# 失真






刚性变换： 只有物体的位置(平移变换)和朝向(旋转变换)发生改变，而形状不变，得到的变换称为刚性变换。刚性变换是最一般的变换。

使用透视变换，文字会扭曲失真。刚性变换就不会。

一些介绍： [https://blog.csdn.net/liuweiyuxiang/article/details/86510191](https://blog.csdn.net/liuweiyuxiang/article/details/86510191)

![在这里插入图片描述](/static/img/images/04473.png)

# Pillow的实现

创建一张空图写文字：

![在这里插入图片描述](/static/img/images/04474.png)

旋转了-30度：

![在这里插入图片描述](/static/img/images/04475.png)

将RGBA图像paste到大图中。

![在这里插入图片描述](/static/img/images/04476.png)

Python代码：

```python
from PIL import Image, ImageDraw, ImageFont
def draw_text_with_rotation(image, position, text, font_size, color, angle):
    draw = ImageDraw.Draw(image)
    font = ImageFont.truetype("STKAITI.TTF", font_size)
    width, height = draw.textsize(text, font=font)
    rotated_text = Image.new("RGBA", (width, height), (0, 0, 0, 0))
    text_draw = ImageDraw.Draw(rotated_text)
    text_draw.text((0, 0), text, font=font, fill=color)
    rotated_text.save("rotated_text1.png")
    rotated_text = rotated_text.rotate(-angle, resample=Image.BICUBIC, expand=True)
    rotated_text.save("rotated_text2.png")
    image.paste(rotated_text, position, rotated_text)
    rotated_text_width, rotated_text_height = rotated_text.size
    return rotated_text_width, rotated_text_height
# 创建一个空白图像
width, height = 800, 600
background_color = (255, 255, 255)  # 白色
image = Image.new("RGB", (width, height), background_color)
# 在大图中写入文本并旋转
text = "Hello, World!是吗可以的呀"
text_position = (200, 200)
text_font_size = 30
text_color = (0, 0, 0)  # 黑色
rotation_angle = -30
rotated_text_width, rotated_text_height = draw_text_with_rotation(image, text_position, text, text_font_size,
                                                                  text_color, rotation_angle)
# 画一个红色框框选上文字区域
draw = ImageDraw.Draw(image)
draw.rectangle((text_position[0], text_position[1], text_position[0] + rotated_text_width,
                text_position[1] + rotated_text_height), outline=(255, 0, 0))
# 保存图片
image.save("rotated_text3.png")
```

# Opencv的实现

## 不裁剪的旋转图像

参考imutils得到：

```python
import math
import cv2
import numpy as np
def rotate_bound2(image, angle):
    # grab the dimensions of the image and then determine the center
    # 抓取图像的尺寸，然后确定中心
    (h, w) = image.shape[:2]
    (cX, cY) = (w / 2, h / 2)
    # grab the rotation matrix (applying the negative of the angle to rotate clockwise), then grab the sine and cosine (i.e., the rotation components of the matrix)
    # 抓取旋转矩阵（应用角度的负数顺时针旋转），然后抓取正弦和余弦（即矩阵的旋转分量）
    M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
    cos = np.abs(M[0, 0])
    sin = np.abs(M[0, 1])
    # compute the new bounding dimensions of the image
    # 计算图像的新边界尺寸
    nW = int((h * sin) + (w * cos))
    nH = int((h * cos) + (w * sin))
    # adjust the rotation matrix to take into account translation
    # 调整旋转矩阵以考虑平移
    M[0, 2] += (nW / 2) - cX
    M[1, 2] += (nH / 2) - cY
    # perform the actual rotation and return the image
    # 执行实际旋转并返回图像
    return cv2.warpAffine(image, M, (nW, nH), flags=cv2.INTER_CUBIC)
def rotate_image(image, angle):
    angle = angle % 360.0
    if angle == 0:
        return image.copy()
    if angle == 180:
        return cv2.rotate(image, cv2.ROTATE_180)
    if angle == 90:
        return cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE)
    if angle == 270:
        return cv2.rotate(image, cv2.ROTATE_90_COUNTERCLOCKWISE)
    return rotate_bound2(image, angle)
# 读取RGBA
image = cv2.imread('rotated_text1.png', cv2.IMREAD_UNCHANGED)
# 对图像进行旋转并扩展
rotated_image = rotate_image(image, 45)
# SAVE
cv2.imwrite("rotated_text1_rotated.png", rotated_image)
```

![在这里插入图片描述](/static/img/images/04477.png)

## 旋转文字并贴图

```python
import math
import cv2
import numpy as np
def rotate_bound2(image, angle):
    # grab the dimensions of the image and then determine the center
    # 抓取图像的尺寸，然后确定中心
    (h, w) = image.shape[:2]
    (cX, cY) = (w / 2, h / 2)
    # grab the rotation matrix (applying the negative of the angle to rotate clockwise), then grab the sine and cosine (i.e., the rotation components of the matrix)
    # 抓取旋转矩阵（应用角度的负数顺时针旋转），然后抓取正弦和余弦（即矩阵的旋转分量）
    M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
    cos = np.abs(M[0, 0])
    sin = np.abs(M[0, 1])
    # compute the new bounding dimensions of the image
    # 计算图像的新边界尺寸
    nW = int((h * sin) + (w * cos))
    nH = int((h * cos) + (w * sin))
    # adjust the rotation matrix to take into account translation
    # 调整旋转矩阵以考虑平移
    M[0, 2] += (nW / 2) - cX
    M[1, 2] += (nH / 2) - cY
    # perform the actual rotation and return the image
    # 执行实际旋转并返回图像
    return cv2.warpAffine(image, M, (nW, nH), flags=cv2.INTER_CUBIC)
def rotate_image(image, angle):
    angle = angle % 360.0
    if angle == 0:
        return image.copy()
    if angle == 180:
        return cv2.rotate(image, cv2.ROTATE_180)
    if angle == 90:
        return cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE)
    if angle == 270:
        return cv2.rotate(image, cv2.ROTATE_90_COUNTERCLOCKWISE)
    return rotate_bound2(image, angle)
def draw_text_with_rotation(image, position, text, font_size, color, angle):
    # 定义字体样式
    font = cv2.FONT_HERSHEY_SIMPLEX
    thickness = 2
    # 获取文字的宽度和高度
    text_size, baseline = cv2.getTextSize(text, font, font_size, thickness)
    print(text_size, baseline)
    text_width, text_height = text_size
    # 灰度图上白纸黑字
    text_image = np.zeros((text_height + baseline, text_width, 1), np.uint8)
    cv2.putText(text_image, text, (0, text_height), font, font_size, (255,), thickness)  # top-left corner.
    # 灰度图给到透明通道上
    text_image2 = np.zeros((text_height + baseline, text_width, 4), np.uint8)
    text_image2[:, :, 3] = text_image[:, :, 0]
    text_image = text_image2
    cv2.imwrite("self1.png", text_image)
    rotated_text = rotate_image(text_image, angle)
    cv2.imwrite("self2.png", rotated_text)
    rotated_text_height, rotated_text_width = rotated_text.shape[:2]
    image[position[0]:position[0] + rotated_text_height, position[1]:position[1] + rotated_text_width] = rotated_text
    return rotated_text_width, rotated_text_height
# 创建一个空白图像
width, height = 800, 600
image = np.zeros((height, width, 4), np.uint8)
# 在大图中写入文本并旋转
text = "Hello, World"
text_position = (200, 200)
text_font_size = 1
text_color = (255, 255, 255)  # 黑色
rotation_angle = -30
rotated_text_width, rotated_text_height = draw_text_with_rotation(image, text_position, text, text_font_size,
                                                                  text_color, rotation_angle)
# 画一个红色框框选上文字区域
cv2.rectangle(image, (text_position[0], text_position[1]),
              (text_position[0] + rotated_text_width, text_position[1] + rotated_text_height), (0, 0, 255, 255), 2)
# 保存图片
cv2.imwrite("self3.png", image)
```

文字图：

![在这里插入图片描述](/static/img/images/04478.png)

旋转后：

![在这里插入图片描述](/static/img/images/04479.png)

贴图：

![在这里插入图片描述](/static/img/images/04480.png)




## C++的图片透视变换

```cpp
        // textImgMask的四个顶点
        std::vector<cv::Point> ptsSrc;
        ptsSrc.emplace_back(0, 0);
        ptsSrc.emplace_back(textImgMask.cols, 0);
        ptsSrc.emplace_back(textImgMask.cols, textImgMask.rows);
        ptsSrc.emplace_back(0, textImgMask.rows);
        // ptsImgText的四个顶点
        std::vector<cv::Point> ptsDst;
        ptsDst.emplace_back(ptsImgText[0]);
        ptsDst.emplace_back(ptsImgText[1]);
        ptsDst.emplace_back(ptsImgText[2]);
        ptsDst.emplace_back(ptsImgText[3]);
        // 计算透视变换矩阵
        cv::Mat homography = cv::findHomography(ptsSrc, ptsDst);
        // 透视变换到imgOutTmp
        cv::Mat imgOutTmp = cv::Mat::zeros(img.size(), CV_8UC3);
        cv::warpPerspective(textImgMask, imgOutTmp, homography, img.size());
        // 转到原图
        cv::Mat gray;
        cv::cvtColor(imgOutTmp, gray, cv::COLOR_BGR2GRAY);
        imgOut.setTo(cv::Scalar(textColors[i][2], textColors[i][1], textColors[i][0]), gray > 125);  // mask部分改色
```

【Opencv】PIL Opencv 向图片写入文字并旋转文字，Opencv图片旋转不截断，Opencv图片旋转不裁剪

版本不一样的时候，返回也不一样。





我使用opencv/4.5.5。

下图是使用minAreaRect判定的角度，可以看到，数值范围是[0,90]，看起来很离谱。

![在这里插入图片描述](/static/img/images/04636.jpeg)

画出这张图使用的程序如下：

C++
```cpp
int main() {
    std::string prefix1 =
        "/mnt/c/Users/dong.xie/Desktop/workcode/cpp_project/photo_translate/03implement/photo_translate/"
        "test_photo_translate/";
    // 写一段程序，显示opencv中的角度是怎么计算的
    // 构建一个全白色的4000*4000的图片
    cv::Mat img = cv::Mat::zeros(4000, 4000, CV_8UC3);
    img.setTo(cv::Scalar(114, 114, 114));
    // 遍历0度到360度
    for (int i = 0; i < 360; i = i + 10) {
        //(2000,2000)与(3200,2000)是一条直线，(2000,2000)是原点，不断旋转这条直线，看看旋转后的直线的角度是多少
        int p0x = 2000;
        int p0y = 2000;
        int p1x = 3200;
        int p1y = 2000;
        p1x = 1200 * std::cos(i * 3.1415926 / 180) + p0x;
        p1y = -1200 * std::sin(i * 3.1415926 / 180) + p0y;
        cv::Mat pts = (cv::Mat_<float>(4, 2) << p0x, p0y, p1x, p1y, p0x + 2, p0y + 2, p1x + 2, p1y + 2);
        // 绘制(p0x,p0y)与（p1x，p1y)这条直线
        cv::line(img, cv::Point2f(p0x, p0y), cv::Point2f(p1x, p1y), cv::Scalar(0, 0, 255), 2);
        cv::RotatedRect rect = cv::minAreaRect(pts);
        // 画出旋转后的直线
        cv::Point2f vertices[4];
        rect.points(vertices);
        for (int i = 0; i < 4; i++)
            cv::line(img, vertices[i], vertices[(i + 1) % 4], cv::Scalar(0, 0, 255), 2);
        // 显示旋转后的直线的角度
        cv::putText(img,
                    std::to_string(rect.angle).substr(0, 5),
                    cv::Point(p1x, p1y),
                    cv::FONT_HERSHEY_SIMPLEX,
                    2,
                    cv::Scalar(0, 255, 0),
                    2);
    }
    cv::imwrite(prefix1 + "test.jpg", img);
    return 0;
}
```

那么python中呢，如果版本是一样的，那么结果是一样的，如果版本不同，比如4.4，那么就不会是一样的结果。

```python
import cv2
import numpy as np
print(cv2.__version__)
img = np.zeros((4000, 4000, 3), np.uint8)
img[:] = 114
for i in range(0, 360, 10):
    p0x = 2000
    p0y = 2000
    p1x = 3200
    p1y = 2000
    p1x = 1200 * np.cos(i * np.pi / 180) + p0x
    p1y = -1200 * np.sin(i * np.pi / 180) + p0y
    pts = np.array([[p0x, p0y], [p1x, p1y], [p0x + 2, p0y + 2], [p1x + 2, p1y + 2]], np.float32)
    cv2.line(img, (int(p0x), int(p0y)), (int(p1x), int(p1y)), (0, 0, 255), 2)
    rect = cv2.minAreaRect(pts)
    box = cv2.boxPoints(rect)
    box = np.int0(box)
    cv2.drawContours(img, [box], 0, (0, 0, 255), 2)
    cv2.putText(img, str(rect[2])[0:5], (int(p1x), int(p1y)), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 2)
cv2.imwrite('test.jpg', img)
```

![在这里插入图片描述](/static/img/images/04637.jpeg)

C++的OpenCV中cv::minAreaRect的返回角度的数值范围是多少？

# 传统方法





程序
```python
import numpy as np
import cv2
def replaceZeroes(data):
    min_nonzero = min(data[np.nonzero(data)])
    data[data == 0] = min_nonzero
    return data
def SSR(src_img, size):
    L_blur = cv2.GaussianBlur(src_img, (size, size), 0)
    img = replaceZeroes(src_img)
    L_blur = replaceZeroes(L_blur)
    dst_Img = cv2.log(img / 255.0)
    dst_Lblur = cv2.log(L_blur / 255.0)
    dst_IxL = cv2.multiply(dst_Img, dst_Lblur)
    log_R = cv2.subtract(dst_Img, dst_IxL)
    dst_R = cv2.normalize(log_R, None, 0, 255, cv2.NORM_MINMAX)
    log_uint8 = cv2.convertScaleAbs(dst_R)
    return log_uint8
# 使用照片修复的办法来去掉图片中的文字
def remove_text1(path):
    size = 3
    src_img = cv2.imread(path)
    # # 膨胀图片
    # src_img = cv2.dilate(src_img, kernel=np.ones((3, 3), dtype=np.uint8), iterations=2)
    # 腐蚀图片
    # src_img = cv2.erode(src_img, kernel=np.ones((3, 3), dtype=np.uint8), iterations=2)
    b_gray, g_gray, r_gray = cv2.split(src_img)
    b_gray = SSR(b_gray, size)
    g_gray = SSR(g_gray, size)
    r_gray = SSR(r_gray, size)
    ssrimg = cv2.merge([b_gray, g_gray, r_gray])
    canny_img = cv2.Canny(ssrimg, 200, 150)
    k = np.ones((3, 3), np.uint8)
    mask = cv2.morphologyEx(canny_img, cv2.MORPH_CLOSE, k)  # 闭运算
    # 对mask进行膨胀
    # mask = cv2.dilate(mask, kernel=np.ones((3, 3), dtype=np.uint8), iterations=6)
    dst = cv2.inpaint(src_img, mask, 3, cv2.INPAINT_TELEA)
    # dst = cv2.inpaint(dst, mask, 3, cv2.INPAINT_TELEA)
    # 膨胀
    dst = cv2.dilate(dst, kernel=np.ones((3, 3), dtype=np.uint8), iterations=5)
    return dst
# 使用mask直接填充颜色的办法来去掉图片中的文字
def remove_text2(path):
    size = 3
    src_img = cv2.imread(path)
    # 腐蚀图片
    # src_img = cv2.erode(src_img, kernel=np.ones((3, 3), dtype=np.uint8), iterations=2)
    b_gray, g_gray, r_gray = cv2.split(src_img)
    b_gray = SSR(b_gray, size)
    g_gray = SSR(g_gray, size)
    r_gray = SSR(r_gray, size)
    ssrimg = cv2.merge([b_gray, g_gray, r_gray])
    canny_img = cv2.Canny(ssrimg, 200, 150)
    k = np.ones((3, 3), np.uint8)
    mask = cv2.morphologyEx(canny_img, cv2.MORPH_CLOSE, k)  # 闭运算
    # 保存mask为图片
    cv2.imwrite("mask.png", mask)
    # mask等于1的区域，用白色填充
    # dst = cv2.bitwise_and(src_img, src_img, mask=mask)
    src_img[mask == 255] = (255, 255, 255)
    # 膨胀
    src_img = cv2.dilate(src_img, kernel=np.ones((3, 3), dtype=np.uint8), iterations=5)
    return src_img
# 移除背景色，增强文字
def remove_ground(path):
    size = 3
    src_img = cv2.imread(path)
    b_gray, g_gray, r_gray = cv2.split(src_img)
    b_gray = SSR(b_gray, size)
    g_gray = SSR(g_gray, size)
    r_gray = SSR(r_gray, size)
    ssrimg = cv2.merge([b_gray, g_gray, r_gray])
    canny_img = cv2.Canny(ssrimg, 200, 150)
    k = np.ones((3, 3), np.uint8)
    mask = cv2.morphologyEx(canny_img, cv2.MORPH_CLOSE, k)  # 闭运算
    # mask等于1的区域，用白色填充
    dst = cv2.bitwise_and(src_img, src_img, mask=mask)
    dst[mask == 0] = (255, 255, 255)
    return dst
if __name__ == '__main__':
    imgPath = "papertext.jpg"
    dst = remove_text2(imgPath)
    cv2.imwrite("result.jpg", dst)
```

原图：

![在这里插入图片描述](/static/img/images/04728.jpeg)

找到文字部分：

![在这里插入图片描述](/static/img/images/04729.png)

去除文字：

![在这里插入图片描述](/static/img/images/04730.jpeg)

保留清晰文字：

![在这里插入图片描述](/static/img/images/04731.jpeg)

# 深度学习

1、

Self-Supervised Text Erasing with Controllable Image Synthesis 即STE ： 论文[https://arxiv.org/abs/2204.12743](https://arxiv.org/abs/2204.12743)。

2、

EnsNet ： [https://blog.csdn.net/u013554402/article/details/104494261](https://blog.csdn.net/u013554402/article/details/104494261)。

3、

[https://paperswithcode.com/paper/mtrnet-one-stage-mask-based-scene-text-eraser](https://paperswithcode.com/paper/mtrnet-one-stage-mask-based-scene-text-eraser)。

4、

[http://www.cjig.cn/html/jig/2022/4/20220420.htm](http://www.cjig.cn/html/jig/2022/4/20220420.htm)





# 译文回填

SickZil-Machine用于去除文本： [https://github.com/KUR-creative/SickZil-Machine](https://github.com/KUR-creative/SickZil-Machine)

lama-cleaner技术：  [https://github.com/Sanster/lama-cleaner](https://github.com/Sanster/lama-cleaner)

【OpenCV】【深度学习】去除图片文字；只保留图片文字；译文回填

原因是png图片里面的profile ，好像又听说高版本的png在做什么。






解决方式很简单，重写一下这个图。


下面程序会读取 r"/ssd/xd/datasets/multilabelsTask/"下面的所有jpg和png图，多进程方式地重写一下图片，注意，如果opencv打不开这个图，这个图会被删除：
```python
import multiprocessing
import os
import cv2
import numpy as np
def listPathAllfiles(dirname):
    result = []
    for maindir, subdir, file_name_list in os.walk(dirname):
        for filename in file_name_list:
            apath = os.path.join(maindir, filename)
            result.append(apath)
    return result
def overwrite(files1):
    for fname in files1:
        try:
            if fname.endswith(".jpg"):
                img = cv2.imdecode(np.fromfile(fname, dtype=np.uint8), 1)  # img是矩阵
                cv2.imencode('.jpg', img)[1].tofile(fname)
            elif fname.endswith(".png"):
                img = cv2.imdecode(np.fromfile(fname, dtype=np.uint8), 1)  # img是矩阵
                cv2.imencode('.png', img)[1].tofile(fname)
        except:
            os.remove(fname)
            print(fname)
if __name__ == '__main__':
    root = r"/ssd/xd/datasets/multilabelsTask/"
    files = listPathAllfiles(root)
    p = multiprocessing.Pool()  # 创建一个包含2个进程的进程池
    # split files to several parts
    for i in range(0, len(files), 10000):
        p.apply_async(func=overwrite, args=(files[i:i + 1000],))  # 往池子里加一个异步执行的子进城
    p.close()  # 等子进程执行完毕后关闭进程池
    p.join()  # 主进程等待
```

【opencv】【python】libpng warning: iCCP: known incorrect sRGB profile 解决

截图目标，分析目标的颜色直方图：





```python
import cv2
from matplotlib import pyplot as plt
def show_img(path):
    img = cv2.imread(path)
    b, g, r = img[:, :, 0], img[:, :, 1], img[:, :, 2]
    hist_b = cv2.calcHist([b], [0], None, [256], [0, 256])
    hist_g = cv2.calcHist([g], [0], None, [256], [0, 256])
    hist_r = cv2.calcHist([r], [0], None, [256], [0, 256])
    plt.figure(figsize=(10, 5))
    plt.subplot(121)
    plt.plot(hist_r, color='r', label="r")
    plt.plot(hist_g, color='g', label="g")
    plt.plot(hist_b, color='b', label="b")
    plt.legend()
    img2 = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    h, s, v = img2[:, :, 0], img2[:, :, 1], img2[:, :, 2]
    hist_h = cv2.calcHist([h], [0], None, [256], [0, 256])
    hist_s = cv2.calcHist([s], [0], None, [256], [0, 256])
    hist_v = cv2.calcHist([v], [0], None, [256], [0, 256])
    plt.subplot(122)
    plt.plot(hist_h, color='r', label="h")
    plt.plot(hist_s, color='g', label="s")
    plt.plot(hist_v, color='b', label="v")
    plt.legend()
    plt.show()
    return hist_r, hist_g, hist_b, hist_h, hist_s, hist_v
r, g, b, h, s, v = show_img("lanse.png")
```

![在这里插入图片描述](/static/img/images/00262.png)


```
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread("1111.jpg")
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
lower_red = np.array([115, 0, 160])
upper_red = np.array([140, 30, 190])
mask = cv2.inRange(hsv, lower_red, upper_red)
res = cv2.bitwise_and(img, img, mask=mask)
# cv2.imshow('img', img)
cv2.imshow('mask', mask)
cv2.imshow('res', res)
cv2.waitKey(0)
cv2.destroyAllWindows()
```

Opencv 颜色过滤 Python mask 选取颜色 颜色直方图

# 边缘检测





![在这里插入图片描述](/static/img/images/00263.jpeg)

拉普拉斯边缘分割：

![在这里插入图片描述](/static/img/images/00264.png)

sobel算子：

![在这里插入图片描述](/static/img/images/00265.png)

canny算子：

![在这里插入图片描述](/static/img/images/00266.png)

加了高斯模糊再用canny算子：

![在这里插入图片描述](/static/img/images/00267.png)






参考：

水文标尺识别opencv：[https://blog.csdn.net/sinat_28371057/article/details/109968240](https://blog.csdn.net/sinat_28371057/article/details/109968240)

边缘 图像分割： [https://www.jianshu.com/p/fb48de8120fd](https://www.jianshu.com/p/fb48de8120fd)

图像分割：[https://zhuanlan.zhihu.com/p/70758906](https://zhuanlan.zhihu.com/p/70758906)

水文标尺识别 深度学习 边缘检测 图像分割

修改video_path = 'test1.mp4' 这一句即可，源码地址：https://github.com/hongcyu/char_painting





```python
import cv2
from PIL import Image, ImageFont, ImageDraw
import os
from cv2 import VideoWriter, VideoWriter_fourcc, imread, resize
# =========================
# coding:UTF-8
# 视频转字符画含音频version-1
# 参考1：https://blog.csdn.net/mp624183768/article/details/81161260
# 参考2：https://blog.csdn.net/qq_42820064/article/details/90958577
# 参考3：https://blog.csdn.net/zj360202/article/details/79026891
# =========================
def get_char(r, g, b, alpha=256):
    ascii_char = list(r"#TONGHUIgogoggoWGPZ*@$C&998798213123123128?3345462I1>;\';][.../]'\]!:-;. ")
    # ascii_char = list("#RMNHQODBWGPZ*@$C&98?32I1>!:-;. ")
    # ascii_char = list("$@B%8&WM#*oahkbdpqwmZO0QLCJUYXzcvunxrjft/\|()1{}[]?-_+~<>i!lI;:oa+>!:+. ")
    if alpha == 0:
        return ''
    length = len(ascii_char)
    gray = int(0.2126 * r + 0.7152 * g + 0.0722 * b)
    unit = (256.0 + 1) / len(ascii_char)
    return ascii_char[int(gray / unit)]
# 将视频转换为图片 并进行计数，返回总共生成了多少张图片！
def video_to_pic(vp):
    # vp = cv2.VideoCapture(video_path)
    number = 0
    if vp.isOpened():
        r, frame = vp.read()
        if not os.path.exists('cache_pic'):
            os.mkdir('cache_pic')
        os.chdir('cache_pic')
    else:
        r = False
    while r:
        number += 1
        cv2.imwrite(str(number) + '.jpg', frame)
        r, frame = vp.read()
    print('\n由视频一共生成了{}张图片！'.format(number))
    os.chdir("..")
    return number
def img_to_char(image_path, raw_width, raw_height, task):
    width = int(raw_width / 6)
    height = int(raw_height / 15)
    im = Image.open(image_path).convert('RGB')  # 必须以RGB模式打开
    im = im.resize((width, height), Image.NEAREST)
    txt = ''
    color = []
    for i in range(height):
        for j in range(width):
            pixel = im.getpixel((j, i))
            color.append((pixel[0], pixel[1], pixel[2]))  # 将颜色加入进行索引
            if len(pixel) == 4:
                txt += get_char(pixel[0], pixel[1], pixel[2], pixel[3])
            else:
                txt += get_char(pixel[0], pixel[1], pixel[2])
        txt += '\n'
        color.append((255, 255, 255))
    im_txt = Image.new("RGB", (raw_width, raw_height), (255, 255, 255))
    dr = ImageDraw.Draw(im_txt)
    # font = ImageFont.truetype('consola.ttf', 10, encoding='unic') #改为这个字体会让图片比例改变
    font = ImageFont.load_default().font
    x, y = 0, 0
    font_w, font_h = font.getsize(txt[1])
    font_h *= 1.37  # 调整字体大小
    for i in range(len(txt)):
        if (txt[i] == '\n'):
            x += font_h
            y = -font_w
        dr.text((y, x), txt[i], fill=color[i])
        y += font_w
    os.chdir('cache_char')
    im_txt.save(str(task) + '.jpg')
    os.chdir("..")
    return 0
def star_to_char(number, save_pic_path):
    if not os.path.exists('cache_char'):
        os.mkdir('cache_char')
    img_path_list = [save_pic_path + r'/{}.jpg'.format(i) for i in range(1, number + 1)]  # 生成目标图片文件的路径列表
    task = 0
    for image_path in img_path_list:
        img_width, img_height = Image.open(image_path).size  # 获取图片的分辨率
        task += 1
        img_to_char(image_path, img_width, img_height, task)
        print('{}/{} is finished.'.format(task, number))
    print('=======================')
    print('All image was finished!')
    print('=======================')
    return 0
def process_bar(percent, start_str='', end_str='', total_length=0):
    # 进度条
    bar = ''.join("■ " * int(percent * total_length)) + ''
    bar = '\r' + start_str + bar.ljust(total_length) + ' {:0>4.1f}%|'.format(percent * 100) + end_str
    print(bar, end='', flush=True)
def jpg_to_video(char_image_path, FPS):
    video_fourcc = VideoWriter_fourcc(*"MP42")  # 设置视频编码器,这里使用使用MP42编码器,可以生成更小的视频文件
    char_img_path_list = [char_image_path + r'/{}.jpg'.format(i) for i in range(1, number + 1)]  # 生成目标字符图片文件的路径列表
    char_img_test = Image.open(char_img_path_list[1]).size  # 获取图片的分辨率
    if not os.path.exists('video'):
        os.mkdir('video')
    video_writter = VideoWriter('video/new_char_video.avi', video_fourcc, FPS, char_img_test)
    sum = len(char_img_path_list)
    count = 0
    for image_path in char_img_path_list:
        img = cv2.imread(image_path)
        video_writter.write(img)
        end_str = '100%'
        count = count + 1
        process_bar(count / sum, start_str='', end_str=end_str, total_length=15)
    video_writter.release()
    print('\n')
    print('=======================')
    print('The video is finished!')
    print('=======================')
if __name__ == '__main__':
    video_path = 'test1.mp4'
    save_pic_path = 'cache_pic'
    save_charpic_path = 'cache_char'
    vp = cv2.VideoCapture(video_path)
    number = video_to_pic(vp)
    FPS = vp.get(cv2.CAP_PROP_FPS)
    star_to_char(number, save_pic_path)
    vp.release()
    jpg_to_video(save_charpic_path, FPS)
```

还是有人不会用，下面具体一点。前提是你会python，你需要有python环境。

安装程序的依赖包：
```
pip install opencv-python pillow
```

把代码弄进去，同级目录下加入一个test1.mp4，然后直接运行代码。

![在这里插入图片描述](/static/img/images/00311.png)

就能得到效果视频了：

![在这里插入图片描述](/static/img/images/00312.gif)

Python 井川里予 当程序员看多了 程序 生成 字符画

OpenCV





```python
img = cv2.imread(os.path.join(filepath, name))
dst = cv2.resize(img, (img.shape[1]//4, img.shape[0]//4))
cv2.imwrite(os.path.join(aimpath, "image" + str(num).zfill(6)) + ".jpg", dst)
```

Python opencv 图像缩放

# 何为bytes？





是Python3的数据类型，详见：[http://c.biancheng.net/view/2175.html](http://c.biancheng.net/view/2175.html)。

# np.frombuffer

返回一维数组：

![在这里插入图片描述](/static/img/images/00321.png)

# cv2.imdecode

cv2.imdecode()函数从指定的内存缓存中读取数据，并把数据转换(解码)成图像格式;主要用于从网络传输数据中恢复出图像。

cv2.imencode()函数是将图片格式转换(编码)成流数据，赋值到内存缓存中;主要用于图像数据格式的压缩，方便网络传输。

# bytes转图片numpy矩阵
```python
img = cv2.imdecode(np.frombuffer(file, dtype=np.uint8), cv2.IMREAD_COLOR)
```

# 逆运算 numpy矩阵转bytes

这里的img_bytes 就是bytes的file
```python
# 对数组的图片格式进行编码
success, encoded_image = cv2.imencode(".jpg", img)
# 将数组转为bytes
img_bytes = encoded_image.tostring()
```

# bytes转图片numpy矩阵


# 完整代码：

```python
# -*- coding:utf-8 -*-
import uvicorn
from fastapi.middleware.cors import CORSMiddleware
from fastapi import FastAPI, File, Form, UploadFile
import cv2
import numpy as np
from io import BytesIO
app = FastAPI(
    title='FastAPI Tutorial',
    description='FastAPI教程',
    version='1.0.0',
    docs_url='/docs',
    redoc_url='/redocs',
)
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)
@app.post("/files/")
async def alg_file(
        file: bytes = File(...),
        token: str = Form(...)
):
    img = cv2.imdecode(np.frombuffer(file, dtype=np.uint8), 1)
    return {
        "token": token,
        "size": img.shape
    }
if __name__ == '__main__':
    uvicorn.run('run1:app', host='0.0.0.0', port=8002, reload=True, debug=True, workers=1)
```

FastAPI bytes转矩阵 bytes转图片 bytes opencv URL传文件 POST FORM Python

Opencv 读取的图片是BGR 矩阵：




```python
import cv2 
import matplotlib.pyplot as plt
img=cv2.imread('./res.jpg')
plt.imshow(img)
plt.show()
```

plt显示方法imshow是默认矩阵是RGB的，

![在这里插入图片描述](/static/img/images/00322.png)

想要正确显示，需要：

```python
imgrgb= cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
plt.imshow(imgrgb)
plt.show()
```

![在这里插入图片描述](/static/img/images/00323.png)