数字图像与机器视觉基础补充1
前言
本次学习使用的图片如下
一、了解以及分析BMP文件
1.BMP位图文件
常见的图像文件格式有:BMP、JPG(JPE,JPEG)、GIF等。
BMP图像文件(Bitmap-File)格式是Windows采用的图像文件存储格式,在Windows环境下运行的所有图像处理软件都支持这种格式。Windows 3.0以后的BMP文件都是指设备无关位图(DIB,device-independent bitmap)。BMP位图文件默认的文件扩展名是.BMP,有时它也会以.DIB或.RLE作扩展名。
2.BMP文件结构
BMP文件由4部分组成:
位图文件头(bitmap-file header)
位图信息头(bitmap-informationheader)
颜色表(colortable)
颜色点阵数据(bits data) 24位真彩色位图没有颜色表,所以只有1、2、4这三部分。
3.查看示例图片并修改为其它形式
此时的位深度为24
(1)16位、32位彩色图
- 32位
查看文件信息,并使用UltraEdit打开
信息显示图片大小为1MB,位图大小计算:1MB×1024×1024=1048576B,这是不包含文件头信息的大小。
- 16位
文件大小:512KB×1024=524288B
不包含文件文件头信息大小。
(2)256色、16色、单色位图
- 256色
文件大小:257KB×1024=263168B
不包含文件头大小。
- 16色
文件大小:128KB×1024=131072B
不包含文件头大小。
- 单色
文件大小:32KB×1024=32768B
不包含文件头大小。
4.不同图片格式的压缩比
因为BMP不是压缩的,所以以它为基准计算压缩比
GIF:大小193KB,压缩比81.1%
JPG:大小68.8KB,压缩比93.2%
PNG:大小423KB,压缩比58.6%
二、图片处理编程
1.奇异函数分解
(1)示例代码
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("D:/z/test.jpg", 'r')
print(A)
output_path = r'D:/z/test/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()
(2)运行结果
可见,当奇异值越少,图片越模糊。
2.用图像的开闭运算(腐蚀-膨胀),检测出2个样本图像中硬币、细胞的个数
(1)硬币
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("D:/z/yingbi.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)
效果
(2)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("D:/z/xibao.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(腐蚀主要为了把每个硬币区分开。过大会造成缺失,过低会无法区分开。参数可以自己设置以达到合适。)
kernel = np.ones((17, 17), int)
img_3 = cv2.erode(img_2, kernel, iterations=1)
#膨胀(膨胀到合适的值,这样每一个白色区域就是一个硬币。)
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, 255,0), 3)
#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)
运行结果
三、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。
1.导入包
打开Anaconda Prompt使用以下命令安装
pip install imutils
pip install pyzbar
2.代码
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("D:/z/tiaoxingma.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((18, 18), int)
img_6 = cv2.morphologyEx(img_5, cv2.MORPH_CLOSE, kernel)
#开运算
kernel = np.ones((100,100), 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), 6)
#显示图片信息
cv2.putText(img, "results", (30, 30), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_1, "gray", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_2, "GaussianBlur",(40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_3, "Sobel", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_4, "blur", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_5, "threshold", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_6, "close", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 0, 0), 3)
cv2.putText(img_7, "open", (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 2.0, (255, 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, (50, 70), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 255, 0), 3)
#显示所有图片
imgStack = stackImages(0.5, ([img_1, img_2,img_3,img_4],[img_5,img_6,img_7,img]))
cv2.imshow("imgStack", imgStack)
cv2.waitKey(0)
3.运行结果
参考文章
https://blog.csdn.net/qq_45659777/article/details/121698713?spm=1001.2014.3001.5501