其他分享
首页 > 其他分享> > 机器学习——数字图像与机器视觉基础

机器学习——数字图像与机器视觉基础

作者:互联网

目录酱

一、bmp图像浅析

名称占用空间内容实际数据
bfType2字节标识,就是“BM”二字BM
bfSize4字节整个BMP文件的大小0x0046b438(4633656)
bfReserved1/24字节保留字,占位0x00000000
bfOffBits4字节偏移数,即 位图文件头+位图信息头+调色板 的大小0x00000036(54)

注意,Windows的数据是倒着念的,这是PC电脑的特色。如果一段数据为50 1A 25 3C,倒着念就是3C 25 1A50,即0x3C251A50。因此,如果bfSize的数据为38 b4 46 00,实际上就成了0x0046b438。彩色表/调色板(color table)是单色、16色和256色图像文件所特有的,相对应的调色板大小是2、16和256,调色板以4字节为单位,每4个字节存放一个颜色值,图像 的数据是指向调色板的索引。

名称占用空间内容实际数据
biSize4字节位图信息头的大小,总为400x28(40)
biWidth4字节位图的宽度,单位是像素0x400(1024)
biHeight4字节位图的高度,单位是像素0x300(768)
biPlanes2字节目标绘图设备包含的层数,固定值11
biBitCount2字节每个像素的位数1-黑白图,4-16色,8-256色,24-真彩色0x10(16)
biCompression4字节压缩方式,BI_RGB(0)为不压缩0
biSizeImage4字节位图全部像素占用的字节数,BI_RGB时可设为00x018000
biXPelsPerMeter4字节水平分辨率(像素/米)0x0b13
biYPelsPerMeter4字节垂直分辨率(像素/米)0x0b13
biClrUsed4字节位图使用的颜色数如果为0,则颜色数为2的biBitCount次方0
biClrImportant4字节重要的颜色数,0代表所有颜色都重要0

二、用奇异值分解对图片进行降维处理

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("C:\\Users\\Leon_D_Alan\\OneDrive\图片\\ps专用图片副本\\碧翠丝.png", 'r')
    print(A)
    output_path = r'C:\\Users\\Leon_D_Alan\\OneDrive\图片\\ps专用图片副本\\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()

在这里插入图片描述
当奇异值越少,图片越模糊。

三、采用图像的开闭运算,检测出2个样本图像中硬币、细胞的个数

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("1.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)

在这里插入图片描述

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("1.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, (0, 0, 0), 3)
cv2.putText(img_3, "erode", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)
cv2.putText(img_4, "dilate", (0, 30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)
imgStack = stackImages(1, ([src, img_1, img_2], [img_3, img_4, img]))
cv2.imshow("imgStack", imgStack)
cv2.waitKey(0)

在这里插入图片描述

四、采用图像梯度、开闭、轮廓运算等,对图片中的条形码进行定位提取;再调用条码库获得条码字符

pip install imutils

pip install pyzbar
import cv2
import numpy as np
import imutils
from pyzbar import pyzbar
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("C:\\Users\\28205\\Documents\\Tencent Files\\2820535964\\FileRecv\\txm.jpg")
img = src.copy()

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

#高斯滤波
img_2 = cv2.GaussianBlur(img_1, (5, 5), 1)


#Sobel算子
sobel_x = cv2.Sobel(img_2, cv2.CV_64F, 1, 0, ksize=3)
sobel_y = cv2.Sobel(img_2, cv2.CV_64F, 0, 1, ksize=3)
sobel_x = cv2.convertScaleAbs(sobel_x)
sobel_y = cv2.convertScaleAbs(sobel_y)
img_3 = cv2.addWeighted(sobel_x, 0.5, sobel_y, 0.5, 0)

#均值方波
img_4 = cv2.blur(img_3, (5, 5))

#二值化
ret, img_5 = cv2.threshold(img_4, 127, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

#闭运算
kernel = np.ones((100, 100), int)
img_6 = cv2.morphologyEx(img_5, cv2.MORPH_CLOSE, kernel)

#开运算
kernel = np.ones((200, 200), int)
img_7 = cv2.morphologyEx(img_6, cv2.MORPH_OPEN, kernel)

#绘制条形码区域
contours = cv2.findContours(img_7, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
c = sorted(contours, key = cv2.contourArea, reverse = True)[0]
rect = cv2.minAreaRect(c)
box = cv2.cv.BoxPoints(rect) if imutils.is_cv2() else cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(img, [box], -1, (0,255,0), 20)

#显示图片信息
cv2.putText(img, "results", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_1, "gray", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)
cv2.putText(img_2, "GaussianBlur",(200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)
cv2.putText(img_3, "Sobel", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_4, "blur", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_5, "threshold", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (255, 0, 0), 3)
cv2.putText(img_6, "close", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)
cv2.putText(img_7, "open", (200, 200), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 3)

#输出条形码
barcodes = pyzbar.decode(src)
for barcode in barcodes:
    barcodeData = barcode.data.decode("utf-8")
    cv2.putText(img, barcodeData, (200, 600), cv2.FONT_HERSHEY_SIMPLEX, 5.0, (0, 255, 0), 30)

#显示所有图片
imgStack = stackImages(0.8, ([img_1, img_2],[img_3,img_4],[img_5,img_6],[img_7,img]))
cv2.imshow("imgStack", imgStack)
cv2.waitKey(0)

在这里插入图片描述

五、总结

在检测图中细胞个数时,效果没有检测硬币那么好,这与图片中某些细胞颜色较浅,转换为灰度图片后,与周围颜色分辨不明显有关。条形码的识别也不是很精准。


参考文献

https://blog.csdn.net/csdn66_2016/article/details/82850695
https://blog.csdn.net/qq_41881259/article/details/106441768
https://blog.csdn.net/qq_45659777/article/details/121698713

标签:scale,机器,img,数字图像,cv2,shape,np,视觉,imgArray
来源: https://blog.csdn.net/zero_zero_seven/article/details/121855642