数字图像与机器视觉基础（1）

---

一、图片各种格式的对比

以Lean图片为例，将其用画图工具转换为256色、16色、单色的位图（BMP)文件，并比较大小

将该图片转换为.jpg、.png、.bmp、.gif，并比较大小：

查看文件头：

Lena.bmp:

Lena-16.bmp:

Lena-24.bmp:

Lena-256.bmp:

Lena-Single.bmp：

位图文件头分4部分，共14字节：

• bfType：2字节，作为标识，就是“BM”二字。
• bfSize：4字节，整个BMP文件的大小。
• bfReserved1/2：4字节，保留字，没用。
• bfOffBits：4字节，偏移数，即 位图文件头+位图信息头+调色板 的大小。

---

二、用奇异值分解对图片进行特征值提取（降维）处理

代码如下：

import numpy as np
import os
from PIL import Image
import matplotlib.pyplot as plt
import matplotlib as mpl
from pprint import pprint


def restore1(sigma, u, v, K):  # 奇异值、左特征向量、右特征向量
    m = len(u)
    n = len(v[0])
    a = np.zeros((m, n))
    for k in range(K):
        uk = u[:, k].reshape(m, 1)
        vk = v[k].reshape(1, n)
        a += sigma[k] * np.dot(uk, vk)
    a[a < 0] = 0
    a[a > 255] = 255
    # a = a.clip(0, 255)
    return np.rint(a).astype('uint8')


def restore2(sigma, u, v, K):  # 奇异值、左特征向量、右特征向量
    m = len(u)
    n = len(v[0])
    a = np.zeros((m, n))
    for k in range(K+1):
        for i in range(m):
            a[i] += sigma[k] * u[i][k] * v[k]
    a[a < 0] = 0
    a[a > 255] = 255
    return np.rint(a).astype('uint8')


if __name__ == "__main__":
    A = Image.open("./lena.jpg", 'r')
    print(A)
    output_path = r'./SVD_Output'
    if not os.path.exists(output_path):
        os.mkdir(output_path)
    a = np.array(A)
    print(a.shape)
    K = 50
    u_r, sigma_r, v_r = np.linalg.svd(a[:, :, 0])
    u_g, sigma_g, v_g = np.linalg.svd(a[:, :, 1])
    u_b, sigma_b, v_b = np.linalg.svd(a[:, :, 2])
    plt.figure(figsize=(11, 9), facecolor='w')
    mpl.rcParams['font.sans-serif'] = ['simHei']
    mpl.rcParams['axes.unicode_minus'] = False
    for k in range(1, K+1):
        print(k)
        R = restore1(sigma_r, u_r, v_r, k)
        G = restore1(sigma_g, u_g, v_g, k)
        B = restore1(sigma_b, u_b, v_b, k)
        I = np.stack((R, G, B), axis=2)
        Image.fromarray(I).save('%s\\svd_%d.png' % (output_path, k))
        if k <= 12:
            plt.subplot(3, 4, k)
            plt.imshow(I)
            plt.axis('off')
            plt.title('奇异值个数：%d' % k)
    plt.suptitle('SVD与图像分解', fontsize=20)
    plt.tight_layout()
    # plt.subplots_adjust(top=0.9)
    plt.show()

---

三、使用开闭运算(腐蚀-膨胀)，检测硬币和细胞的个数

原图如下：

硬币检测代码如下：

import cv2
import numpy as np

def stackImages(scale, imgArray):
    """
        将多张图像压入同一个窗口显示
        :param scale:float类型，输出图像显示百分比，控制缩放比例，0.5=图像分辨率缩小一半
        :param imgArray:元组嵌套列表，需要排列的图像矩阵
        :return:输出图像
    """
    rows = len(imgArray)
    cols = len(imgArray[0])
    rowsAvailable = isinstance(imgArray[0], list)
    width = imgArray[0][0].shape[1]
    height = imgArray[0][0].shape[0]
    if rowsAvailable:
        for x in range(0, rows):
            for y in range(0, cols):
                if imgArray[x][y].shape[:2] == imgArray[0][0].shape[:2]:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (0, 0), None, scale, scale)
                else:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (imgArray[0][0].shape[1], imgArray[0][0].shape[0]),
                                                None, scale, scale)
                if len(imgArray[x][y].shape) == 2: imgArray[x][y] = cv2.cvtColor(imgArray[x][y], cv2.COLOR_GRAY2BGR)
        imageBlank = np.zeros((height, width, 3), np.uint8)
        hor = [imageBlank] * rows
        hor_con = [imageBlank] * rows
        for x in range(0, rows):
            hor[x] = np.hstack(imgArray[x])
        ver = np.vstack(hor)
    else:
        for x in range(0, rows):
            if imgArray[x].shape[:2] == imgArray[0].shape[:2]:
                imgArray[x] = cv2.resize(imgArray[x], (0, 0), None, scale, scale)
            else:
                imgArray[x] = cv2.resize(imgArray[x], (imgArray[0].shape[1], imgArray[0].shape[0]), None, scale, scale)
            if len(imgArray[x].shape) == 2: imgArray[x] = cv2.cvtColor(imgArray[x], cv2.COLOR_GRAY2BGR)
        hor = np.hstack(imgArray)
        ver = hor
    return ver


#读取图片
src = cv2.imread("coin.png")
img = src.copy()

#灰度
img_1 = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#二值化
ret, img_2 = cv2.threshold(img_1, 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)

#腐蚀
kernel = np.ones((20, 20), int)
img_3 = cv2.erode(img_2, kernel, iterations=1)

#膨胀
kernel = np.ones((3, 3), int)
img_4 = cv2.dilate(img_3, kernel, iterations=1)

#找到硬币中心
contours, hierarchy = cv2.findContours(img_4, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[-2:]

#标识硬币
cv2.drawContours(img, contours, -1, (0, 0, 255), 5)

#显示图片
cv2.putText(img, "count:{}".format(len(contours)), (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(src, "src", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_1, "gray", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_2, "thresh", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_3, "erode", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_4, "dilate", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
imgStack = stackImages(1, ([src, img_1, img_2], [img_3, img_4, img]))
cv2.imshow("imgStack", imgStack)
cv2.waitKey(0)

同理，检测细胞:

import cv2
import numpy as np

def stackImages(scale, imgArray):
    """
        将多张图像压入同一个窗口显示
        :param scale:float类型，输出图像显示百分比，控制缩放比例，0.5=图像分辨率缩小一半
        :param imgArray:元组嵌套列表，需要排列的图像矩阵
        :return:输出图像
    """
    rows = len(imgArray)
    cols = len(imgArray[0])
    rowsAvailable = isinstance(imgArray[0], list)
    width = imgArray[0][0].shape[1]
    height = imgArray[0][0].shape[0]
    if rowsAvailable:
        for x in range(0, rows):
            for y in range(0, cols):
                if imgArray[x][y].shape[:2] == imgArray[0][0].shape[:2]:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (0, 0), None, scale, scale)
                else:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (imgArray[0][0].shape[1], imgArray[0][0].shape[0]),
                                                None, scale, scale)
                if len(imgArray[x][y].shape) == 2: imgArray[x][y] = cv2.cvtColor(imgArray[x][y], cv2.COLOR_GRAY2BGR)
        imageBlank = np.zeros((height, width, 3), np.uint8)
        hor = [imageBlank] * rows
        hor_con = [imageBlank] * rows
        for x in range(0, rows):
            hor[x] = np.hstack(imgArray[x])
        ver = np.vstack(hor)
    else:
        for x in range(0, rows):
            if imgArray[x].shape[:2] == imgArray[0].shape[:2]:
                imgArray[x] = cv2.resize(imgArray[x], (0, 0), None, scale, scale)
            else:
                imgArray[x] = cv2.resize(imgArray[x], (imgArray[0].shape[1], imgArray[0].shape[0]), None, scale, scale)
            if len(imgArray[x].shape) == 2: imgArray[x] = cv2.cvtColor(imgArray[x], cv2.COLOR_GRAY2BGR)
        hor = np.hstack(imgArray)
        ver = hor
    return ver


#读取图片
src = cv2.imread("cell.png")
img = src.copy()

#灰度
img_1 = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#二值化
ret, img_2 = cv2.threshold(img_1, 127, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)

#腐蚀
kernel = np.ones((20, 20), int)
img_3 = cv2.erode(img_2, kernel, iterations=1)

#膨胀
kernel = np.ones((3, 3), int)
img_4 = cv2.dilate(img_3, kernel, iterations=1)

#找到硬币中心
contours, hierarchy = cv2.findContours(img_4, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[-2:]

#标识硬币
cv2.drawContours(img, contours, -1, (0, 0, 255), 5)

#显示图片
cv2.putText(img, "count:{}".format(len(contours)), (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(src, "src", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_1, "gray", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_2, "thresh", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_3, "erode", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_4, "dilate", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
imgStack = stackImages(1, ([src, img_1, img_2], [img_3, img_4, img]))
cv2.imshow("imgStack", imgStack)
cv2.waitKey(0)

---

四、条形码检测

原图：

代码：

import cv2
import pyzbar.pyzbar as pyzbar
import numpy
from PIL import Image, ImageDraw, ImageFont


def decodeDisplay(img_path):

    img_data = cv2.imread(img_path)
    # 转为灰度图像
    gray = cv2.cvtColor(img_data, cv2.COLOR_BGR2GRAY)
    barcodes = pyzbar.decode(gray)

    for barcode in barcodes:

        # 提取条形码的边界框的位置
        # 画出图像中条形码的边界框
        (x, y, w, h) = barcode.rect
        cv2.rectangle(img_data, (x, y), (x + w, y + h), (0, 255, 0), 2)
        # 条形码数据为字节对象，所以如果我们想在输出图像上
        # 画出来，就需要先将它转换成字符串
        barcodeData = barcode.data.decode("utf-8")
        barcodeType = barcode.type
        #不能显示中文
        # 绘出图像上条形码的数据和条形码类型
        #text = "{} ({})".format(barcodeData, barcodeType)
        #cv2.putText(imagex1, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX,5, (0, 0, 125), 2)

        #更换为：
        img_PIL = Image.fromarray(cv2.cvtColor(img_data, cv2.COLOR_BGR2RGB))
        # 参数（字体，默认大小）
        font = ImageFont.truetype('msyh.ttc', 35)
        # 字体颜色（rgb)
        fillColor = (0, 255, 255)
        # 文字输出位置
        position = (x, y-50)
        # 输出内容
        str = barcodeData
        # 需要先把输出的中文字符转换成Unicode编码形式(  str.decode("utf-8)   )

        draw = ImageDraw.Draw(img_PIL)
        draw.text(position, str, font=font, fill=fillColor)
        # 使用PIL中的save方法保存图片到本地
        img_PIL.save('1.jpg', 'jpeg')
        # 向终端打印条形码数据和条形码类型
        print("扫描结果==》 类别： {0} 内容： {1}".format(barcodeType, barcodeData))

if __name__ == '__main__':
    decodeDisplay("txm.jpg")

运行结果：

---

五、总结

OpenCV处理图像十分方便

---

参考

OpenCV简单实践之数字图像与机器视觉

Opencv：10个步骤检测出图片中条形码

【计算机视觉】数字图像与机器视觉基础