CN113034482A - Surface roughness detection method based on machine vision and machine learning - Google Patents
Surface roughness detection method based on machine vision and machine learning Download PDFInfo
- Publication number
- CN113034482A CN113034482A CN202110372321.4A CN202110372321A CN113034482A CN 113034482 A CN113034482 A CN 113034482A CN 202110372321 A CN202110372321 A CN 202110372321A CN 113034482 A CN113034482 A CN 113034482A
- Authority
- CN
- China
- Prior art keywords
- machine
- characteristic index
- image
- surface roughness
- index vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a surface roughness detection method based on machine vision and machine learning, which is applied to the technical field of roughness detection and comprises the following steps: s1, acquiring an image of the surface of the object by using a machine vision method, and carrying out image preprocessing on the acquired image to obtain a processed image; s2, calculating the processed image and extracting the characteristic index value of the texture to form a characteristic index vector; s3, establishing a linear mapping relation model between the object surface roughness and the characteristic index vector by using a machine learning method; s4 obtains the texture characteristic index vector of the surface of the object to be measured by utilizing S1 and S2, and inputs the texture characteristic index vector into the model in S3 to obtain the surface roughness of the object to be measured. The invention constructs an effective linear mapping relation model between the object image characteristic index vector and the roughness, realizes non-contact and rapid measurement of the object surface roughness and reduces the detection cost.
Description
Technical Field
The invention relates to the technical field of roughness detection, in particular to a surface roughness detection method based on machine vision and machine learning.
Background
Grinding is one of the most widely applied precision machining methods in the mechanical manufacturing industry, and is generally used as a final process of precision machining of parts to ensure the shape precision and roughness requirement of the surfaces of the parts, the surface roughness is one of important indexes for evaluating the surface quality, is the microscopic geometric shape deviation consisting of smaller intervals and peaks and valleys on the machined surfaces of workpieces, and is mainly characterized in that abrasive particles on the surfaces of grinding wheels are gradually dull due to the action of grinding force and grinding heat in the grinding process, so that the surface quality and the geometric precision of the machined parts are seriously influenced, and the subsequent working performance of the parts is seriously influenced.
At present, for the detection of surface roughness, the detection of a contact pin type contourgraph is wide, but a contact pin is in direct contact with a detected surface, so that scratches on the surface of a workpiece cannot be avoided, the detection sampling is linear sampling, the characteristics of the whole surface profile cannot be represented, and the measurement efficiency is low; the non-contact roughness detection method mainly comprises optical detection, electronic detection and the like, but has the defects of small measurement area, high price of a detection instrument, low efficiency and the like, so that the non-contact roughness detection method is not applied in a large scale in the industrial field. In recent years, the roughness detection method based on machine vision is gradually emphasized, but an effective mapping model between a characteristic index and roughness is lacked in the detection process, so that the detection accuracy and efficiency are reduced.
Therefore, it is an urgent need to solve the problems of the prior art by providing a surface roughness detecting method using machine vision and machine learning to overcome the difficulties in the prior art.
Disclosure of Invention
In view of this, the invention provides a surface roughness detection method based on machine vision and machine learning, which can be used for conveniently, rapidly and non-contact and rapid measurement of the surface roughness of an object, and reduces the technical effect of detection cost.
In order to achieve the purpose, the invention adopts the following technical scheme:
the surface roughness detection method based on machine vision and machine learning comprises the following steps:
s1, acquiring an image of the surface of the object, and performing image preprocessing on the acquired image to obtain a processed image;
s2, calculating the processed image and extracting the characteristic index value of the texture to form a characteristic index vector;
s3, establishing a linear mapping relation model between the object surface roughness and the characteristic index vector;
and S4, acquiring the texture characteristic index vector of the surface of the object to be detected by utilizing the S1 and the S2, and inputting the texture characteristic index vector into the model in the S3 to obtain the surface roughness of the object to be detected.
Preferably, S1 specifically includes the following:
acquiring an image of the surface of an object by using a machine vision method: acquiring an image of the surface of an object through a machine vision acquisition device;
carrying out image preprocessing on the acquired image: and carrying out gray level conversion, median filtering and gray level enhancement processing on the image by using an image preprocessing program.
Preferably, the machine vision acquisition device comprises: the device comprises an industrial camera, an industrial lens, a light source controller, a fixed support and a computer.
Preferably, the image pre-processing program is programmed in a LabVIEW software platform matched with the machine vision acquisition device.
Preferably, S2 specifically includes the following:
and obtaining a characteristic index value of the image texture of the preprocessed image by utilizing the gray level co-occurrence matrix, and extracting the characteristic index value of the texture by LabVIEW software to form a characteristic index vector.
Preferably, the characteristic index values are respectively: one or more of energy, contrast, entropy, homogeneity, variability, and correlation.
Preferably, S3 specifically includes the following:
and obtaining a linear mapping relation model of the roughness of the object and the characteristic index vector by a clustering method, and forming a database for storing the roughness of the object and the characteristic index vector.
Preferably, S4 specifically includes the following:
and the object to be detected obtains the texture characteristic index vector of the surface of the object to be detected through S1 and S2, inputs the texture characteristic index vector into the linear mapping relation model of S3, obtains the roughness value corresponding to the texture characteristic index vector, and outputs the roughness value as a result.
According to the technical scheme, compared with the prior art, the surface roughness detection method based on machine vision and machine learning is provided, and comprises the following steps: the invention integrates image acquisition, image preprocessing and image roughness detection into a whole by utilizing a machine vision technology and a machine learning technology, and is convenient and quick; an effective linear mapping relation model between the object image characteristic index vector and the roughness is established by utilizing a machine learning technology, the current situation that the traditional detection method is discrete or lacks a mapping model is changed, the non-contact and rapid measurement of the object surface roughness is realized, and the detection cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the surface roughness detection method based on machine vision and machine learning according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1, the invention discloses a surface roughness detection method based on machine vision and machine learning, comprising the following steps:
s1, acquiring an image of the surface of the object, and performing image preprocessing on the acquired image to obtain a processed image;
s2, calculating the processed image and extracting the characteristic index value of the texture to form a characteristic index vector;
s3, establishing a linear mapping relation model between the object surface roughness and the characteristic index vector;
and S4, acquiring the texture characteristic index vector of the surface of the object to be detected by utilizing the S1 and the S2, and inputting the texture characteristic index vector into the model in the S3 to obtain the surface roughness of the object to be detected.
In a specific embodiment, S1 specifically includes the following:
acquiring an image of the surface of an object by using a machine vision method: acquiring an image of the surface of an object through a machine vision acquisition device;
carrying out image preprocessing on the acquired image: and carrying out gray level conversion, median filtering and gray level enhancement processing on the image by using an image preprocessing program.
In one particular embodiment, a machine vision acquisition device includes: the device comprises an industrial camera, an industrial lens, a light source controller, a fixed support and a computer.
In one embodiment, the image pre-processing program is programmed in a LabVIEW software platform matched to the machine vision acquisition device.
In a specific embodiment, S2 specifically includes the following:
and obtaining a characteristic index value of the image texture of the preprocessed image by utilizing the gray level co-occurrence matrix, and extracting the characteristic index value of the texture by LabVIEW software to form a characteristic index vector.
In one embodiment, the characteristic index values are respectively: one or more of energy, contrast, entropy, homogeneity, variability, and correlation.
In a specific embodiment, S3 specifically includes the following:
and obtaining a linear mapping relation model of the roughness of the object and the characteristic index vector by a clustering method, and forming a database for storing the roughness of the object and the characteristic index vector.
In a specific embodiment, S4 specifically includes the following:
and the object to be detected obtains the texture characteristic index vector of the surface of the object to be detected through S1 and S2, inputs the texture characteristic index vector into the linear mapping relation model of S3, obtains the roughness value corresponding to the texture characteristic index vector, and outputs the roughness value as a result.
In one particular embodiment, the characteristic index value: the energy, contrast, entropy, homogeneity, difference and correlation calculation method comprises the following steps:
1) energy: the degree of uniformity and the thickness of the texture of the gray scale distribution of the reaction image are shown in the following formula
2) Contrast ratio: reflecting the definition of the image and the depth of the texture grooves, as shown in the following formula
3) Entropy: representing the degree of non-uniformity or complexity of the texture in the image, as shown in
4) Homogeneity: reflecting how much the texture of the image is locally changed, as shown in the following formula
5) Difference: the degree of the sharpness and the depth of the texture groove of the image is reflected together with the contrast, as shown in the following formula
6) Correlation: reflecting the degree of similarity of the matrix elements in the row or column direction, as shown in the following,
wherein, in 1) -6), L × L is the number of rows and columns in the image gray matrix, p (i, j) is the matrix value of i rows and j columns in the gray matrix, μxIs the mean of j rows, μyIs the mean value of i rows, δxIs the standard deviation of j rows, δyIs the standard deviation of the i rows.
In one embodiment, the characteristic index value of the texture is extracted by LabVIEW software to form a characteristic index vector, wherein f is [ f [ [ f ]1,f2,f3,f4,f5,f6]-1。
In one embodiment, referring to fig. 1, a flow chart for implementing the roughness detection of the present invention is disclosed, which is mainly divided into two modules, machine vision and machine learning.
And in the machine vision module, a machine vision acquisition device and image preprocessing are included.
The machine vision acquisition device consists of an industrial camera, a lens, a light source controller, an object to be detected, a fixed support and a computer. The industrial camera is an important component of a machine vision system, the resolution and the image quality of the acquired image are directly determined by the selection of the camera, and a proper camera is selected according to the detected object and the environment. The basic function of the lens is to achieve beam transformation. The light source plays the effect of illumination light filling to the device, and suitable illumination scheme often concerns the success or failure of whole system. The light source controller is used for controlling the brightness and the intensity of the light source. The fixed support is used for providing work support for the camera, the lens, the light source and the object to be measured. The computer is used to transmit and process images taken by the camera.
The image preprocessing is to perform operations such as image gray level conversion, image filtering, gray level enhancement and the like on an original collected image, and is beneficial to quickly and accurately extracting image characteristic information in subsequent work. In the process, the gray level of an image is converted by using a program written in LabVIEW software, and a single gray level color plane is extracted. Meanwhile, in the process of digital image acquisition and transmission, due to the influence of external factors such as light, temperature, equipment vibration and the like, noise interference is doped, the quality of the image is reduced, the difficulty of image analysis and identification is increased, and image filtering is a processing mode for eliminating noise, improving the signal-to-noise ratio and improving the image quality. The median filtering is a nonlinear low-pass filtering method, and a program is written in LabVIEW software to realize the function of the median filtering. After the image is acquired, in order to make the information of the target object more prominent in the background and to facilitate the identification of the target object, the image needs to be enhanced, and the gray level of the image needs to be stretched or compressed by performing mathematical operation on the gray level of the image. The gray scale transformation is a mode of image enhancement, and a program is written in LabVIEW to realize the function of the gray scale transformation of the image.
In the machine learning module, the construction of a characteristic index vector and the construction of a linear relation model are included.
Texture is an inherent property of the image surface and has periodicity, so the gray values of pixels in adjacent periods also have some spatial correlation. The gray level co-occurrence matrix was proposed by Haralick in 1973, and the core idea is to describe texture features by studying the spatial correlation characteristics of pixel gray levels. Based on a gray level co-occurrence matrix, Haralick counts 14 characteristic index values capable of reflecting texture characteristics, the method selects 6 characteristic index values mainly related to roughness, and the calculation process is realized depending on a program written in LabVIEW software. The calculation of the characteristic index values is as described in step 2.1. And then, forming a feature index vector according to each feature index value obtained by calculation.
The linear mapping relation model is constructed by inputting the roughness value of the object sample as a Label, so that each characteristic index vector corresponds to the roughness value of the object sample one by one, and the final result is stored in the classifier. Because each roughness value can correspond to a plurality of feature vectors, a clustering method based on machine learning of a support vector machine is required to be adopted to classify and train samples, and a linear mapping relation model between the feature index vectors and the roughness is obtained.
In the detection process of the object to be detected, firstly, the image of the object to be detected is collected and preprocessed through two parts of contents of machine vision, then, a machine learning module is used for calculating and extracting a characteristic index vector of the object to be detected, the characteristic index vector is further led into a constructed linear mapping relation model, and a roughness value corresponding to the characteristic index vector is found and is output as a result.
In one embodiment, a machine vision acquisition device diagram is disclosed, optionally comprising: the system comprises an industrial camera, an industrial lens, a light source controller, a fixed bracket 5 and a computer;
an object to be detected is placed under an industrial lens of a fixed support workbench; the light source is clamped and placed between the industrial lens and the object to be detected by the fixing support; the industrial lens is matched with the industrial camera and is clamped by the fixing support, and the industrial camera is connected with the computer. In consideration of the reflection influence of the object to be detected, the light source adopts an LED white coaxial light source, and the illumination is controlled through the light source controller.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention in a progressive manner. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The surface roughness detection method based on machine vision and machine learning is characterized by comprising the following steps of:
s1, acquiring an image of the surface of the object, and performing image preprocessing on the acquired image to obtain a processed image;
s2, calculating the processed image and extracting the characteristic index value of the texture to form a characteristic index vector;
s3, establishing a linear mapping relation model between the object surface roughness and the characteristic index vector;
and S4, acquiring the texture characteristic index vector of the surface of the object to be detected by utilizing the S1 and the S2, and inputting the texture characteristic index vector into the model in the S3 to obtain the surface roughness of the object to be detected.
2. The machine-vision and machine-learning based surface roughness detection method of claim 1,
s1 specifically includes the following:
acquiring an image of the surface of an object by using a machine vision method: acquiring an image of the surface of an object through a machine vision acquisition device;
carrying out image preprocessing on the acquired image: and carrying out gray level conversion, median filtering and gray level enhancement processing on the image by using an image preprocessing program.
3. The machine-vision and machine-learning based surface roughness detection method of claim 2,
the machine vision collection system includes: the device comprises an industrial camera, an industrial lens, a light source controller, a fixed support and a computer.
4. The machine-vision and machine-learning based surface roughness detection method of claim 2,
and programming an image preprocessing program in a LabVIEW software platform matched with the machine vision acquisition device.
5. The machine-vision and machine-learning based surface roughness detection method of claim 1,
s2 specifically includes the following:
and obtaining a characteristic index value of the image texture of the preprocessed image by utilizing the gray level co-occurrence matrix, and extracting the characteristic index value of the texture by LabVIEW software to form a characteristic index vector.
6. The machine-vision and machine-learning based surface roughness detection method of claim 5,
the characteristic index values are respectively: one or more of energy, contrast, entropy, homogeneity, variability, and correlation.
7. The machine-vision and machine-learning based surface roughness detection method of claim 1,
s3 specifically includes the following:
and obtaining a linear mapping relation model of the roughness of the object and the characteristic index vector by a clustering method, and forming a database for storing the roughness of the object and the characteristic index vector.
8. The machine-vision and machine-learning based surface roughness detection method of claim 1,
s4 specifically includes the following:
and the object to be detected obtains the texture characteristic index vector of the surface of the object to be detected through S1 and S2, inputs the texture characteristic index vector into the linear mapping relation model of S3, obtains the roughness value corresponding to the texture characteristic index vector, and outputs the roughness value as a result.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372321.4A CN113034482A (en) | 2021-04-07 | 2021-04-07 | Surface roughness detection method based on machine vision and machine learning |
| AU2021104874A AU2021104874A4 (en) | 2021-04-07 | 2021-08-03 | A surface roughness detection method based on machine vision and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372321.4A CN113034482A (en) | 2021-04-07 | 2021-04-07 | Surface roughness detection method based on machine vision and machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113034482A true CN113034482A (en) | 2021-06-25 |
Family
ID=76453969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110372321.4A Pending CN113034482A (en) | 2021-04-07 | 2021-04-07 | Surface roughness detection method based on machine vision and machine learning |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113034482A (en) |
| AU (1) | AU2021104874A4 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838055A (en) * | 2021-11-29 | 2021-12-24 | 惠民万顺节能新材料有限公司 | System and method for detecting surface roughness uniformity of cold-rolled plate |
| CN114119599A (en) * | 2021-12-08 | 2022-03-01 | 重庆大学 | Surface roughness detection method based on image interesting region extraction |
| CN116203031A (en) * | 2023-03-24 | 2023-06-02 | 苏州电光波工业智能科技有限公司 | Industrial product defect intelligent detection system based on microwave and machine vision technology |
| CN116448019A (en) * | 2023-06-14 | 2023-07-18 | 山西首科工程质量检测有限公司 | Intelligent detection device and method for quality flatness of building energy-saving engineering |
| CN117934461A (en) * | 2024-03-21 | 2024-04-26 | 广州航海学院 | Method, system and equipment for analyzing polishing surface roughness of side polishing optical fiber |
| CN118009934A (en) * | 2024-02-02 | 2024-05-10 | 惠州市双诚鑫科技有限公司 | Method and system for detecting surface roughness of optical lens |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103759676A (en) * | 2014-01-06 | 2014-04-30 | 南京信息工程大学 | Non-contact type workpiece surface roughness detecting method |
| CN104848808A (en) * | 2015-06-03 | 2015-08-19 | 湖南大学 | Surface roughness detection method and equipment |
| CN105243450A (en) * | 2015-10-16 | 2016-01-13 | 华北电力大学 | Method and system for predicting surface roughness of alternating-current conducting wire |
| CN108428231A (en) * | 2018-03-19 | 2018-08-21 | 南京信息工程大学 | A kind of multi-parameter Part Surface Roughness learning method based on random forest |
| CN109191433A (en) * | 2018-07-31 | 2019-01-11 | 华南理工大学 | Flexible IC substrate covers the micro-imaging detection method of copper surface roughness Ra |
| CN109840899A (en) * | 2018-12-20 | 2019-06-04 | 上海理工大学 | A kind of roughness grade number recognition methods based on depth convolutional neural networks |
| CN110110758A (en) * | 2019-04-15 | 2019-08-09 | 南京航空航天大学 | A kind of surface roughness classification method based on convolutional neural networks |
| CN110411380A (en) * | 2019-08-01 | 2019-11-05 | 合肥工业大学 | Non-contact Surface Roughness Measurement method based on wavelet package texture analysis |
| CN110793472A (en) * | 2019-11-11 | 2020-02-14 | 桂林理工大学 | Grinding surface roughness detection method based on quaternion singular value entropy index |
| CN112435217A (en) * | 2020-11-02 | 2021-03-02 | 上海祐云信息技术有限公司 | Algorithm for recognizing rough surface of prefabricated reinforced concrete by image |
-
2021
- 2021-04-07 CN CN202110372321.4A patent/CN113034482A/en active Pending
- 2021-08-03 AU AU2021104874A patent/AU2021104874A4/en not_active Ceased
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103759676A (en) * | 2014-01-06 | 2014-04-30 | 南京信息工程大学 | Non-contact type workpiece surface roughness detecting method |
| CN104848808A (en) * | 2015-06-03 | 2015-08-19 | 湖南大学 | Surface roughness detection method and equipment |
| CN105243450A (en) * | 2015-10-16 | 2016-01-13 | 华北电力大学 | Method and system for predicting surface roughness of alternating-current conducting wire |
| CN108428231A (en) * | 2018-03-19 | 2018-08-21 | 南京信息工程大学 | A kind of multi-parameter Part Surface Roughness learning method based on random forest |
| CN109191433A (en) * | 2018-07-31 | 2019-01-11 | 华南理工大学 | Flexible IC substrate covers the micro-imaging detection method of copper surface roughness Ra |
| CN109840899A (en) * | 2018-12-20 | 2019-06-04 | 上海理工大学 | A kind of roughness grade number recognition methods based on depth convolutional neural networks |
| CN110110758A (en) * | 2019-04-15 | 2019-08-09 | 南京航空航天大学 | A kind of surface roughness classification method based on convolutional neural networks |
| CN110411380A (en) * | 2019-08-01 | 2019-11-05 | 合肥工业大学 | Non-contact Surface Roughness Measurement method based on wavelet package texture analysis |
| CN110793472A (en) * | 2019-11-11 | 2020-02-14 | 桂林理工大学 | Grinding surface roughness detection method based on quaternion singular value entropy index |
| CN112435217A (en) * | 2020-11-02 | 2021-03-02 | 上海祐云信息技术有限公司 | Algorithm for recognizing rough surface of prefabricated reinforced concrete by image |
Non-Patent Citations (7)
| Title |
|---|
| 吴春亚: "基于机器视觉的磨削表面粗糙度检测", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 张卿: "基于机器视觉的齿轮齿面粗糙度检测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技||辑》 * |
| 张斌: "打磨工件缺陷及粗糙度的视觉在线检测***研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 戴琨等: "数字图像技术在铸件表面粗糙度检测中的应用研究", 《铸造技术》 * |
| 臧俊涛: "基于机器视觉与机器学习的磨削齿面粗糙度测量研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技|辑》 * |
| 闵莉等: "基于BP神经网络的车削表面粗糙度检测", 《沈阳建筑大学学报(自然科学版)》 * |
| 陈毅: "基于数字图像的机械加工表面质量检测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技||辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838055A (en) * | 2021-11-29 | 2021-12-24 | 惠民万顺节能新材料有限公司 | System and method for detecting surface roughness uniformity of cold-rolled plate |
| CN114119599A (en) * | 2021-12-08 | 2022-03-01 | 重庆大学 | Surface roughness detection method based on image interesting region extraction |
| CN116203031A (en) * | 2023-03-24 | 2023-06-02 | 苏州电光波工业智能科技有限公司 | Industrial product defect intelligent detection system based on microwave and machine vision technology |
| CN116448019A (en) * | 2023-06-14 | 2023-07-18 | 山西首科工程质量检测有限公司 | Intelligent detection device and method for quality flatness of building energy-saving engineering |
| CN116448019B (en) * | 2023-06-14 | 2023-08-25 | 山西首科工程质量检测有限公司 | Intelligent detection device and method for quality flatness of building energy-saving engineering |
| CN118009934A (en) * | 2024-02-02 | 2024-05-10 | 惠州市双诚鑫科技有限公司 | Method and system for detecting surface roughness of optical lens |
| CN117934461A (en) * | 2024-03-21 | 2024-04-26 | 广州航海学院 | Method, system and equipment for analyzing polishing surface roughness of side polishing optical fiber |
| CN117934461B (en) * | 2024-03-21 | 2024-06-07 | 广州航海学院 | Method, system and equipment for analyzing polishing surface roughness of side polishing optical fiber |
Also Published As
| Publication number | Publication date |
|---|---|
| AU2021104874A4 (en) | 2021-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034482A (en) | Surface roughness detection method based on machine vision and machine learning | |
| CN108332689B (en) | Optical measurement system and method for detecting surface roughness and surface damage | |
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN111612737B (en) | Artificial board surface flaw detection device and detection method | |
| CN105783723B (en) | Precision die surface processing accuracy detection device and method based on machine vision | |
| Abouelatta | 3D surface roughness measurement using a light sectioning vision system | |
| CN109211110A (en) | A kind of flat-type workpiece size detection system and method based on machine vision | |
| CN112345539A (en) | Aluminum die casting surface defect detection method based on deep learning | |
| CN110544231A (en) | lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| CN109182081A (en) | A kind of unicellular separation system based on image processing model | |
| JP2020532122A (en) | Defect detection for transparent or translucent wafers | |
| CN111445471A (en) | Product surface defect detection method and device based on deep learning and machine vision | |
| CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
| CN115979183A (en) | Laser polishing surface roughness on-machine detection method for 3D printing workpiece | |
| CN113327243B (en) | PAD light guide plate defect visual detection method based on Ayolov3-Tiny new framework | |
| CN117085969B (en) | Artificial intelligence industrial vision detection method, device, equipment and storage medium | |
| CN109785290A (en) | Normalized steel plate defect detection method is shone based on local light | |
| CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| CN115753791B (en) | Defect detection method, device and system based on machine vision | |
| CN109063738B (en) | Automatic online detection method for compressed sensing ceramic water valve plate | |
| Chebrolu et al. | Automated Evaluation of Surface Roughness using Machine Vision based Intelligent Systems | |
| Guo et al. | FE-trans-net: Feature enhancement based single branch deep learning model for surface roughness detection | |
| CN112857216B (en) | Method, apparatus, system and medium for checking dimensional compliance of fastener | |
| Bharat et al. | Surface finish evaluation using curvelet transforms based machine vision system | |
| Dar et al. | Field surface roughness levelling of the lapping metal surface using specular white light |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |