WO2021208424A1 - Laplacian feature mapping learning-based machine testing method for graphics card interface - Google Patents
Laplacian feature mapping learning-based machine testing method for graphics card interface Download PDFInfo
- Publication number
- WO2021208424A1 WO2021208424A1 PCT/CN2020/129654 CN2020129654W WO2021208424A1 WO 2021208424 A1 WO2021208424 A1 WO 2021208424A1 CN 2020129654 W CN2020129654 W CN 2020129654W WO 2021208424 A1 WO2021208424 A1 WO 2021208424A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- graphics card
- laplacian
- image
- card interface
- feature mapping
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Definitions
- the invention belongs to the field of graphics card interface testing, and in particular relates to an automatic testing method of a graphics card interface.
- the present invention uses an industrial host computer equipped with a composite interface video collector to replace the display, collects the output signal of the graphics card interface through the video collector, and decodes it in the host computer, and realizes the automatic classification of video quality in combination with a machine learning method.
- the present invention provides an automated test method for a graphics card interface, which includes the following steps:
- a test method for graphics card interface machines based on Laplace feature mapping learning according to the following steps:
- Step 1 Connect the product to be tested to the video capture device with the corresponding type of wire;
- Step 2 Play the test video, the video collector collects the output information of the display interface, and uploads it to the industrial host computer;
- Step 3 The industrial host computer decodes the graphics card interface information and saves the frame image
- Step 4 Perform Laplacian feature mapping dimensionality reduction preprocessing on the rows and columns of the frame image respectively, the purpose of which is to reduce the data dimension and increase the detection rate;
- each frame of image can be digitized into an m ⁇ n matrix A.
- Each element in matrix A represents a pixel in the picture.
- the frame image has a total of mn pixels.
- the size of m and n is determined by the test video. Determined by the resolution; in order to achieve dimensionality reduction of Laplacian feature mapping, the image A is rearranged and combined into the following vector form
- a v1 A v2 ... A vn represents the column vector of image A; then z is put into the historical data set for Laplacian feature map dimensionality reduction processing;
- the input layer of the neural network is composed of k neurons, which corresponds to the k elements of image A after dimensionality reduction.
- the hidden layer is composed of p neurons, and its output is
- the output layer is composed of 2 neurons, which represent qualified and unqualified respectively; its expression is
- v j is the offset of the corresponding output
- v jh is the corresponding input t h to the output the weight of.
- Laplacian Eigenmaps is a non-linear dimensionality reduction method that uses a local perspective to construct the relationship between data, which can reflect the inherent manifold structure of the data. Its intuitive idea is to hope that the points that are related to each other are as close as possible in the space after dimensionality reduction.
- the preferred step 4 is
- the objective function for minimizing the Laplacian feature map is
- w ij is the weight of the connection between the measurement samples z (i) and z (j) ; w ij is determined according to whether the two sample points are close, first use KNN The method determines whether to set an edge connection between the sample z (i) and z (j) .
- the preferred objective function can be expressed as the following quadratic form after sorting
- the eigenvector corresponding to the non-zero eigenvalue obtained by the solution is the output after dimensionality reduction.
- step 5 train to obtain the weights ⁇ hi , v jh and the bias ⁇ h , v j by solving the following optimization problem
- the advantages of the present invention are mainly embodied in that it can be compatible with various types of interfaces, does not need to be equipped with a display corresponding to the interface, uses a video collector and an industrial upper computer to complete the collection and decoding of interface information, and reduces the material cost.
- detection it combines principal component analysis and machine learning methods to achieve rapid and efficient automatic video quality detection, reducing labor costs and improving efficiency.
- Fig. 1 is a flowchart of an automated testing method for a graphics card interface of the present invention.
- Figure 2 is a framework diagram of an automated testing method for a graphics card interface of the present invention.
- Step 1 Connect the product to be tested to the industrial host computer with the video capture card installed with the corresponding type of wire;
- Step 2 Play the test video, and the video capture card collects the graphics interface information of the product to be tested and sends it to the industrial host computer
- Step 3 The industrial host computer decodes the graphics card interface information to generate and save a frame image
- Step 4 Perform Laplacian feature mapping dimensionality reduction preprocessing on the rows and columns of the frame image respectively, the purpose of which is to reduce the data dimension and increase the detection rate.
- each frame of image can be digitized into an m ⁇ n matrix A.
- Each element in matrix A represents a pixel in the picture.
- the frame image has a total of mn pixels.
- the size of m and n is determined by the test video. The resolution is determined.
- image A is rearranged and combined into the following vector form
- a v1 A v2 ... A vn represents the column vector of image A. Then put z into the historical data set for Laplacian feature map dimensionality reduction processing.
- the eigenvector corresponding to the non-zero eigenvalue obtained by the solution is the output after dimensionality reduction.
- Step 5 Use the image after the dimensionality reduction process as the input of the machine learning classifier to obtain the detection result.
- the input layer of the neural network is composed of k neurons, which corresponds to the k elements of image A after dimensionality reduction.
- the hidden layer is composed of p neurons, and its output is
- the output layer is composed of 2 neurons, which represent qualified and unqualified respectively. Its expression is
- the output image of the graphics card interface of the product to be tested is used as input, and the machine learning classifier outputs qualified or unqualified classification results.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
A Laplacian feature mapping learning-based machine testing method for a graphics card interface, which is carried out according to the following steps: step 1: a product to be tested is connected to a video collector by using a corresponding type of wire; step 2: a test video is played back, and the video collector collects output information of a display interface and uploads same to an industrial host computer; step 3: the industrial host computer decodes graphics card interface information and saves a frame image; step 4: Laplacian feature mapping and dimensionality reduction preprocessing is performed on rows and columns of the frame image separately; and step 5: an analyzed image is used as an input for a machine learning classifier so as to obtain a detection result. The method is compatible with various types of interfaces without needing to be equipped with a display corresponding to the interface, and uses a video collector and an industrial host computer to complete the collection and decoding of interface information, which reduces the amount of material resources and costs.
Description
本发明属于显卡接口测试领域,具体涉及一种显卡接口的自动化测试方法。The invention belongs to the field of graphics card interface testing, and in particular relates to an automatic testing method of a graphics card interface.
在显卡接口测试领域中,通常需要将待测产品接到具备对应类型接口的显示器,然后播放测试视频,由人工来检查视频显示质量是否合格。不仅在设备上需要配备各种接口类型的显示器,人工检查也存在因人工失误和检测时间长而影响生产效率。尤其是近年来市场对画质的要求不断提高,需要更高性能的显示器,人工肉眼检查也更难分辨细小的瑕疵,因此需要大量的人力物力成本。为此,本发明采用配备复合接口视频采集器的工业上位机替代显示器,通过视频采集器收集显卡接口输出信号,并在上位机中进行解码,结合机器学习方法实现视频质量的自动分类。In the field of graphics card interface testing, it is usually necessary to connect the product to be tested to a monitor with a corresponding type of interface, and then play the test video, and manually check whether the video display quality is qualified. Not only need to be equipped with displays of various interface types on the equipment, but manual inspections also affect production efficiency due to manual errors and long inspection time. Especially in recent years, the market's requirements for image quality have continued to increase, requiring higher-performance displays, and manual visual inspection is also more difficult to distinguish small defects, so a lot of manpower and material resources are required. For this reason, the present invention uses an industrial host computer equipped with a composite interface video collector to replace the display, collects the output signal of the graphics card interface through the video collector, and decodes it in the host computer, and realizes the automatic classification of video quality in combination with a machine learning method.
发明内容Summary of the invention
为克服上述困难,本发明提供一种显卡接口的自动化测试方法,包括以下步骤:In order to overcome the above-mentioned difficulties, the present invention provides an automated test method for a graphics card interface, which includes the following steps:
1.一种基于拉普拉斯特征映射学习的显卡接口机器测试方法,按照如下步骤进行:1. A test method for graphics card interface machines based on Laplace feature mapping learning, according to the following steps:
步骤1:用相应类型线材将待测产品连接到视频采集器;Step 1: Connect the product to be tested to the video capture device with the corresponding type of wire;
步骤2:播放测试视频,视频采集器收集显示接口输出信息,并上传至工业上位机;Step 2: Play the test video, the video collector collects the output information of the display interface, and uploads it to the industrial host computer;
步骤3:工业上位机对显卡接口信息进行解码,并保存帧图像;Step 3: The industrial host computer decodes the graphics card interface information and saves the frame image;
步骤4:对所述帧图像的行和列分别进行拉普拉斯特征映射降维预处理,其目的是降低数据维度,提高检测速率;Step 4: Perform Laplacian feature mapping dimensionality reduction preprocessing on the rows and columns of the frame image respectively, the purpose of which is to reduce the data dimension and increase the detection rate;
首先每一帧图像都可以被数字化为一个m×n的矩阵A,矩阵A中的每一个元素都表示图片中的一个像素,帧图像一共有mn个像素,m和n的大小是由测试视频的分辨率决定的;为了实现拉普拉斯特征映射降维,将图像A重新排列组合为如下向量形式First of all, each frame of image can be digitized into an m×n matrix A. Each element in matrix A represents a pixel in the picture. The frame image has a total of mn pixels. The size of m and n is determined by the test video. Determined by the resolution; in order to achieve dimensionality reduction of Laplacian feature mapping, the image A is rearranged and combined into the following vector form
z=[A
v1 A
v2 … A
vn]
T
z=[A v1 A v2 … A vn ] T
其中A
v1 A
v2 … A
vn表示图像A的列向量;然后将z放入历史数据集当中进行拉普拉斯特征映射降维处理;
Among them, A v1 A v2 … A vn represents the column vector of image A; then z is put into the historical data set for Laplacian feature map dimensionality reduction processing;
步骤5:将上述分析后的图像作为机器学习分类器的输入,从而得到检测结果;选择三层神经网络作为机器学习分类器的训练模型,训练数据
则由标记好的历史的检测数据得到,其中y
l=1表示z
kl质量不合格,y
l=0则表示z
kl质量合格;
Step 5: Use the analyzed image as the input of the machine learning classifier to obtain the detection result; select the three-layer neural network as the training model of the machine learning classifier, and the training data It is obtained from the marked historical test data, where y l =1 means that the quality of z kl is unqualified, and y l =0 means that the quality of z kl is qualified;
神经网络的输入层由k个神经元组成,即对应图像A降维后的k个元素,隐藏层由p个神经元组成,其输出为The input layer of the neural network is composed of k neurons, which corresponds to the k elements of image A after dimensionality reduction. The hidden layer is composed of p neurons, and its output is
ω
h对应每个隐藏层神经元的偏置,ω
hi对应输入u
i到神经元t
h的权重,
σ则是激活函数
最后输出层由2个神经元组成,分别代表合格与不合格;其表达式为
h [omega] corresponding to the offset of each hidden layer neuron, ω hi corresponds to the neuron input u i t h, weightings, σ is the activation function Finally, the output layer is composed of 2 neurons, which represent qualified and unqualified respectively; its expression is
其中v
j为对应输出的偏置,v
jh为对应输入t
h到输出
的权重。
Where v j is the offset of the corresponding output, and v jh is the corresponding input t h to the output the weight of.
拉普拉斯特征映射(Laplacian Eigenmaps,LE)是一种非线性的降维方法,用局部的角度去构建数据之间的关系,可以反映出数据内在的流形结构。它的直观思想是希望相互间有关系的点在降维后的空间中尽可能的靠近,优选的步骤4中的Laplacian Eigenmaps (LE) is a non-linear dimensionality reduction method that uses a local perspective to construct the relationship between data, which can reflect the inherent manifold structure of the data. Its intuitive idea is to hope that the points that are related to each other are as close as possible in the space after dimensionality reduction. The preferred step 4 is
拉普拉斯特征映射最小化的目标函数是The objective function for minimizing the Laplacian feature map is
其中
为z
(i)降到k维后的点,w
ij是测量样本z
(i)和z
(j)之间的连接权重;w
ij是根据两个样本点是否接近来确定的,首先利用KNN方法确定 是否在样本z
(i)与z
(j)之间设置边连接,若z
(i)在z
(j)的k个最近邻居中,则将z
(i)和z
(j)相连,k是一个预先设定的值,或者设定合适的ε,将
的节点相连接;然后确定权重大小,采用Heat kernel函数,将相连节点的权重设置为
这里的t为预先设定的值,或令t=∞,将所有相连节点的权重设为w
ij=1,其他未连接的均为0;最终可以得到一个对称邻接矩阵W。
in Is the point after z (i) is reduced to k dimension, w ij is the weight of the connection between the measurement samples z (i) and z (j) ; w ij is determined according to whether the two sample points are close, first use KNN The method determines whether to set an edge connection between the sample z (i) and z (j) . If z (i) is among the k nearest neighbors of z (j) , then z (i) and z (j) are connected, k is a preset value, or set an appropriate ε, will The nodes are connected; then the weight is determined, and the Heat kernel function is used to set the weight of the connected nodes to Here t is a preset value, or let t=∞, set the weights of all connected nodes to w ij =1, and all other unconnected nodes are 0; finally, a symmetric adjacency matrix W can be obtained.
通过最小化目标函数公式(1),保证了相近的z
(i)和z
(j)映射后u
(i)和u
(j)两点仍能够保持相近。优选的目标函数经过整理后可以表示为如下二次型的形式
By minimizing the objective function formula (1), it is ensured that the two points u (i) and u (j) can still remain close after the similar z (i) and z (j) are mapped. The preferred objective function can be expressed as the following quadratic form after sorting
其中u=(u
(1),u
(2),…,u
(n))
T,L=D-W为拉普拉斯矩阵,D是一个对角矩阵,满足D
ii=∑
jw
ij,W是一个对称邻接矩阵,且拉普拉斯矩阵L是半正定的;
Where u = (u (1) , u (2) ,..., u (n) ) T , L = DW is the Laplacian matrix, D is a diagonal matrix, satisfying D ii =∑ j w ij , W Is a symmetric adjacency matrix, and the Laplacian matrix L is positive semi-definite;
最终求解如下最小化问题The final solution is the following minimization problem
其中约束u
TDu=1避免了缩放的影响,最小化目标函数的向量u由广义特征值问题的最小特征值解给出:
Among them, the constraint u T Du = 1 avoids the impact of scaling, and the vector u that minimizes the objective function is given by the minimum eigenvalue solution of the generalized eigenvalue problem:
Lu=λDu (4)Lu = λDu (4)
求解得到的非零特征值所对应的特征向量就是降维后的输出。The eigenvector corresponding to the non-zero eigenvalue obtained by the solution is the output after dimensionality reduction.
优选的,步骤5:最后通过求解以下最优化问题来训练得到权重ω
hi,v
jh和偏置ω
h,v
j
Preferably, step 5: Finally, train to obtain the weights ω hi , v jh and the bias ω h , v j by solving the following optimization problem
其中y
lj为样本A
kl的标签,N为历史数据的样本数;最后,将待测产品的显卡接口输出图像作为输入,得到最终的检测结果。
Where y lj is the label of the sample A kl , and N is the number of samples of historical data; finally, the output image of the graphics card interface of the product to be tested is used as input to obtain the final detection result.
本发明的优势主要体现在:能够兼容各种类型的接口,无需配备对应接口的显示器,利用视频采集器和工业上位机完成接口信息的采集与解码,降低了物力成本。在检测方面,结合了主成分分析与机器学习方法,实现了快速高效的视频质量自动化检测,降低了人力成本,同时提高了效率。The advantages of the present invention are mainly embodied in that it can be compatible with various types of interfaces, does not need to be equipped with a display corresponding to the interface, uses a video collector and an industrial upper computer to complete the collection and decoding of interface information, and reduces the material cost. In terms of detection, it combines principal component analysis and machine learning methods to achieve rapid and efficient automatic video quality detection, reducing labor costs and improving efficiency.
图1为本发明一种显卡接口的自动化测试方法流程图。Fig. 1 is a flowchart of an automated testing method for a graphics card interface of the present invention.
图2为本发明一种显卡接口的自动化测试方法框架图。Figure 2 is a framework diagram of an automated testing method for a graphics card interface of the present invention.
下面结合附图1,2对本发明做进一步说明。In the following, the present invention will be further described with reference to Figures 1 and 2.
步骤1:用相应类型线材将待测产品连接安装了视频采集卡的工业上位机;Step 1: Connect the product to be tested to the industrial host computer with the video capture card installed with the corresponding type of wire;
步骤2:播放测试视频,视频采集卡采集待测产品的显卡接口信息并发送到所述工业上位机Step 2: Play the test video, and the video capture card collects the graphics interface information of the product to be tested and sends it to the industrial host computer
步骤3:所述工业上位机对所述显卡接口信息解码生成并保存帧图像;Step 3: The industrial host computer decodes the graphics card interface information to generate and save a frame image;
步骤4:对所述帧图像的行和列分别进行拉普拉斯特征映射降维预处理,其目的是降低数据维度,提高检测速率。首先每一帧图像都可以被数字化为一个m×n的矩阵A,矩阵A中的每一个元素都表示图片中的一个像素,帧图像一共有mn个像素,m和n的大小是由测试视频的分辨率决定的。为了实现拉普拉斯特征映射降维,将图像A重新排列组合为如下向量形式Step 4: Perform Laplacian feature mapping dimensionality reduction preprocessing on the rows and columns of the frame image respectively, the purpose of which is to reduce the data dimension and increase the detection rate. First of all, each frame of image can be digitized into an m×n matrix A. Each element in matrix A represents a pixel in the picture. The frame image has a total of mn pixels. The size of m and n is determined by the test video. The resolution is determined. In order to achieve dimensionality reduction of Laplacian feature mapping, image A is rearranged and combined into the following vector form
z=[A
v1 A
v2 … A
vn]
T
z=[A v1 A v2 … A vn ] T
其中A
v1 A
v2 … A
vn表示图像A的列向量。然后将z放入历史数据集当中进行拉普拉斯特征映射降维处理。
Among them, A v1 A v2 … A vn represents the column vector of image A. Then put z into the historical data set for Laplacian feature map dimensionality reduction processing.
首先,构造邻接矩阵W:First, construct the adjacency matrix W:
然后,根据邻接矩阵W,计算对角矩阵DThen, according to the adjacency matrix W, calculate the diagonal matrix D
D
ii=∑
jw
ij
D ii =∑ j w ij
最后,得到拉普拉斯矩阵L=D-W,最终求解如下最小化问题Finally, the Laplace matrix L=D-W is obtained, and the following minimization problem is finally solved
其中约束u
TDu=1避免了缩放的影响,最小化目标函数的向量u由广义特征值问题的最小特征值解给出:
Among them, the constraint u T Du = 1 avoids the impact of scaling, and the vector u that minimizes the objective function is given by the minimum eigenvalue solution of the generalized eigenvalue problem:
Lu=λDuLu=λDu
求解得到的非零特征值所对应的特征向量就是降维后的输出。The eigenvector corresponding to the non-zero eigenvalue obtained by the solution is the output after dimensionality reduction.
步骤5:将上述降维处理后的图像作为机器学习分类器的输入,从而得到检测结果。其中,选择三层神经网络作为机器学习分类器的训练模型,训练数据
则由标记好的历史的检测数据得到,其中y
l=1表示z
kl质量不合格,y
l=0则表示z
kl质量合格。
Step 5: Use the image after the dimensionality reduction process as the input of the machine learning classifier to obtain the detection result. Among them, the three-layer neural network is selected as the training model of the machine learning classifier, and the training data It is obtained from the marked historical test data, where y l =1 indicates that the quality of z kl is unqualified, and y l =0 indicates that the quality of z kl is qualified.
神经网络的输入层由k个神经元组成,即对应图像A降维后的k个元素,隐藏层由p个神经元组成,其输出为The input layer of the neural network is composed of k neurons, which corresponds to the k elements of image A after dimensionality reduction. The hidden layer is composed of p neurons, and its output is
ω
h对应每个隐藏层神经元的偏置,ω
hi对应输入u
i到神经元t
h的权重,σ则是激活函数
最后输出层由2个神经元组成,分别代表合格与不合格。其表达式为
h [omega] corresponding to the offset of each hidden layer neuron, ω hi corresponds to the neuron input u i t h, weightings, σ is the activation function Finally, the output layer is composed of 2 neurons, which represent qualified and unqualified respectively. Its expression is
其中v
j为对应输出的偏置,v
jh为对应输入t
h到输出
的权重。最后通过求解以下最优化问题来训练得到权重ω
hi,v
jh和偏置ω
h,v
j
Where v j is the offset of the corresponding output, and v jh is the corresponding input t h to the output the weight of. Finally, the weights ω hi , v jh and bias ω h , v j are obtained by training by solving the following optimization problem
其中y
lj为样本A
kl的标签。
Where y lj is the label of the sample A kl.
最后,将待测产品的显卡接口输出图像作为输入,机器学习分类器输出合格或者不合格的分类结果。Finally, the output image of the graphics card interface of the product to be tested is used as input, and the machine learning classifier outputs qualified or unqualified classification results.
如上所述,便可较好地实现本发明,上述实施例仅为本发明的典型实施例,并非用来限定本发明的实施范围,即凡依本发明内容所作的均等变化与修饰,都为本发明权利要求所要求保护的范围所涵盖。As described above, the present invention can be implemented well. The above-mentioned embodiments are only typical embodiments of the present invention, and are not used to limit the scope of implementation of the present invention. The scope of protection claimed by the claims of the present invention is covered.
以上所述,仅为本发明较佳的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明披露的技术范围内,可轻易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应该以权利要求书的保护范围为准。The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of changes or changes within the technical scope disclosed in the present invention. All replacements should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (4)
- 一种基于拉普拉斯特征映射学习的显卡接口机器测试方法,其特征在于:A graphics interface machine testing method based on Laplacian feature mapping learning, which is characterized by:步骤1:用相应类型线材将待测产品连接到视频采集器;Step 1: Connect the product to be tested to the video capture device with the corresponding type of wire;步骤2:播放测试视频,视频采集器收集显示接口输出信息,并上传至工业上位机;Step 2: Play the test video, the video collector collects the output information of the display interface, and uploads it to the industrial host computer;步骤3:工业上位机对显卡接口信息进行解码,并保存帧图像;Step 3: The industrial host computer decodes the graphics card interface information and saves the frame image;步骤4:对所述帧图像的行和列分别进行拉普拉斯特征映射降维预处理;Step 4: Perform Laplacian feature map dimensionality reduction preprocessing on the rows and columns of the frame image respectively;首先每一帧图像都可以被数字化为一个m×n的矩阵A,矩阵A中的每一个元素都表示图片中的一个像素,帧图像一共有mn个像素,m和n的大小是由测试视频的分辨率决定的;为了实现拉普拉斯特征映射降维,将图像A重新排列组合为如下向量形式First of all, each frame of image can be digitized into an m×n matrix A. Each element in matrix A represents a pixel in the picture. The frame image has a total of mn pixels. The size of m and n is determined by the test video. Determined by the resolution; in order to achieve dimensionality reduction of Laplacian feature mapping, the image A is rearranged and combined into the following vector formz=[A v1 A v2 … A vn] T z=[A v1 A v2 … A vn ] T其中A v1 A v2 … A vn表示图像A的列向量;然后将z放入历史数据集当中进行拉普拉斯特征映射降维处理; Among them, A v1 A v2 … A vn represents the column vector of image A; then z is put into the historical data set for Laplacian feature map dimensionality reduction processing;步骤5:将上述分析后的图像作为机器学习分类器的输入,从而得到检测结果;选择三层神经网络作为机器学习分类器的训练模型,训练数据S=(z kl,y l)则由标记好的历史的检测数据得到,其中y l=1表示z kl质量不合格,y l=0则表示z kl质量合格; Step 5: Use the analyzed image as the input of the machine learning classifier to obtain the detection result; select the three-layer neural network as the training model of the machine learning classifier, and the training data S = (z kl , y l ) is marked Good historical test data is obtained, where y l =1 means that the quality of z kl is unqualified, and y l =0 means that the quality of z kl is qualified;神经网络的输入层由k个神经元组成,即对应图像A降维后的k个元素,隐藏层由p个神经元组成,其输出为The input layer of the neural network is composed of k neurons, which corresponds to the k elements of image A after dimensionality reduction. The hidden layer is composed of p neurons, and its output isω h对应每个隐藏层神经元的偏置,ω hi对应输入u i到神经元t h的权重,σ则是激活函数 最后输出层由2个神经元组成,分别代表合格与不合格;其表达式为 h [omega] corresponding to the offset of each hidden layer neuron, ω hi corresponds to the neuron input u i t h, weightings, σ is the activation function Finally, the output layer is composed of 2 neurons, which represent qualified and unqualified respectively; its expression is
- 根据权利要求1所述的基于拉普拉斯特征映射学习的显卡接口机器测试方法,其特征在于:步骤4中的The graphics card interface machine testing method based on Laplacian feature mapping learning according to claim 1, characterized in that: in step 4拉普拉斯特征映射最小化的目标函数是The objective function for minimizing the Laplacian feature map is其中 为z (i)降到k维后的点,w ij是测量样本z (i)和z (j)之间的连接权重;w ij是根据两个样本点是否接近来确定的,首先利用KNN方法确定是否在样本z (i)与z (j)之间设置边连接,若z (i)在z (j)的k个最近邻居中,则将z (i)和z (j)相连,k是一个预先设定的值,或者设定合适的ε,将||z (i)-z (j)|| 2≤ε的节点相连接;然后确定权重大小,采用Heat kernel函数,将相连节点的权重设置为 这里的t为预先设定的值,或令t=∞,将所有相连节点的权重设为w ij=1,其他未连接的均为0;最终可以得到一个对称邻接矩阵W。 in Is the point after z (i) is reduced to k dimension, w ij is the weight of the connection between the measurement samples z (i) and z (j) ; w ij is determined according to whether the two sample points are close, first use KNN The method determines whether to set an edge connection between the sample z (i) and z (j) . If z (i) is among the k nearest neighbors of z (j) , then z (i) and z (j) are connected, k is a preset value, or set an appropriate ε, connect the nodes with ||z (i) -z (j) || 2 ≤ ε; then determine the weight and use the Heat kernel function to connect The weight of the node is set to Here t is a preset value, or let t=∞, set the weights of all connected nodes as w ij =1, and other unconnected ones are 0; finally, a symmetric adjacency matrix W can be obtained.
- 根据权利要求2所述的基于拉普拉斯特征映射学习的显卡接口机器测试方法,其特征在于:目标函数经过整理后可以表示为如下二次型的形式The method for testing a graphics card interface machine based on Laplacian feature mapping learning according to claim 2, characterized in that: the objective function can be expressed as the following quadratic form after sorting其中u=(u (1),u (2),…,u (n)) T,L=D-W为拉普拉斯矩阵,D是一个对角矩阵,满足D ii=Σ jw ij,W是一个对称邻接矩阵,且拉普拉斯矩阵L是半正定的; Where u = (u (1) , u (2) ,..., u (n) ) T , L = DW is the Laplacian matrix, D is a diagonal matrix, satisfying D ii =Σ j w ij , W Is a symmetric adjacency matrix, and the Laplacian matrix L is positive semi-definite;最终求解如下最小化问题The final solution is the following minimization problemu TDu=1 u T Du = 1其中约束u TDu=1避免了缩放的影响,最小化目标函数的向量u由广义特征值问题的最小特征值解给出: Among them, the constraint u T Du = 1 avoids the impact of scaling, and the vector u that minimizes the objective function is given by the minimum eigenvalue solution of the generalized eigenvalue problem:Lu=λDu (4)Lu = λDu (4)求解得到的非零特征值所对应的特征向量就是降维后的输出。The eigenvector corresponding to the non-zero eigenvalue obtained by the solution is the output after dimensionality reduction.
- 根据权利要求1所述的基于拉普拉斯特征映射学习的显卡接口机器测试方法,其特征在于步骤5:最后通过求解以下最优化问题来训练得到权重ω hi,v jh和偏置ω h,v j The graphics card interface machine testing method based on Laplacian feature mapping learning according to claim 1, characterized in that step 5: Finally, the weights ω hi , v jh and bias ω h are obtained by training by solving the following optimization problem, v j其中y lj为样本A kl的标签,N为历史数据的样本数;最后,将待测产品的显卡接口输出图像作为输入,得到最终的检测结果。 Where y lj is the label of the sample A kl , and N is the number of samples of historical data; finally, the output image of the graphics card interface of the product to be tested is used as input to obtain the final detection result.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010290292.2 | 2020-04-14 | ||
CN202010290292.2A CN111507393B (en) | 2020-04-14 | 2020-04-14 | Display card interface machine testing method based on Laplace feature mapping learning |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021208424A1 true WO2021208424A1 (en) | 2021-10-21 |
Family
ID=71875911
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/129654 WO2021208424A1 (en) | 2020-04-14 | 2020-11-18 | Laplacian feature mapping learning-based machine testing method for graphics card interface |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111507393B (en) |
WO (1) | WO2021208424A1 (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111507393B (en) * | 2020-04-14 | 2021-11-09 | 艾瑞思检测技术(苏州)有限公司 | Display card interface machine testing method based on Laplace feature mapping learning |
CN114124517B (en) * | 2021-11-22 | 2024-05-28 | 码客工场工业科技(北京)有限公司 | Industrial Internet intrusion detection method based on Gaussian process |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101777326A (en) * | 2009-01-09 | 2010-07-14 | 深圳宝龙达信息技术股份有限公司 | VGA video card test tooling and method |
CN104023224A (en) * | 2014-03-31 | 2014-09-03 | 深圳英飞拓科技股份有限公司 | Camera performance detection method and system and server |
CN108696747A (en) * | 2018-04-17 | 2018-10-23 | 青岛海信电器股份有限公司 | A kind of video measurement method and apparatus |
CN109815855A (en) * | 2019-01-07 | 2019-05-28 | 中国电子科技集团公司第四十一研究所 | A kind of electronic equipment automatic test approach and system based on machine learning |
US20200012932A1 (en) * | 2018-07-09 | 2020-01-09 | National Central University | Machine learning method and machine learning device |
CN111507393A (en) * | 2020-04-14 | 2020-08-07 | 艾瑞思检测技术(苏州)有限公司 | Display card interface machine testing method based on Laplace feature mapping learning |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7113880B1 (en) * | 2004-02-04 | 2006-09-26 | American Megatrends, Inc. | Video testing via pixel comparison to known image |
CN101727373A (en) * | 2008-10-16 | 2010-06-09 | 和硕联合科技股份有限公司 | Display card testing device and method |
CN102053899A (en) * | 2009-10-28 | 2011-05-11 | 鸿富锦精密工业(深圳)有限公司 | Memory test method and system |
CN106681868A (en) * | 2015-11-10 | 2017-05-17 | 技嘉科技股份有限公司 | Image data testing method and system |
CN106384364A (en) * | 2016-08-31 | 2017-02-08 | 天津大学 | LPP-ELM based objective stereoscopic image quality evaluation method |
JP6757378B2 (en) * | 2018-08-28 | 2020-09-16 | 株式会社モルフォ | Image identification device, image identification method and image identification program |
-
2020
- 2020-04-14 CN CN202010290292.2A patent/CN111507393B/en active Active
- 2020-11-18 WO PCT/CN2020/129654 patent/WO2021208424A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101777326A (en) * | 2009-01-09 | 2010-07-14 | 深圳宝龙达信息技术股份有限公司 | VGA video card test tooling and method |
CN104023224A (en) * | 2014-03-31 | 2014-09-03 | 深圳英飞拓科技股份有限公司 | Camera performance detection method and system and server |
CN108696747A (en) * | 2018-04-17 | 2018-10-23 | 青岛海信电器股份有限公司 | A kind of video measurement method and apparatus |
US20200012932A1 (en) * | 2018-07-09 | 2020-01-09 | National Central University | Machine learning method and machine learning device |
CN109815855A (en) * | 2019-01-07 | 2019-05-28 | 中国电子科技集团公司第四十一研究所 | A kind of electronic equipment automatic test approach and system based on machine learning |
CN111507393A (en) * | 2020-04-14 | 2020-08-07 | 艾瑞思检测技术(苏州)有限公司 | Display card interface machine testing method based on Laplace feature mapping learning |
Also Published As
Publication number | Publication date |
---|---|
CN111507393A (en) | 2020-08-07 |
CN111507393B (en) | 2021-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111739075B (en) | Deep network lung texture recognition method combining multi-scale attention | |
WO2021208423A1 (en) | Display card interface machine testing method based on pca learning | |
WO2021208424A1 (en) | Laplacian feature mapping learning-based machine testing method for graphics card interface | |
CN109859163A (en) | A kind of LCD defect inspection method based on feature pyramid convolutional neural networks | |
CN109829895A (en) | A kind of AOI defect inspection method based on GAN | |
CN112102229A (en) | Intelligent industrial CT detection defect identification method based on deep learning | |
CN112070134A (en) | Power equipment image classification method and device, power equipment and storage medium | |
CN110045015A (en) | A kind of concrete structure Inner Defect Testing method based on deep learning | |
CN113920107A (en) | Insulator damage detection method based on improved yolov5 algorithm | |
CN109978872B (en) | White matter microstructure characteristic screening system and method based on white matter fiber tracts | |
CN111753873A (en) | Image detection method and device | |
CN111222545B (en) | Image classification method based on linear programming incremental learning | |
CN113435282A (en) | Unmanned aerial vehicle image ear recognition method based on deep learning | |
CN108427970A (en) | Picture mask method and device | |
CN115830004A (en) | Surface defect detection method, device, computer equipment and storage medium | |
CN111680738A (en) | Screening device for apple quality detection and detection method thereof | |
CN113706496B (en) | Aircraft structure crack detection method based on deep learning model | |
CN111078565A (en) | Analysis method of software test result based on HOG feature extraction and SVM multi-classifier | |
CN110363196A (en) | It is a kind of tilt text text precisely know method for distinguishing | |
CN113962980A (en) | Glass container flaw detection method and system based on improved YOLOV5X | |
CN116485766A (en) | Grain imperfect grain detection and counting method based on improved YOLOX | |
CN116958073A (en) | Small sample steel defect detection method based on attention feature pyramid mechanism | |
CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
Maningo et al. | Crack detection with 2D wall mapping for building safety inspection | |
CN113344006A (en) | Polarization image analysis method adopting learnable parameter fusion network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20930811 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20930811 Country of ref document: EP Kind code of ref document: A1 |