CN109359703A - A kind of ceramic tile grade separation method based on decision tree - Google Patents
A kind of ceramic tile grade separation method based on decision tree Download PDFInfo
- Publication number
- CN109359703A CN109359703A CN201811556156.2A CN201811556156A CN109359703A CN 109359703 A CN109359703 A CN 109359703A CN 201811556156 A CN201811556156 A CN 201811556156A CN 109359703 A CN109359703 A CN 109359703A
- Authority
- CN
- China
- Prior art keywords
- scoring
- ceramic tile
- flatness
- result
- decision
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30168—Image quality inspection
Abstract
The ceramic tile grade separation method based on decision tree that the invention discloses a kind of, comprising the following steps: establish decision-tree model;Image Acquisition operation is carried out to ceramic tile to be measured, obtains testing image;Image pretreatment operation is carried out to the testing image;Carry out acetes chinensis, surface defects detection and flatness detection;Obtain color difference scoring, surface defect scoring and flatness scoring;Color difference scoring, surface defect scoring and flatness scoring are input in decision-tree model, the decision-tree model exports the grade separation result of ceramic tile to be measured.Judgment criteria of the technical program using the acetes chinensis result, surface defects detection result and flatness detection results of ceramic tile as ceramic tile credit rating, using decision-tree model according to the credit rating of acetes chinensis result, surface defects detection result and flatness detection results comprehensive descision ceramic tile, intelligence degree is high, detection speed is fast, realizes and carries out comprehensively unified detection to each ceramic tile.
Description
Technical field
The present invention relates to intelligent identification technology fields, lead more specifically to a kind of ceramic tile grade separation method and technology
Domain.
Background technique
Development of Real Estate Market is rapid at present, has fundamentally driven Decoration Industry fast-developing, annual Decoration Industry pair
The demand of ceramic tile is extremely huge.
Ceramic tile manufacturing enterprise often formulates specific selling price according to ceramic tile grade produced, but how to judge porcelain
Brick grade becomes a great problem for perplexing each quarry-tile manufacturing enterprise, and the detection method of those skilled in the art's routine is mainly
The quality that certain index parameters of ceramic tile are judged by artificial or machine integrally judges one by the combination of each index parameter
The credit rating of a ceramic tile judges that process is cumbersome to the credit rating of ceramic tile in the prior art, and intelligence degree is low, results in pair
The credit rating detection of ceramic tile can only be carried out by the way of sampling, cause quality in tile product by the gross irregular.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of ceramic tile grade separation method based on decision tree.
The solution that the present invention solves its technical problem is:
A kind of ceramic tile grade separation method based on decision tree, comprising the following steps:
Step 100, decision-tree model is established;
Step 200, Image Acquisition operation is carried out to ceramic tile to be measured, obtains testing image;
Step 300, image pretreatment operation is carried out to the testing image;
Step 400, to the testing image after image pretreatment operation, carry out acetes chinensis, surface defects detection with
And flatness detection;
Step 500, according to the acetes chinensis result of step 400, surface defects detection result and flatness detection results,
Obtain color difference scoring, surface defect scoring and flatness scoring;
Step 600, color difference scoring, surface defect scoring and flatness scoring are input in decision-tree model,
The decision-tree model exports the grade separation result of ceramic tile to be measured.
As a further improvement of the above technical scheme, step 100 the following steps are included:
Step 110, from top and under set gradually root node layer, the first child node layer, the second child node layer and leaf node
Layer;
Step 120, the node of the node of the root node layer, the node of the first child node layer and the second child node layer is enabled
It is corresponding with color difference scoring, surface defect scoring and flatness scoring that one is selected respectively;
Step 130, the section of the node of the root node layer, the node of the first child node layer and the second child node layer is set
The branch condition of point, the branch condition on every node layer are set as two or three.
It as a further improvement of the above technical scheme, further include step 140 after step 130, to the decision tree mould
Type carries out cut operator.
As a further improvement of the above technical scheme, the step 300 the following steps are included:
Step 310, gray processing processing is carried out to the testing image;
Step 320, noise is carried out to the testing image to consider except processing;
Step 330, Threshold segmentation operation is carried out to the testing image, obtains the testing image of removal background information.
As a further improvement of the above technical scheme, in step 500 the following steps are included:
Step 510, respectively standard is arranged in acetes chinensis result, surface defects detection result and flatness detection results
Value;
Step 520, respectively acetes chinensis result, surface defects detection result and flatness detection results setting first
Threshold range, second threshold range and third threshold range, the first threshold range, second threshold range and third threshold
Value range successively becomes larger;
Step 530, judge that acetes chinensis result, surface defects detection result and flatness detection results and institute are right respectively
Which threshold range is the difference for the standard value answered belong to;
Step 540, according to acetes chinensis result, surface defects detection result and flatness detection results and corresponding
Threshold range belonging to the difference of standard value, the scoring of output color difference, surface defect scoring and flatness scoring.
The beneficial effects of the present invention are: the present invention is with the acetes chinensis result of ceramic tile, surface defects detection result and puts down
Judgment criteria of the whole degree testing result as ceramic tile credit rating is lacked using decision-tree model according to acetes chinensis result, surface
The credit rating of testing result and flatness detection results comprehensive descision ceramic tile is fallen into, intelligence degree is high, and detection speed is fast, real
Comprehensively unified detection is now carried out to each ceramic tile.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described.Obviously, described attached drawing is a part of the embodiments of the present invention, rather than is all implemented
Example, those skilled in the art without creative efforts, can also be obtained according to these attached drawings other designs
Scheme and attached drawing.
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this Shen
A part of the embodiment please, rather than whole embodiments, are based on embodiments herein, and those skilled in the art is not paying
Other embodiments obtained under the premise of creative work belong to the range of the application protection.
Referring to Fig.1, the ceramic tile grade separation method based on decision tree that this application discloses a kind of, comprising the following steps:
Step 100, decision-tree model is established;
Step 200, Image Acquisition operation is carried out to ceramic tile to be measured, obtains testing image;
Step 300, image pretreatment operation is carried out to the testing image;
Step 400, to the testing image after image pretreatment operation, carry out acetes chinensis, surface defects detection with
And flatness detection;
Step 500, according to the acetes chinensis result of step 400, surface defects detection result and flatness detection results,
Obtain color difference scoring, surface defect scoring and flatness scoring;
Step 600, color difference scoring, surface defect scoring and flatness scoring are input in decision-tree model,
The decision-tree model exports the grade separation result of ceramic tile to be measured.
Specifically, the technical program is with the acetes chinensis result, surface defects detection result and flatness detection of ceramic tile
As a result the judgment criteria as ceramic tile credit rating, using decision-tree model according to acetes chinensis result, surface defects detection knot
The credit rating of fruit and flatness detection results comprehensive descision ceramic tile, intelligence degree is high, and detection speed is fast, realizes to each
Ceramic tile carries out comprehensively unified detection.
Be further used as preferred embodiment, in the application specific embodiment, step 100 the following steps are included:
Step 110, from top and under set gradually root node layer, the first child node layer, the second child node layer and leaf node
Layer;
Step 120, the node of the node of the root node layer, the node of the first child node layer and the second child node layer is enabled
It is corresponding with color difference scoring, surface defect scoring and flatness scoring that one is selected respectively;
Step 130, the section of the node of the root node layer, the node of the first child node layer and the second child node layer is set
The branch condition of point, the branch condition on every node layer are set as two or three.
Specifically, in actual application, the section of root node layer freely can be freely set according to tile type detected
Point, the node of the node of the first child node layer and the second child node layer and color difference scoring, surface defect scoring and flatness
The corresponding relationship and setting branch node of scoring.It should be noted that being characterized in since different types of ceramic tile is of interest
It is different, such as polished bricks feature of greatest concern is flatness, and glazed tile feature of greatest concern is color difference, root knot
Feature scoring corresponding to the node of point layer can regard as ceramic tile to be measured feature of greatest concern, i.e. the technical program can be free
The priority of color difference scoring, surface defect scoring and flatness scoring is set.
It is further used as preferred embodiment, further includes step after step 130 in the application specific embodiment
140, cut operator is carried out to the decision-tree model, effectively simplifies the calculation process of ceramic tile credit rating deterministic process, reduces
Overall calculation number improves credit rating detection efficiency.
It is further used as preferred embodiment, in the application specific embodiment, the step 300 includes following step
It is rapid:
Step 310, gray processing processing is carried out to the testing image;
Step 320, noise is carried out to the testing image to consider except processing;
Step 330, Threshold segmentation operation is carried out to the testing image, obtains the testing image of removal background information.
Be further used as preferred embodiment, in the application specific embodiment, in step 500 the following steps are included:
Step 510, respectively standard is arranged in acetes chinensis result, surface defects detection result and flatness detection results
Value;
Step 520, respectively acetes chinensis result, surface defects detection result and flatness detection results setting first
Threshold range, second threshold range and third threshold range, the first threshold range, second threshold range and third threshold
Value range successively becomes larger;
Step 530, judge that acetes chinensis result, surface defects detection result and flatness detection results and institute are right respectively
Which threshold range is the difference for the standard value answered belong to;
Step 540, according to acetes chinensis result, surface defects detection result and flatness detection results and corresponding
Threshold range belonging to the difference of standard value, the scoring of output color difference, surface defect scoring and flatness scoring.
The better embodiment of the application is illustrated above, but the application is not limited to the specific embodiments,
Those skilled in the art can also make various equivalent modifications or replacement on the premise of without prejudice to spirit of the invention, this
Equivalent variation or replacement are all included in the scope defined by the claims of the present application a bit.
Claims (5)
1. a kind of ceramic tile grade separation method based on decision tree, which comprises the following steps:
Step 100, decision-tree model is established;
Step 200, Image Acquisition operation is carried out to ceramic tile to be measured, obtains testing image;
Step 300, image pretreatment operation is carried out to the testing image;
Step 400, to the testing image after image pretreatment operation, acetes chinensis, surface defects detection is carried out and is put down
Whole degree detection;
Step 500, it according to the acetes chinensis result of step 400, surface defects detection result and flatness detection results, obtains
Color difference scoring, surface defect scoring and flatness scoring;
Step 600, color difference scoring, surface defect scoring and flatness scoring are input in decision-tree model, it is described
Decision-tree model exports the grade separation result of ceramic tile to be measured.
2. a kind of ceramic tile grade separation method based on decision tree according to claim 1, which is characterized in that step 100
The following steps are included:
Step 110, from top and under set gradually root node layer, the first child node layer, the second child node layer and leaf node layer;
Step 120, the node of the node of the root node layer, the node of the first child node layer and the second child node layer is enabled to distinguish
It is corresponding with color difference scoring, surface defect scoring and flatness scoring to select one;
Step 130, the node of the node of the root node layer, the node of the first child node layer and the second child node layer is set
Branch condition, the branch condition on every node layer are set as two or three.
3. a kind of ceramic tile grade separation method based on decision tree according to claim 2, which is characterized in that step 130
Later further include step 140, cut operator is carried out to the decision-tree model.
4. a kind of ceramic tile grade separation method based on decision tree according to claim 2, which is characterized in that the step
300 the following steps are included:
Step 310, gray processing processing is carried out to the testing image;
Step 320, noise is carried out to the testing image to consider except processing;
Step 330, Threshold segmentation operation is carried out to the testing image, obtains the testing image of removal background information.
5. a kind of ceramic tile grade separation method based on decision tree according to claim 1, which is characterized in that step 500
In the following steps are included:
Step 510, respectively standard value is arranged in acetes chinensis result, surface defects detection result and flatness detection results;
Step 520, respectively first threshold is arranged in acetes chinensis result, surface defects detection result and flatness detection results
Range, second threshold range and third threshold range, the first threshold range, second threshold range and third threshold value model
It encloses and successively becomes larger;
Step 530, acetes chinensis result, surface defects detection result and flatness detection results and corresponding are judged respectively
Which threshold range is the difference of standard value belong to;
Step 540, according to acetes chinensis result, surface defects detection result and flatness detection results and corresponding standard
Threshold range belonging to the difference of value, the scoring of output color difference, surface defect scoring and flatness scoring.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811556156.2A CN109359703A (en) | 2018-12-19 | 2018-12-19 | A kind of ceramic tile grade separation method based on decision tree |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811556156.2A CN109359703A (en) | 2018-12-19 | 2018-12-19 | A kind of ceramic tile grade separation method based on decision tree |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109359703A true CN109359703A (en) | 2019-02-19 |
Family
ID=65329127
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811556156.2A Pending CN109359703A (en) | 2018-12-19 | 2018-12-19 | A kind of ceramic tile grade separation method based on decision tree |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109359703A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113096073A (en) * | 2021-03-19 | 2021-07-09 | 浙江华睿科技有限公司 | Method and device for detecting surface flatness of chemical fiber spindle |
CN113408573A (en) * | 2021-05-11 | 2021-09-17 | 广东工业大学 | Method and device for automatically classifying and classifying tile color numbers based on machine learning |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104394385A (en) * | 2014-12-10 | 2015-03-04 | 华南师范大学 | Online detection device and detection method for ceramic tile quality |
CN106558046A (en) * | 2016-10-31 | 2017-04-05 | 深圳市飘飘宝贝有限公司 | A kind of quality determining method and detection means of certificate photo |
CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
CN107507161A (en) * | 2016-06-14 | 2017-12-22 | 科大讯飞股份有限公司 | A kind of evaluation method and system for writing tidiness |
CN206808452U (en) * | 2017-06-02 | 2017-12-29 | 刘国群 | A kind of Intelligent fish tank |
CN108863298A (en) * | 2018-07-17 | 2018-11-23 | 佛山高明顺成陶瓷有限公司 | A kind of the Shi ceramic tile and its production technology of high rigidity and high water absorbing capacity |
-
2018
- 2018-12-19 CN CN201811556156.2A patent/CN109359703A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104394385A (en) * | 2014-12-10 | 2015-03-04 | 华南师范大学 | Online detection device and detection method for ceramic tile quality |
CN107507161A (en) * | 2016-06-14 | 2017-12-22 | 科大讯飞股份有限公司 | A kind of evaluation method and system for writing tidiness |
CN106558046A (en) * | 2016-10-31 | 2017-04-05 | 深圳市飘飘宝贝有限公司 | A kind of quality determining method and detection means of certificate photo |
CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
CN206808452U (en) * | 2017-06-02 | 2017-12-29 | 刘国群 | A kind of Intelligent fish tank |
CN108863298A (en) * | 2018-07-17 | 2018-11-23 | 佛山高明顺成陶瓷有限公司 | A kind of the Shi ceramic tile and its production technology of high rigidity and high water absorbing capacity |
Non-Patent Citations (3)
Title |
---|
佛山高明顺成陶瓷有限公司: "Q/MSC 1-2017", 《佛山高明顺成陶瓷有限公司企业标准》 * |
施泉生等: "《电力企业决策支持系统原理及应用》", 31 October 2007, 中国电力出版社 * |
邓亚芳: "基于决策树的瓷砖图像分类方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113096073A (en) * | 2021-03-19 | 2021-07-09 | 浙江华睿科技有限公司 | Method and device for detecting surface flatness of chemical fiber spindle |
CN113096073B (en) * | 2021-03-19 | 2022-10-18 | 浙江华睿科技股份有限公司 | Method and device for detecting surface flatness of chemical fiber spindle |
CN113408573A (en) * | 2021-05-11 | 2021-09-17 | 广东工业大学 | Method and device for automatically classifying and classifying tile color numbers based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10082491B2 (en) | Pearl grading method | |
CN107742286B (en) | Method for detecting EL test crack defects of polycrystalline silicon solar cell | |
CN106918594B (en) | Method for on-line analysis of seed cotton color characteristics and impurities | |
CN107315012B (en) | Composite polycrystal-diamond end face collapses the intelligent detecting method at angle | |
CN110070552B (en) | Rock image pore type identification method based on semantic segmentation | |
CN107578409A (en) | A kind of method of the disconnected grid defects detection of solar battery sheet outward appearance | |
CN108943179B (en) | Optimal cutting method for wood surface defects | |
CN104331710B (en) | On off state identifying system | |
CN106934418B (en) | Insulator infrared diagnosis method based on convolution recursive network | |
CN109359703A (en) | A kind of ceramic tile grade separation method based on decision tree | |
CN110111301A (en) | Metal based on frequency-domain transform aoxidizes surface defect visible detection method | |
CN108985337A (en) | A kind of product surface scratch detection method based on picture depth study | |
CN101926501A (en) | Method for classifying tobacco in threshing process of cured tobacco | |
CN106493094A (en) | A kind of detection method of LED chip | |
CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
CN111160451A (en) | Flexible material detection method and storage medium thereof | |
CN105654099A (en) | Sugarcane segmentation and identification method based on improved vision | |
CN105004722A (en) | Method for rapidly detecting maturity of tobacco leaves | |
CN105740521B (en) | Small grid elimination method and device during reservoir numerical simulation system solution | |
Yang et al. | Wood veneer defect detection system based on machine vision | |
CN107563990B (en) | Detection method for edge breakage, blunt type and V-shaped notches of photovoltaic cell | |
CN113570652A (en) | Quantitative analysis method for sandstone reservoir mineral intercrystalline pores based on SEM image | |
CN110458231B (en) | Ceramic product detection method, device and equipment | |
Zhu et al. | A surface fatal defect detection method for magnetic tiles based on semantic segmentation and object detection: IEEE ITAIC (ISSN: 2693-2865) | |
CN208082927U (en) | The automatic storting apparatus of refractory brick |
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 |
Application publication date: 20190219 |
|
RJ01 | Rejection of invention patent application after publication |