图像增强之字符区域检测

目录

1.水平翻转

2.垂直翻转

3.随机旋转

4. 改变图像的属性

---

1.水平翻转

(对图片和文本框进行水平翻转)

    def horizontal_flip(self, im: np.ndarray, text_polys: np.ndarray) -> tuple:
        """
        对图片和文本框进行水平翻转
        :param im: 图片
        :param text_polys: 文本框
        :return: 水平翻转之后的图片和文本框
        """
        flip_text_polys = text_polys.copy()
        flip_im = cv2.flip(im, 1)
        h, w, _ = flip_im.shape
        flip_text_polys[:, :, 0] = w - flip_text_polys[:, :, 0]
        return flip_im, flip_text_polys

2.垂直翻转

(对图片和文本框进行竖直翻转)

    def vertical_flip(self, im: np.ndarray, text_polys: np.ndarray) -> tuple:
        """
         对图片和文本框进行竖直翻转
        :param im: 图片
        :param text_polys: 文本框
        :return: 竖直翻转之后的图片和文本框
        """
        flip_text_polys = text_polys.copy()
        flip_im = cv2.flip(im, 0)
        h, w, _ = flip_im.shape
        flip_text_polys[:, :, 1] = h - flip_text_polys[:, :, 1]
        return flip_im, flip_text_polys

3.随机旋转

(从给定的角度中选择一个角度，对图片和文本框进行旋转)

    def random_rotate_img_bbox(self, img, text_polys, degrees: numbers.Number or list or tuple or np.ndarray,
                               same_size=False):
        """
        从给定的角度中选择一个角度，对图片和文本框进行旋转
        :param img: 图片
        :param text_polys: 文本框
        :param degrees: 角度，可以是一个数值或者list
        :param same_size: 是否保持和原图一样大
        :return: 旋转后的图片和角度
        """
        if isinstance(degrees, numbers.Number):
            if degrees < 0:
                raise ValueError("If degrees is a single number, it must be positive.")
            degrees = (-degrees, degrees)
        elif isinstance(degrees, list) or isinstance(degrees, tuple) or isinstance(degrees, np.ndarray):
            if len(degrees) != 2:
                raise ValueError("If degrees is a sequence, it must be of len 2.")
            degrees = degrees
        else:
            raise Exception('degrees must in Number or list or tuple or np.ndarray')
        # ---------------------- 旋转图像 ----------------------
        w = img.shape[1]
        h = img.shape[0]
        angle = np.random.uniform(degrees[0], degrees[1])

        if same_size:
            nw = w
            nh = h
        else:
            # 角度变弧度
            rangle = np.deg2rad(angle)
            # 计算旋转之后图像的w, h
            nw = (abs(np.sin(rangle) * h) + abs(np.cos(rangle) * w))
            nh = (abs(np.cos(rangle) * h) + abs(np.sin(rangle) * w))
        # 构造仿射矩阵
        rot_mat = cv2.getRotationMatrix2D((nw * 0.5, nh * 0.5), angle, 1)
        # 计算原图中心点到新图中心点的偏移量
        rot_move = np.dot(rot_mat, np.array([(nw - w) * 0.5, (nh - h) * 0.5, 0]))
        # 更新仿射矩阵
        rot_mat[0, 2] += rot_move[0]
        rot_mat[1, 2] += rot_move[1]
        # 仿射变换
        rot_img = cv2.warpAffine(img, rot_mat, (int(math.ceil(nw)), int(math.ceil(nh))), flags=cv2.INTER_LANCZOS4)

        # ---------------------- 矫正bbox坐标 ----------------------
        # rot_mat是最终的旋转矩阵
        # 获取原始bbox的四个中点，然后将这四个点转换到旋转后的坐标系下
        rot_text_polys = list()
        for bbox in text_polys:
            point1 = np.dot(rot_mat, np.array([bbox[0, 0], bbox[0, 1], 1]))
            point2 = np.dot(rot_mat, np.array([bbox[1, 0], bbox[1, 1], 1]))
            point3 = np.dot(rot_mat, np.array([bbox[2, 0], bbox[2, 1], 1]))
            point4 = np.dot(rot_mat, np.array([bbox[3, 0], bbox[3, 1], 1]))
            rot_text_polys.append([point1, point2, point3, point4])
        return rot_img, np.array(rot_text_polys, dtype=np.float32)

4. 改变图像的属性

亮度（brightness）、对比度（contrast）、饱和度（saturation）和色调（hue)

# 单独设置
# 随机改变图像的亮度
brightness_change = transforms.ColorJitter(brightness=0.5)
# 随机改变图像的色调
hue_change = transforms.ColorJitter(hue=0.5)
# 随机改变图像的对比度
contrast_change = transforms.ColorJitter(contrast=0.5)