Image.Image, np.ndarray]: 결과 이미지

    Note:
        - image가 Image.Image인 경우, 결과 이미지도 Image.Image로 반환합니다.
        - image의 값이 inplace로 변경됩니다. 값이 변경되지 않길 원한다면, copy를 해주세요.
    """
    is_pil = isinstance(image, Image.Image)
    image = np.asarray(image)

    assert image.ndim in [2, 3] and image.shape[:2] == bool_mask.shape  # HW or HWC

    if image.ndim > bool_mask.ndim:  # max ndim difference is 1
        bool_mask = np.expand_dims(bool_mask, axis=-1)

    image = np.where(bool_mask, value, image)

    if is_pil:
        image = Image.fromarray(image)

    return image