img_tools.py 11.0 KB
Newer Older
L
LDOUBLEV 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
#Licensed under the Apache License, Version 2.0 (the "License");
#you may not use this file except in compliance with the License.
#You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
#Unless required by applicable law or agreed to in writing, software
#distributed under the License is distributed on an "AS IS" BASIS,
#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#See the License for the specific language governing permissions and
#limitations under the License.

import math
import cv2
import numpy as np
T
tink2123 已提交
18
import random
L
LDOUBLEV 已提交
19 20
from ppocr.utils.utility import initial_logger
logger = initial_logger()
L
LDOUBLEV 已提交
21 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


def get_bounding_box_rect(pos):
    left = min(pos[0])
    right = max(pos[0])
    top = min(pos[1])
    bottom = max(pos[1])
    return [left, top, right, bottom]


def resize_norm_img(img, image_shape):
    imgC, imgH, imgW = image_shape
    h = img.shape[0]
    w = img.shape[1]
    ratio = w / float(h)
    if math.ceil(imgH * ratio) > imgW:
        resized_w = imgW
    else:
        resized_w = int(math.ceil(imgH * ratio))
    resized_image = cv2.resize(img, (resized_w, imgH))
    resized_image = resized_image.astype('float32')
    if image_shape[0] == 1:
        resized_image = resized_image / 255
        resized_image = resized_image[np.newaxis, :]
    else:
        resized_image = resized_image.transpose((2, 0, 1)) / 255
    resized_image -= 0.5
    resized_image /= 0.5
    padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
    padding_im[:, :, 0:resized_w] = resized_image
    return padding_im


T
tink2123 已提交
54 55 56
def resize_norm_img_chinese(img, image_shape):
    imgC, imgH, imgW = image_shape
    # todo: change to 0 and modified image shape
T
tink2123 已提交
57
    max_wh_ratio = 0
T
tink2123 已提交
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
    h, w = img.shape[0], img.shape[1]
    ratio = w * 1.0 / h
    max_wh_ratio = max(max_wh_ratio, ratio)
    imgW = int(32 * max_wh_ratio)
    if math.ceil(imgH * ratio) > imgW:
        resized_w = imgW
    else:
        resized_w = int(math.ceil(imgH * ratio))
    resized_image = cv2.resize(img, (resized_w, imgH))
    resized_image = resized_image.astype('float32')
    if image_shape[0] == 1:
        resized_image = resized_image / 255
        resized_image = resized_image[np.newaxis, :]
    else:
        resized_image = resized_image.transpose((2, 0, 1)) / 255
    resized_image -= 0.5
    resized_image /= 0.5
    padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
    padding_im[:, :, 0:resized_w] = resized_image
    return padding_im


L
LDOUBLEV 已提交
80 81 82 83 84 85 86 87 88 89 90 91 92
def get_img_data(value):
    """get_img_data"""
    if not value:
        return None
    imgdata = np.frombuffer(value, dtype='uint8')
    if imgdata is None:
        return None
    imgori = cv2.imdecode(imgdata, 1)
    if imgori is None:
        return None
    return imgori


T
tink2123 已提交
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
def flag():
    """
    flag
    """
    return 1 if random.random() > 0.5000001 else -1


def cvtColor(img):
    """
    cvtColor
    """
    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    delta = 0.001 * random.random() * flag()
    hsv[:, :, 2] = hsv[:, :, 2] * (1 + delta)
    new_img = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)
    return new_img


def blur(img):
    """
    blur
    """
    h, w, _ = img.shape
    if h > 10 and w > 10:
        return cv2.GaussianBlur(img, (5, 5), 1)
    else:
        return img


T
tink2123 已提交
122
def jitter(img):
T
tink2123 已提交
123
    """
T
tink2123 已提交
124
    jitter
T
tink2123 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
    """
    w, h, _ = img.shape
    if h > 10 and w > 10:
        thres = min(w, h)
        s = int(random.random() * thres * 0.01)
        src_img = img.copy()
        for i in range(s):
            img[i:, i:, :] = src_img[:w - i, :h - i, :]
        return img
    else:
        return img


def add_gasuss_noise(image, mean=0, var=0.1):

    noise = np.random.normal(mean, var**0.5, image.shape)
    out = image + 0.5 * noise
    out = np.clip(out, 0, 255)
    out = np.uint8(out)
    return out


def get_crop(image):
    """
    random crop
    """
    h, w, _ = image.shape
    top_min = 1
    top_max = 8
    top_crop = int(random.randint(top_min, top_max))

    crop_img = image.copy()

    ratio = random.randint(0, 1)
    if ratio:
        crop_img = crop_img[top_crop:h, :, :]
    else:
        crop_img = crop_img[0:h - top_crop, :, :]
    return crop_img


class Config:
    """
    Config
    """

    def __init__(self, ):
        self.anglex = random.random() * 30
        self.angley = random.random() * 15
        self.anglez = random.random() * 10
        self.fov = 42
        self.r = 0
        self.shearx = random.random() * 0.3
        self.sheary = random.random() * 0.05
        self.borderMode = cv2.BORDER_REPLICATE

    def make(self, w, h, ang):
        """
        make
        """
        self.anglex = random.random() * 5 * flag()
        self.angley = random.random() * 5 * flag()
        self.anglez = -1 * random.random() * int(ang) * flag()
        self.fov = 42
        self.r = 0
        self.shearx = 0
        self.sheary = 0
        self.borderMode = cv2.BORDER_REPLICATE
        self.w = w
        self.h = h

        self.perspective = True
        self.crop = True
        self.affine = False
        self.reverse = True
        self.noise = True
T
tink2123 已提交
201
        self.jitter = True
T
tink2123 已提交
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
        self.blur = True
        self.color = True


def rad(x):
    """
    rad
    """
    return x * np.pi / 180


def get_warpR(config):
    """
    get_warpR
    """
    anglex, angley, anglez, fov, w, h, r = \
        config.anglex, config.angley, config.anglez, config.fov, config.w, config.h, config.r
    if w > 69 and w < 112:
        anglex = anglex * 1.5

    z = np.sqrt(w**2 + h**2) / 2 / np.tan(rad(fov / 2))
    # Homogeneous coordinate transformation matrix
    rx = np.array([[1, 0, 0, 0],
                   [0, np.cos(rad(anglex)), -np.sin(rad(anglex)), 0], [
                       0,
                       -np.sin(rad(anglex)),
                       np.cos(rad(anglex)),
                       0,
                   ], [0, 0, 0, 1]], np.float32)
    ry = np.array([[np.cos(rad(angley)), 0, np.sin(rad(angley)), 0],
                   [0, 1, 0, 0], [
                       -np.sin(rad(angley)),
                       0,
                       np.cos(rad(angley)),
                       0,
                   ], [0, 0, 0, 1]], np.float32)
    rz = np.array([[np.cos(rad(anglez)), np.sin(rad(anglez)), 0, 0],
                   [-np.sin(rad(anglez)), np.cos(rad(anglez)), 0, 0],
                   [0, 0, 1, 0], [0, 0, 0, 1]], np.float32)
    r = rx.dot(ry).dot(rz)
    # generate 4 points
    pcenter = np.array([h / 2, w / 2, 0, 0], np.float32)
    p1 = np.array([0, 0, 0, 0], np.float32) - pcenter
    p2 = np.array([w, 0, 0, 0], np.float32) - pcenter
    p3 = np.array([0, h, 0, 0], np.float32) - pcenter
    p4 = np.array([w, h, 0, 0], np.float32) - pcenter
    dst1 = r.dot(p1)
    dst2 = r.dot(p2)
    dst3 = r.dot(p3)
    dst4 = r.dot(p4)
    list_dst = [dst1, dst2, dst3, dst4]
    org = np.array([[0, 0], [w, 0], [0, h], [w, h]], np.float32)
    dst = np.zeros((4, 2), np.float32)
    # Project onto the image plane
    for i in range(4):
        dst[i, 0] = list_dst[i][0] * z / (z - list_dst[i][2]) + pcenter[0]
        dst[i, 1] = list_dst[i][1] * z / (z - list_dst[i][2]) + pcenter[1]
    warpR = cv2.getPerspectiveTransform(org, dst)

    dst1, dst2, dst3, dst4 = dst
    r1 = int(min(dst1[1], dst2[1]))
    r2 = int(max(dst3[1], dst4[1]))
    c1 = int(min(dst1[0], dst3[0]))
    c2 = int(max(dst2[0], dst4[0]))

    try:
        ratio = min(1.0 * h / (r2 - r1), 1.0 * w / (c2 - c1))

        dx = -c1
        dy = -r1
        T1 = np.float32([[1., 0, dx], [0, 1., dy], [0, 0, 1.0 / ratio]])
        ret = T1.dot(warpR)
    except:
        ratio = 1.0
        T1 = np.float32([[1., 0, 0], [0, 1., 0], [0, 0, 1.]])
        ret = T1
    return ret, (-r1, -c1), ratio, dst


def get_warpAffine(config):
    """
    get_warpAffine
    """
    anglez = config.anglez
    rz = np.array([[np.cos(rad(anglez)), np.sin(rad(anglez)), 0],
                   [-np.sin(rad(anglez)), np.cos(rad(anglez)), 0]], np.float32)
    return rz


def warp(img, ang):
    """
    warp
    """
    h, w, _ = img.shape
    config = Config()
    config.make(w, h, ang)
    new_img = img

    if config.perspective:
        tp = random.randint(1, 100)
        if tp >= 50:
            warpR, (r1, c1), ratio, dst = get_warpR(config)
            new_w = int(np.max(dst[:, 0])) - int(np.min(dst[:, 0]))
            new_img = cv2.warpPerspective(
                new_img,
                warpR, (int(new_w * ratio), h),
                borderMode=config.borderMode)
    if config.crop:
        img_height, img_width = img.shape[0:2]
        tp = random.randint(1, 100)
        if tp >= 50 and img_height >= 20 and img_width >= 20:
            new_img = get_crop(new_img)
    if config.affine:
        warpT = get_warpAffine(config)
        new_img = cv2.warpAffine(
            new_img, warpT, (w, h), borderMode=config.borderMode)
    if config.blur:
        tp = random.randint(1, 100)
        if tp >= 50:
            new_img = blur(new_img)
    if config.color:
        tp = random.randint(1, 100)
        if tp >= 50:
            new_img = cvtColor(new_img)
T
tink2123 已提交
326 327
    if config.jitter:
        new_img = jitter(new_img)
T
tink2123 已提交
328 329 330 331 332 333 334 335 336 337 338
    if config.noise:
        tp = random.randint(1, 100)
        if tp >= 50:
            new_img = add_gasuss_noise(new_img)
    if config.reverse:
        tp = random.randint(1, 100)
        if tp >= 50:
            new_img = 255 - new_img
    return new_img


L
LDOUBLEV 已提交
339 340 341 342 343
def process_image(img,
                  image_shape,
                  label=None,
                  char_ops=None,
                  loss_type=None,
T
tink2123 已提交
344
                  max_text_length=None,
T
tink2123 已提交
345
                  tps=None,
T
tink2123 已提交
346 347 348 349
                  infer_mode=False,
                  distort=False):
    if distort:
        img = warp(img, 10)
T
tink2123 已提交
350
    if infer_mode and char_ops.character_type == "ch" and not tps:
T
tink2123 已提交
351
        norm_img = resize_norm_img_chinese(img, image_shape)
T
tink2123 已提交
352 353 354
    else:
        norm_img = resize_norm_img(img, image_shape)

L
LDOUBLEV 已提交
355 356
    norm_img = norm_img[np.newaxis, :]
    if label is not None:
L
LDOUBLEV 已提交
357
        # char_num = char_ops.get_char_num()
L
LDOUBLEV 已提交
358 359
        text = char_ops.encode(label)
        if len(text) == 0 or len(text) > max_text_length:
L
LDOUBLEV 已提交
360 361
            logger.info(
                "Warning in ppocr/data/rec/img_tools.py:line106: Wrong data type."
T
tink2123 已提交
362
                "Excepted string with length between 1 and {}, but "
T
tink2123 已提交
363 364
                "got '{}'. Label is '{}'".format(max_text_length,
                                                 len(text), label))
L
LDOUBLEV 已提交
365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381
            return None
        else:
            if loss_type == "ctc":
                text = text.reshape(-1, 1)
                return (norm_img, text)
            elif loss_type == "attention":
                beg_flag_idx = char_ops.get_beg_end_flag_idx("beg")
                end_flag_idx = char_ops.get_beg_end_flag_idx("end")
                beg_text = np.append(beg_flag_idx, text)
                end_text = np.append(text, end_flag_idx)
                beg_text = beg_text.reshape(-1, 1)
                end_text = end_text.reshape(-1, 1)
                return (norm_img, beg_text, end_text)
            else:
                assert False, "Unsupport loss_type %s in process_image"\
                    % loss_type
    return (norm_img)