TexTeller/texteller/paddleocr/utility.py

# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# 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 argparse
import os
import sys
import functools
import logging
import cv2
import numpy as np
import PIL
from PIL import Image, ImageDraw, ImageFont
import math
import random


def str2bool(v):
    return v.lower() in ("true", "yes", "t", "y", "1")


def str2int_tuple(v):
    return tuple([int(i.strip()) for i in v.split(",")])


def init_args():
    parser = argparse.ArgumentParser()
    # params for prediction engine
    parser.add_argument("--use_gpu", type=str2bool, default=True)
    parser.add_argument("--use_xpu", type=str2bool, default=False)
    parser.add_argument("--use_npu", type=str2bool, default=False)
    parser.add_argument("--use_mlu", type=str2bool, default=False)
    parser.add_argument("--ir_optim", type=str2bool, default=True)
    parser.add_argument("--use_tensorrt", type=str2bool, default=False)
    parser.add_argument("--min_subgraph_size", type=int, default=15)
    parser.add_argument("--precision", type=str, default="fp32")
    parser.add_argument("--gpu_mem", type=int, default=500)
    parser.add_argument("--gpu_id", type=int, default=0)

    # params for text detector
    parser.add_argument("--image_dir", type=str)
    parser.add_argument("--page_num", type=int, default=0)
    parser.add_argument("--det_algorithm", type=str, default="DB")
    parser.add_argument("--det_model_dir", type=str)
    parser.add_argument("--det_limit_side_len", type=float, default=960)
    parser.add_argument("--det_limit_type", type=str, default="max")
    parser.add_argument("--det_box_type", type=str, default="quad")

    # DB parmas
    parser.add_argument("--det_db_thresh", type=float, default=0.3)
    parser.add_argument("--det_db_box_thresh", type=float, default=0.6)
    parser.add_argument("--det_db_unclip_ratio", type=float, default=1.5)
    parser.add_argument("--max_batch_size", type=int, default=10)
    parser.add_argument("--use_dilation", type=str2bool, default=False)
    parser.add_argument("--det_db_score_mode", type=str, default="fast")

    # EAST parmas
    parser.add_argument("--det_east_score_thresh", type=float, default=0.8)
    parser.add_argument("--det_east_cover_thresh", type=float, default=0.1)
    parser.add_argument("--det_east_nms_thresh", type=float, default=0.2)

    # SAST parmas
    parser.add_argument("--det_sast_score_thresh", type=float, default=0.5)
    parser.add_argument("--det_sast_nms_thresh", type=float, default=0.2)

    # PSE parmas
    parser.add_argument("--det_pse_thresh", type=float, default=0)
    parser.add_argument("--det_pse_box_thresh", type=float, default=0.85)
    parser.add_argument("--det_pse_min_area", type=float, default=16)
    parser.add_argument("--det_pse_scale", type=int, default=1)

    # FCE parmas
    parser.add_argument("--scales", type=list, default=[8, 16, 32])
    parser.add_argument("--alpha", type=float, default=1.0)
    parser.add_argument("--beta", type=float, default=1.0)
    parser.add_argument("--fourier_degree", type=int, default=5)

    # params for text recognizer
    parser.add_argument("--rec_algorithm", type=str, default="SVTR_LCNet")
    parser.add_argument("--rec_model_dir", type=str)
    parser.add_argument("--rec_image_inverse", type=str2bool, default=True)
    parser.add_argument("--rec_image_shape", type=str, default="3, 48, 320")
    parser.add_argument("--rec_batch_num", type=int, default=6)
    parser.add_argument("--max_text_length", type=int, default=25)
    parser.add_argument("--rec_char_dict_path", type=str, default="./ppocr_keys_v1.txt")
    parser.add_argument("--use_space_char", type=str2bool, default=True)
    parser.add_argument("--vis_font_path", type=str, default="./doc/fonts/simfang.ttf")
    parser.add_argument("--drop_score", type=float, default=0.5)

    # params for e2e
    parser.add_argument("--e2e_algorithm", type=str, default="PGNet")
    parser.add_argument("--e2e_model_dir", type=str)
    parser.add_argument("--e2e_limit_side_len", type=float, default=768)
    parser.add_argument("--e2e_limit_type", type=str, default="max")

    # PGNet parmas
    parser.add_argument("--e2e_pgnet_score_thresh", type=float, default=0.5)
    parser.add_argument("--e2e_char_dict_path", type=str, default="./ppocr/utils/ic15_dict.txt")
    parser.add_argument("--e2e_pgnet_valid_set", type=str, default="totaltext")
    parser.add_argument("--e2e_pgnet_mode", type=str, default="fast")

    # params for text classifier
    parser.add_argument("--use_angle_cls", type=str2bool, default=False)
    parser.add_argument("--cls_model_dir", type=str)
    parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
    parser.add_argument("--label_list", type=list, default=["0", "180"])
    parser.add_argument("--cls_batch_num", type=int, default=6)
    parser.add_argument("--cls_thresh", type=float, default=0.9)

    parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
    parser.add_argument("--cpu_threads", type=int, default=10)
    parser.add_argument("--use_pdserving", type=str2bool, default=False)
    parser.add_argument("--warmup", type=str2bool, default=False)

    # SR parmas
    parser.add_argument("--sr_model_dir", type=str)
    parser.add_argument("--sr_image_shape", type=str, default="3, 32, 128")
    parser.add_argument("--sr_batch_num", type=int, default=1)

    #
    parser.add_argument("--draw_img_save_dir", type=str, default="./inference_results")
    parser.add_argument("--save_crop_res", type=str2bool, default=False)
    parser.add_argument("--crop_res_save_dir", type=str, default="./output")

    # multi-process
    parser.add_argument("--use_mp", type=str2bool, default=False)
    parser.add_argument("--total_process_num", type=int, default=1)
    parser.add_argument("--process_id", type=int, default=0)

    parser.add_argument("--benchmark", type=str2bool, default=False)
    parser.add_argument("--save_log_path", type=str, default="./log_output/")

    parser.add_argument("--show_log", type=str2bool, default=True)
    parser.add_argument("--use_onnx", type=str2bool, default=False)

    # extended function
    parser.add_argument(
        "--return_word_box",
        type=str2bool,
        default=False,
        help="Whether return the bbox of each word (split by space) or chinese character. Only used in ppstructure for layout recovery",
    )

    return parser


def parse_args():
    parser = init_args()
    return parser.parse_args([])


def create_predictor(args, mode, logger):
    if mode == "det":
        model_dir = args.det_model_dir
    elif mode == "cls":
        model_dir = args.cls_model_dir
    elif mode == "rec":
        model_dir = args.rec_model_dir
    elif mode == "table":
        model_dir = args.table_model_dir
    elif mode == "ser":
        model_dir = args.ser_model_dir
    elif mode == "re":
        model_dir = args.re_model_dir
    elif mode == "sr":
        model_dir = args.sr_model_dir
    elif mode == "layout":
        model_dir = args.layout_model_dir
    else:
        model_dir = args.e2e_model_dir

    if model_dir is None:
        logger.info("not find {} model file path {}".format(mode, model_dir))
        sys.exit(0)
    assert args.use_onnx

    import onnxruntime as ort

    model_file_path = model_dir
    if not os.path.exists(model_file_path):
        raise ValueError("not find model file path {}".format(model_file_path))
    if args.use_gpu:
        sess = ort.InferenceSession(model_file_path, providers=["CUDAExecutionProvider"])
    else:
        sess = ort.InferenceSession(model_file_path)
    return sess, sess.get_inputs()[0], None, None


def get_output_tensors(args, mode, predictor):
    output_names = predictor.get_output_names()
    output_tensors = []
    if mode == "rec" and args.rec_algorithm in ["CRNN", "SVTR_LCNet", "SVTR_HGNet"]:
        output_name = "softmax_0.tmp_0"
        if output_name in output_names:
            return [predictor.get_output_handle(output_name)]
        else:
            for output_name in output_names:
                output_tensor = predictor.get_output_handle(output_name)
                output_tensors.append(output_tensor)
    else:
        for output_name in output_names:
            output_tensor = predictor.get_output_handle(output_name)
            output_tensors.append(output_tensor)
    return output_tensors


def draw_e2e_res(dt_boxes, strs, img_path):
    src_im = cv2.imread(img_path)
    for box, str in zip(dt_boxes, strs):
        box = box.astype(np.int32).reshape((-1, 1, 2))
        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
        cv2.putText(
            src_im,
            str,
            org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
            fontFace=cv2.FONT_HERSHEY_COMPLEX,
            fontScale=0.7,
            color=(0, 255, 0),
            thickness=1,
        )
    return src_im


def draw_text_det_res(dt_boxes, img):
    for box in dt_boxes:
        box = np.array(box).astype(np.int32).reshape(-1, 2)
        cv2.polylines(img, [box], True, color=(255, 255, 0), thickness=2)
    return img


def resize_img(img, input_size=600):
    """
    resize img and limit the longest side of the image to input_size
    """
    img = np.array(img)
    im_shape = img.shape
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(input_size) / float(im_size_max)
    img = cv2.resize(img, None, None, fx=im_scale, fy=im_scale)
    return img


def draw_ocr(
    image,
    boxes,
    txts=None,
    scores=None,
    drop_score=0.5,
    font_path="./doc/fonts/simfang.ttf",
):
    """
    Visualize the results of OCR detection and recognition
    args:
        image(Image|array): RGB image
        boxes(list): boxes with shape(N, 4, 2)
        txts(list): the texts
        scores(list): txxs corresponding scores
        drop_score(float): only scores greater than drop_threshold will be visualized
        font_path: the path of font which is used to draw text
    return(array):
        the visualized img
    """
    if scores is None:
        scores = [1] * len(boxes)
    box_num = len(boxes)
    for i in range(box_num):
        if scores is not None and (scores[i] < drop_score or math.isnan(scores[i])):
            continue
        box = np.reshape(np.array(boxes[i]), [-1, 1, 2]).astype(np.int64)
        image = cv2.polylines(np.array(image), [box], True, (255, 0, 0), 2)
    if txts is not None:
        img = np.array(resize_img(image, input_size=600))
        txt_img = text_visual(
            txts,
            scores,
            img_h=img.shape[0],
            img_w=600,
            threshold=drop_score,
            font_path=font_path,
        )
        img = np.concatenate([np.array(img), np.array(txt_img)], axis=1)
        return img
    return image


def draw_ocr_box_txt(
    image,
    boxes,
    txts=None,
    scores=None,
    drop_score=0.5,
    font_path="./doc/fonts/simfang.ttf",
):
    h, w = image.height, image.width
    img_left = image.copy()
    img_right = np.ones((h, w, 3), dtype=np.uint8) * 255
    random.seed(0)

    draw_left = ImageDraw.Draw(img_left)
    if txts is None or len(txts) != len(boxes):
        txts = [None] * len(boxes)
    for idx, (box, txt) in enumerate(zip(boxes, txts)):
        if scores is not None and scores[idx] < drop_score:
            continue
        color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
        draw_left.polygon(box, fill=color)
        img_right_text = draw_box_txt_fine((w, h), box, txt, font_path)
        pts = np.array(box, np.int32).reshape((-1, 1, 2))
        cv2.polylines(img_right_text, [pts], True, color, 1)
        img_right = cv2.bitwise_and(img_right, img_right_text)
    img_left = Image.blend(image, img_left, 0.5)
    img_show = Image.new("RGB", (w * 2, h), (255, 255, 255))
    img_show.paste(img_left, (0, 0, w, h))
    img_show.paste(Image.fromarray(img_right), (w, 0, w * 2, h))
    return np.array(img_show)


def draw_box_txt_fine(img_size, box, txt, font_path="./doc/fonts/simfang.ttf"):
    box_height = int(math.sqrt((box[0][0] - box[3][0]) ** 2 + (box[0][1] - box[3][1]) ** 2))
    box_width = int(math.sqrt((box[0][0] - box[1][0]) ** 2 + (box[0][1] - box[1][1]) ** 2))

    if box_height > 2 * box_width and box_height > 30:
        img_text = Image.new("RGB", (box_height, box_width), (255, 255, 255))
        draw_text = ImageDraw.Draw(img_text)
        if txt:
            font = create_font(txt, (box_height, box_width), font_path)
            draw_text.text([0, 0], txt, fill=(0, 0, 0), font=font)
        img_text = img_text.transpose(Image.ROTATE_270)
    else:
        img_text = Image.new("RGB", (box_width, box_height), (255, 255, 255))
        draw_text = ImageDraw.Draw(img_text)
        if txt:
            font = create_font(txt, (box_width, box_height), font_path)
            draw_text.text([0, 0], txt, fill=(0, 0, 0), font=font)

    pts1 = np.float32([[0, 0], [box_width, 0], [box_width, box_height], [0, box_height]])
    pts2 = np.array(box, dtype=np.float32)
    M = cv2.getPerspectiveTransform(pts1, pts2)

    img_text = np.array(img_text, dtype=np.uint8)
    img_right_text = cv2.warpPerspective(
        img_text,
        M,
        img_size,
        flags=cv2.INTER_NEAREST,
        borderMode=cv2.BORDER_CONSTANT,
        borderValue=(255, 255, 255),
    )
    return img_right_text


def create_font(txt, sz, font_path="./doc/fonts/simfang.ttf"):
    font_size = int(sz[1] * 0.99)
    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
    if int(PIL.__version__.split(".")[0]) < 10:
        length = font.getsize(txt)[0]
    else:
        length = font.getlength(txt)

    if length > sz[0]:
        font_size = int(font_size * sz[0] / length)
        font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
    return font


def str_count(s):
    """
    Count the number of Chinese characters,
    a single English character and a single number
    equal to half the length of Chinese characters.
    args:
        s(string): the input of string
    return(int):
        the number of Chinese characters
    """
    import string

    count_zh = count_pu = 0
    s_len = len(s)
    en_dg_count = 0
    for c in s:
        if c in string.ascii_letters or c.isdigit() or c.isspace():
            en_dg_count += 1
        elif c.isalpha():
            count_zh += 1
        else:
            count_pu += 1
    return s_len - math.ceil(en_dg_count / 2)


def text_visual(texts, scores, img_h=400, img_w=600, threshold=0.0, font_path="./doc/simfang.ttf"):
    """
    create new blank img and draw txt on it
    args:
        texts(list): the text will be draw
        scores(list|None): corresponding score of each txt
        img_h(int): the height of blank img
        img_w(int): the width of blank img
        font_path: the path of font which is used to draw text
    return(array):
    """
    if scores is not None:
        assert len(texts) == len(scores), "The number of txts and corresponding scores must match"

    def create_blank_img():
        blank_img = np.ones(shape=[img_h, img_w], dtype=np.int8) * 255
        blank_img[:, img_w - 1 :] = 0
        blank_img = Image.fromarray(blank_img).convert("RGB")
        draw_txt = ImageDraw.Draw(blank_img)
        return blank_img, draw_txt

    blank_img, draw_txt = create_blank_img()

    font_size = 20
    txt_color = (0, 0, 0)
    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")

    gap = font_size + 5
    txt_img_list = []
    count, index = 1, 0
    for idx, txt in enumerate(texts):
        index += 1
        if scores[idx] < threshold or math.isnan(scores[idx]):
            index -= 1
            continue
        first_line = True
        while str_count(txt) >= img_w // font_size - 4:
            tmp = txt
            txt = tmp[: img_w // font_size - 4]
            if first_line:
                new_txt = str(index) + ": " + txt
                first_line = False
            else:
                new_txt = "    " + txt
            draw_txt.text((0, gap * count), new_txt, txt_color, font=font)
            txt = tmp[img_w // font_size - 4 :]
            if count >= img_h // gap - 1:
                txt_img_list.append(np.array(blank_img))
                blank_img, draw_txt = create_blank_img()
                count = 0
            count += 1
        if first_line:
            new_txt = str(index) + ": " + txt + "   " + "%.3f" % (scores[idx])
        else:
            new_txt = "  " + txt + "  " + "%.3f" % (scores[idx])
        draw_txt.text((0, gap * count), new_txt, txt_color, font=font)
        # whether add new blank img or not
        if count >= img_h // gap - 1 and idx + 1 < len(texts):
            txt_img_list.append(np.array(blank_img))
            blank_img, draw_txt = create_blank_img()
            count = 0
        count += 1
    txt_img_list.append(np.array(blank_img))
    if len(txt_img_list) == 1:
        blank_img = np.array(txt_img_list[0])
    else:
        blank_img = np.concatenate(txt_img_list, axis=1)
    return np.array(blank_img)


def base64_to_cv2(b64str):
    import base64

    data = base64.b64decode(b64str.encode("utf8"))
    data = np.frombuffer(data, np.uint8)
    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
    return data


def draw_boxes(image, boxes, scores=None, drop_score=0.5):
    if scores is None:
        scores = [1] * len(boxes)
    for box, score in zip(boxes, scores):
        if score < drop_score:
            continue
        box = np.reshape(np.array(box), [-1, 1, 2]).astype(np.int64)
        image = cv2.polylines(np.array(image), [box], True, (255, 0, 0), 2)
    return image


def get_rotate_crop_image(img, points):
    """
    img_height, img_width = img.shape[0:2]
    left = int(np.min(points[:, 0]))
    right = int(np.max(points[:, 0]))
    top = int(np.min(points[:, 1]))
    bottom = int(np.max(points[:, 1]))
    img_crop = img[top:bottom, left:right, :].copy()
    points[:, 0] = points[:, 0] - left
    points[:, 1] = points[:, 1] - top
    """
    assert len(points) == 4, "shape of points must be 4*2"
    img_crop_width = int(
        max(np.linalg.norm(points[0] - points[1]), np.linalg.norm(points[2] - points[3]))
    )
    img_crop_height = int(
        max(np.linalg.norm(points[0] - points[3]), np.linalg.norm(points[1] - points[2]))
    )
    pts_std = np.float32(
        [
            [0, 0],
            [img_crop_width, 0],
            [img_crop_width, img_crop_height],
            [0, img_crop_height],
        ]
    )
    M = cv2.getPerspectiveTransform(points, pts_std)
    dst_img = cv2.warpPerspective(
        img,
        M,
        (img_crop_width, img_crop_height),
        borderMode=cv2.BORDER_REPLICATE,
        flags=cv2.INTER_CUBIC,
    )
    dst_img_height, dst_img_width = dst_img.shape[0:2]
    if dst_img_height * 1.0 / dst_img_width >= 1.5:
        dst_img = np.rot90(dst_img)
    return dst_img


def get_minarea_rect_crop(img, points):
    bounding_box = cv2.minAreaRect(np.array(points).astype(np.int32))
    points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])

    index_a, index_b, index_c, index_d = 0, 1, 2, 3
    if points[1][1] > points[0][1]:
        index_a = 0
        index_d = 1
    else:
        index_a = 1
        index_d = 0
    if points[3][1] > points[2][1]:
        index_b = 2
        index_c = 3
    else:
        index_b = 3
        index_c = 2

    box = [points[index_a], points[index_b], points[index_c], points[index_d]]
    crop_img = get_rotate_crop_image(img, np.array(box))
    return crop_img


# def check_gpu(use_gpu):
#     if use_gpu and (
#         not paddle.is_compiled_with_cuda() or paddle.device.get_device() == "cpu"
#     ):
#         use_gpu = False
#     return use_gpu


def _check_image_file(path):
    img_end = {"jpg", "bmp", "png", "jpeg", "rgb", "tif", "tiff", "gif", "pdf"}
    return any([path.lower().endswith(e) for e in img_end])


def get_image_file_list(img_file, infer_list=None):
    imgs_lists = []
    if img_file is None or not os.path.exists(img_file):
        raise Exception("not found any img file in {}".format(img_file))

    if os.path.isfile(img_file) and _check_image_file(img_file):
        imgs_lists.append(img_file)
    elif os.path.isdir(img_file):
        for single_file in os.listdir(img_file):
            file_path = os.path.join(img_file, single_file)
            if os.path.isfile(file_path) and _check_image_file(file_path):
                imgs_lists.append(file_path)

    if len(imgs_lists) == 0:
        raise Exception("not found any img file in {}".format(img_file))
    imgs_lists = sorted(imgs_lists)
    return imgs_lists


logger_initialized = {}


@functools.lru_cache()
def get_logger(name="ppocr", log_file=None, log_level=logging.DEBUG):
    """Initialize and get a logger by name.
    If the logger has not been initialized, this method will initialize the
    logger by adding one or two handlers, otherwise the initialized logger will
    be directly returned. During initialization, a StreamHandler will always be
    added. If `log_file` is specified a FileHandler will also be added.
    Args:
        name (str): Logger name.
        log_file (str | None): The log filename. If specified, a FileHandler
            will be added to the logger.
        log_level (int): The logger level. Note that only the process of
            rank 0 is affected, and other processes will set the level to
            "Error" thus be silent most of the time.
    Returns:
        logging.Logger: The expected logger.
    """
    logger = logging.getLogger(name)
    if name in logger_initialized:
        return logger
    for logger_name in logger_initialized:
        if name.startswith(logger_name):
            return logger

    formatter = logging.Formatter(
        "[%(asctime)s] %(name)s %(levelname)s: %(message)s", datefmt="%Y/%m/%d %H:%M:%S"
    )

    stream_handler = logging.StreamHandler(stream=sys.stdout)
    stream_handler.setFormatter(formatter)
    logger.addHandler(stream_handler)
    logger_initialized[name] = True
    logger.propagate = False
    return logger


def get_rotate_crop_image(img, points):
    """
    img_height, img_width = img.shape[0:2]
    left = int(np.min(points[:, 0]))
    right = int(np.max(points[:, 0]))
    top = int(np.min(points[:, 1]))
    bottom = int(np.max(points[:, 1]))
    img_crop = img[top:bottom, left:right, :].copy()
    points[:, 0] = points[:, 0] - left
    points[:, 1] = points[:, 1] - top
    """
    assert len(points) == 4, "shape of points must be 4*2"
    img_crop_width = int(
        max(np.linalg.norm(points[0] - points[1]), np.linalg.norm(points[2] - points[3]))
    )
    img_crop_height = int(
        max(np.linalg.norm(points[0] - points[3]), np.linalg.norm(points[1] - points[2]))
    )
    pts_std = np.float32(
        [
            [0, 0],
            [img_crop_width, 0],
            [img_crop_width, img_crop_height],
            [0, img_crop_height],
        ]
    )
    M = cv2.getPerspectiveTransform(points, pts_std)
    dst_img = cv2.warpPerspective(
        img,
        M,
        (img_crop_width, img_crop_height),
        borderMode=cv2.BORDER_REPLICATE,
        flags=cv2.INTER_CUBIC,
    )
    dst_img_height, dst_img_width = dst_img.shape[0:2]
    if dst_img_height * 1.0 / dst_img_width >= 1.5:
        dst_img = np.rot90(dst_img)
    return dst_img


def get_minarea_rect_crop(img, points):
    bounding_box = cv2.minAreaRect(np.array(points).astype(np.int32))
    points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])

    index_a, index_b, index_c, index_d = 0, 1, 2, 3
    if points[1][1] > points[0][1]:
        index_a = 0
        index_d = 1
    else:
        index_a = 1
        index_d = 0
    if points[3][1] > points[2][1]:
        index_b = 2
        index_c = 3
    else:
        index_b = 3
        index_c = 2

    box = [points[index_a], points[index_b], points[index_c], points[index_d]]
    crop_img = get_rotate_crop_image(img, np.array(box))
    return crop_img


if __name__ == "__main__":
    pass