当前位置:网站首页>Reprint: defect detection technology of industrial components based on deep learning
Reprint: defect detection technology of industrial components based on deep learning
2022-07-06 18:10:00 【Kamigen】
One 、 Dataset shortcomings
1. The sample size of the dataset is small , There's only... In all 117 A sample picture , There are fewer pictures of defect samples . Insufficient data samples easily lead to the fitting phenomenon of the model , Generalization ability is not strong .
2. The pixel size of the picture is 512*512, Large amount of computation . If the image size is compressed or the image is converted to gray-scale image, it may lead to the loss of useful feature information .
Two 、 Data preprocessing
For the above shortcomings , The simplest and most effective method is to expand the sample size of the data set , Generally, geometric transformation is used to increase the training set samples . The commonly used geometric transformation methods are rotation 、 Zoom translation .
1. Rotation and scaling of pictures
use cv2.getRotationMatrix2D Generating transformation matrix M, Reuse warpAffine Apply affine transformation to the picture . In order to generate multiple pictures with different rotation modes , You can set the rotation angle range , And image zoom range , Take random values in the range every time to generate the rotated picture . The code is as follows ( The code only shows ideas , loosely )
# Set image rotation parameters
RotateOrign=(250,250) # Represents the center of rotation
RotateAngle=(60,90) # It means to rotate clockwise 60-90 degree
RotateScale=(0.8,1) # It means that the image will be scaled to the original after rotation 0.8-1 times
# Define the rotation operation function
def Rotate(image,rotateOrign,rotateAngle,rotateScale):
img=cv2.imread(image)
rows,cols=img.shape[:2]
M=cv2.getRotationMatrix2D(rotateOrign,rotateAngle,rotateScale) # Transformation matrix M
dst=cv2.warpAffine(img,M,(rows,cols))
return dst
# Generate pictures
for item in imgList:
for num in range(generateImgNum): #generateImgNum: Number of generated pictures
RotateAngleTmp=random.uniform(RotateAngle[0],RotateAngle[1])
RotateScaleTmp=random.uniform(RotateScale[0],RotateScale[1])
outImg=Rotate(item,RotateOrign,RotateAngleTmp,RotateScaleTmp)
cv2.imwrite(path,outImg)
2. The translation of the picture
First define the translation matrix M, Reuse warpAffine Apply affine transformation to the picture .
# Image translation parameters
MoveX=(50,100) # towards X How many pixel units to move in the direction
MoveY=(-50,50) # towards Y How many pixel units to move in the direction
# Define the translation operation function
def Translate(image,moveX,moveY):
img=cv2.imread(image)
M=np.float32([[1,0,moveX],[0,1,moveY]])
dst=cv2.warpAffine(img,M,img.shape[:2])
return dst
# Generate pictures
for item in imgList:
for num in range(generateImgNum): #generateImgNum: Number of generated pictures
outImg=Translate(item,random.randint(MoveX[0],MoveX[1])
,random.randint(MoveY[0],MoveY[1]))
cv2.imwrite(path,outImg)
In addition to expanding the sample size of the data set through geometric transformation , Common data preprocessing is to extract features from the input image through convolution . Common convolution operations include Gaussian blur and edge detection .
3. Gaussian blur
Gaussian blur , It's also called Gaussian smoothing , It is usually used to reduce image noise and reduce the level of detail ( Baidu Encyclopedia )
use cv2.GaussianBlur Gaussian Blur , The size of Gaussian convolution kernel must be positive and odd .
# Gaussian blur parameter
GaussianBlurkernelSize=5 # The size of Gaussian convolution kernel
GaussianBlurSigma=(0,2) # Gaussian kernel standard deviation range
# Define Gaussian blur function
def GaussianBlur(image,kernelSize,sigma):
img=cv2.imread(image)
Gblur=cv2.GaussianBlur(img,(kernelSize,kernelSize),sigma)
return Gblur
# Blur the picture
for item in imgList:
for num in range(generateImgNum): #generateImgNum: Number of generated pictures
GaussianBlurSigmaTmp=random.randint(GaussianBlurSigma[0],GaussianBlurSigma[1])
outImg=GaussianBlur(item,GaussianBlurkernelSize,GaussianBlurSigmaTmp)
cv2.imwrite(path,outImg)
4. edge detection
Edge detection extracts the edge features of the picture .Canny Images before and after algorithm processing ( The picture is from OpenCV file ):
Several common algorithms of edge detection :Sobel、Laplacian、Canny.
4.1 Sobel
basis : Up and down the pixel 、 The gray weighted difference between the left and right adjacent points , Reach the extreme value at the edge . First pair x Calculate the gradient of the direction and take the absolute value ( There is less than 0 Pixel value ), Right again y Calculate the gradient of the direction and take the absolute value , Finally, the image is mixed and weighted .
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3) #1,0 Indicates that the calculation direction is x
sobelx = cv2.convertScaleAbs(sobelx) # Take the absolute value
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3) #0,1 Indicates that the calculation direction is y
sobely = cv2.convertScaleAbs(sobely) # Take the absolute value
sobelxy = cv2.addWeighted(sobelx, 0.5, sobely, 0.5, 0) # Mixed weighting
4.2 Laplacian
basis : Calculate the second derivative , The value at the maximum change is zero, that is, the edge is zero . Direct use cv2.Laplacian Edge detection .
aplacian = cv2.Laplacian(img, cv2.CV_64F,ksize=3)
laplacian = cv2.convertScaleAbs(laplacian)
4.3 Canny
use cv2.Canny Achieve edge detection .Canny Set high threshold and low threshold in the algorithm , The high threshold distinguishes the object to be extracted from the background , Low threshold is used to smooth the contour .
EdgeDetectionThreshold1=25 # Low threshold
EdgeDetectionThreshold2=250 # High threshold
def EdgeDetection(image,threshold1,threshold2,):
img=cv2.imread(image)
edges=cv2.Canny(img,threshold1,threshold2)
return edges
for item in imgList:
outImg=EdgeDetection(item,EdgeDetectionThreshold1,EdgeDetectionThreshold2)
cv2.imwrite(path,outImg)
4.4 Canny Algorithm improvement
reference : An improved adaptive threshold Canny Algorithm
OpenCV Documentation about tradition Canny Introduction of algorithm :Canny Edge Detector
Tradition Canny The realization process of the algorithm :
Image Gaussian filtering . Smooth the image , Eliminate noise .
Calculate the gradient intensity and direction of each pixel in the image .
Apply non maximum suppression . Delete some pixels that are not considered edges , Only candidate edges are preserved .
Apply double threshold detection to determine the edge .
Canny Algorithm improvement :
Use bilateral filtering instead of Gaussian filtering . The kernel function of bilateral filtering is the synthesis result of the kernel of spatial domain and the kernel of pixel domain , At the same time, the spatial domain information and gray similarity are considered , Gaussian filtering only considers the spatial distance between pixels . Bilateral filtering implementation function :cv2.bilateralFilter Realize bilateral filtering ,cv2.adaptiveBilateralFilter Realize adaptive bilateral filtering .
The optimal threshold segmentation method is used to obtain the high threshold , use Otsu Method to determine the low threshold .
————————————————
Copyright notice : This paper is about CSDN Blogger 「 Five six six 」 The original article of , follow CC 4.0 BY-SA Copyright agreement , For reprint, please attach the original source link and this statement .
Link to the original text :https://blog.csdn.net/qq_54000005/article/details/125410538
边栏推荐
- 2022暑期项目实训(一)
- Kill -9 system call used by PID to kill process
- OliveTin能在网页上安全运行shell命令(上)
- Kivy tutorial: support Chinese in Kivy to build cross platform applications (tutorial includes source code)
- Will openeuler last long
- adb常用命令
- How to use scroll bars to dynamically adjust parameters in opencv
- Interesting - questions about undefined
- 最新财报发布+天猫618双榜第一,耐克蓄力领跑下个50年
- HMS Core 机器学习服务打造同传翻译新“声”态,AI让国际交流更顺畅
猜你喜欢
Selected technical experts from China Mobile, ant, SF, and Xingsheng will show you the guarantee of architecture stability
After entering Alibaba for the interview and returning with a salary of 35K, I summarized an interview question of Alibaba test engineer
30 分钟看懂 PCA 主成分分析
std::true_ Type and std:: false_ type
虚拟机VirtualBox和Vagrant安装
Getting started with pytest ----- test case pre post, firmware
Unity particle special effects series - treasure chest of shining stars
Is it meaningful for 8-bit MCU to run RTOS?
The easycvr platform reports an error "ID cannot be empty" through the interface editing channel. What is the reason?
【Android】Kotlin代码编写规范化文档
随机推荐
带你穿越古罗马,元宇宙巴士来啦 #Invisible Cities
Reppoints: advanced order of deformable convolution
Stealing others' vulnerability reports and selling them into sidelines, and the vulnerability reward platform gives rise to "insiders"
FMT open source self driving instrument | FMT middleware: a high real-time distributed log module Mlog
Jerry's setting currently uses the dial. Switch the dial through this function [chapter]
Kill -9 system call used by PID to kill process
Nodejs 开发者路线图 2022 零基础学习指南
面向程序员的精品开源字体
Take you through ancient Rome, the meta universe bus is coming # Invisible Cities
Getting started with pytest ----- allow generate report
Unity particle special effects series - treasure chest of shining stars
Compilation principle - top-down analysis and recursive descent analysis construction (notes)
關於這次通信故障,我想多說幾句…
IP, subnet mask, gateway, default gateway
Jerry's updated equipment resource document [chapter]
Fleet tutorial 13 basic introduction to listview's most commonly used scroll controls (tutorial includes source code)
On time and parameter selection of asemi rectifier bridge db207
推荐好用的后台管理脚手架,人人开源
scratch疫情隔离和核酸检测模拟 电子学会图形化编程scratch等级考试三级真题和答案解析2022年6月
Alertmanager sends the alarm email and specifies it as the Alibaba mailbox of the company