CASIA数据集转png HWDB2.0-2.2

https://nlpr.ia.ac.cn/databases/handwriting/Home.html

CASIA在线和离线中文手写数据库

https://nlpr.ia.ac.cn/databases/handwriting/Offline_database.html

CASIA-HWDB2.0-2.2

离线文本数据库是由孤立字符数据集的作者制作的。每人撰写了五页给定文本。由于数据丢失，缺少一位作者（编号 371）和四页内容。每一页都存储在以作者索引和页码命名的 *.dgrl 文件中。除灰度图像外，数据文件还包括文本行分割的基本事实和字符类别标签（GB 码）。(训练集和测试集的作者是互斥的)

Dataset	#writers	#pages	#lines	#character/#class	#out-of-class sample
HWDB2.0	419	2,092	20,495	538,868/1,222	1,106
HWDB2.1	300	1,500	17,292	429,553/2,310	172
HWDB2.2	300	1,499	14,443	380,993/1,331	581
Total	1,019	5,091	52,230	1,349,414/2,703	1,859

截图(使用https://nlpr.ia.ac.cn/databases/Download/DGRLView.exe查看)

使用准备

把原训练集和测试集的数据合并到一个文件夹里,再根据作者重新分配训练集和测试集,确保训练集中存在每一个作者的笔迹.还要把dgrl 转成 png.

使用dgrl 查看002-P18.dgrl 是正常的(不会出现上下行重叠)

使用代码导出 png 时,发生了重叠(每行的坐标和长宽使用的是文件里面解析的结果)

软件应该是进行了渲染的处理,比如正片叠底

这里使用简单的方法处理,记录每行添加进大图后的最下边的 y 值,这样虽然上下距离变远了但不影响使用.

007-P19

这里的白边切不掉

修改后的代码(参考https://blog.youkuaiyun.com/DaGongJiGuoMaLu09/article/details/107050519)

import os
import struct
from pathlib import Path

import cv2 as cv
import numpy as np
from tqdm import tqdm

#切割白边
def remove_white(image):
    # 将图像反相
    inverted_image = cv.bitwise_not(image)

    # 计算上下左右投影
    horizontal_projection = np.sum(inverted_image, axis=1)
    vertical_projection = np.sum(inverted_image, axis=0)


    # 找到非零元素的索引范围
    non_zero_horizontal = np.where(horizontal_projection > 0)
    non_zero_vertical = np.where(vertical_projection > 0)

    # 获取边界
    top = non_zero_horizontal[0][0]
    bottom = non_zero_horizontal[0][-1]
    left = non_zero_vertical[0][0]
    right = non_zero_vertical[0][-1]

    # 切割图像并返回
    cropped_image = image[top:bottom, left:right]
    return cropped_image

def read_from_dgrl(dgrl):
    if not os.path.exists(dgrl):
        print("DGRL not exists!")
        return


    # if(os.path.basename(dgrl)!="385-P20.dgrl"):
    #     return

    gray_output_dir = "Y:/RawData/CASIA-HWDB2-png/gray/test"
    binary_output_dir = "Y:/RawData/CASIA-HWDB2-png/binary/test"


    with open(dgrl, "rb") as f:
        # 读取表头尺寸
        header_size = np.fromfile(f, dtype="uint8", count=4)
        header_size = sum([j << (i * 8) for i, j in enumerate(header_size)])
        # print(header_size)

        # 读取表头剩下内容，提取 code_length
        header = np.fromfile(f, dtype="uint8", count=header_size - 4)
        code_length = sum([j << (i * 8) for i, j in enumerate(header[-4:-2])])
        # print(code_length)

        # 读取图像尺寸信息，提取图像中行数量
        image_record = np.fromfile(f, dtype="uint8", count=12)
        height = sum([j << (i * 8) for i, j in enumerate(image_record[:4])])
        width = sum([j << (i * 8) for i, j in enumerate(image_record[4:8])])
        line_num = sum([j << (i * 8) for i, j in enumerate(image_record[8:])])
        # print("图像尺寸:")
        # print(height, width, line_num)

        # 创建一个空白图像来存储所有行的图像
        big_image = np.zeros((height+3000, 9000), dtype=np.uint8)
        big_image.fill(255)

        now_x=0
        now_y=0

        # 读取每一行的信息
        for k in range(line_num):
            # print(k + 1)

            # 读取该行的字符数量
            char_num = np.fromfile(f, dtype="uint8", count=4)
            char_num = sum([j << (i * 8) for i, j in enumerate(char_num)])
            # print("字符数量:", char_num)

            # 读取该行的标注信息
            label = np.fromfile(f, dtype="uint8", count=code_length * char_num)
            label = [
                label[i] << (8 * (i % code_length))
                for i in range(code_length * char_num)
            ]
            label = [
                sum(label[i * code_length : (i + 1) * code_length])
                for i in range(char_num)
            ]
            label = [struct.pack("I", i).decode("gbk", "ignore")[0] for i in label]
            # print("合并前：", label)
            label = "".join(label)
            # 去掉不可见字符 \x00，这一步不加的话后面保存的内容会出现看不见的问题
            label = "".join(label.split(b"\x00".decode()))
            # print("合并后：", label)

            # 读取该行的位置和尺寸
            pos_size = np.fromfile(f, dtype="uint8", count=16)
            y = sum([j << (i * 8) for i, j in enumerate(pos_size[:4])])
            x = sum([j << (i * 8) for i, j in enumerate(pos_size[4:8])])
            h = sum([j << (i * 8) for i, j in enumerate(pos_size[8:12])])
            w = sum([j << (i * 8) for i, j in enumerate(pos_size[12:])])
            # print(x, y, w, h)

            
            # 读取该行的图片
            bitmap = np.fromfile(f, dtype="uint8", count=h * w)
            bitmap = np.array(bitmap).reshape(h, w)

            base_name = os.path.basename(dgrl)
            filename, _ = os.path.splitext(base_name)

            # 保存图片(每行的图片)
            bitmap=remove_white(bitmap)
            # image_file = os.path.join(gray_output_dir, filename + "_"+str(k)+".png")
            # cv.imwrite(image_file, bitmap)
            
            h, w = bitmap.shape[0], bitmap.shape[1]

            # if np.all(bitmap == 0) or np.all(bitmap == 255):
            #     pass
            
            # 将该行图像放入大图中的相应位置
            if(k==0):
                big_image[y : y + h, x : x + w] = bitmap[:h, :w]
                now_y=y+h
            else:
                # print(x+w)
                # print(big_image.shape[:2])
                # print(big_image[now_y : now_y + h, x : x + w].shape[:2])
                
                if(x<0):
                    x=abs(x)
                big_image[now_y : now_y + h, x : x + w] = bitmap[:h, :w]
                now_y=now_y + h

        cropped_image=remove_white(big_image)
        cropped_image_file = os.path.join(gray_output_dir, filename + ".png")
        cv.imwrite(cropped_image_file, cropped_image)
        
        # 使用大津法进行二值化处理
        _, binaryx_image =cv.threshold(cropped_image, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)

        # 将二值图像保存到文件中
        cv.imwrite(os.path.join(binary_output_dir, filename + ".png"), binaryx_image)


if __name__ == "__main__":
    dgrl_paths = Path("Y:/RawData/CASIA-HWDB2/test").iterdir()
    dgrl_paths = list(dgrl_paths)

    la=False
    for dgrl_path in tqdm(dgrl_paths):
        print(dgrl_path)
        
        # if(os.path.basename(dgrl_path)=="385-P20.dgrl"):
        #     la=True
        # if(la):
        #     read_from_dgrl(dgrl_path)
        
        read_from_dgrl(dgrl_path)

提取结果(保存灰度图和二值图)