CN107274394A - One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium - Google Patents
One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN107274394A CN107274394A CN201710440961.8A CN201710440961A CN107274394A CN 107274394 A CN107274394 A CN 107274394A CN 201710440961 A CN201710440961 A CN 201710440961A CN 107274394 A CN107274394 A CN 107274394A
- Authority
- CN
- China
- Prior art keywords
- filter cloth
- image texture
- database
- gray level
- texture characteristic
- 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
- 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
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Filter cloth defect damage testing method is based on the invention discloses one kind, is comprised the following steps：Image texture extraction step：The image texture characteristic of filter cloth is extracted, and forms database；Analyze judgment step：The image texture characteristic in database is analyzed using the detection of classifier modellings of SVM bis-, and sentences whether the disconnected image texture characteristic area in filter cloth is defect damage zone.The invention also discloses a kind of electronic equipment and computer-readable recording medium.The present invention solves to detect filter cloth open defect there is the problem of filter cloth open defect detection and identification ability is low in the prior art.
Description
Technical field
Filter cloth defect damage testing method, electronics are based on the present invention relates to a kind of detection technique field, more particularly to one kind
Equipment and storage medium.
Background technology
Industrial filter cloth is the filter medium by natural fiber and synthetic fibers weaving, is mainly used in separation of solid and liquid and work
Industry dedusting, synthetic fibers mainly have polypropylene fibre, terylene, polyamide fibre, polyvinyl etc., wherein it is the most commonly used with terylene and polypropylene fibre, with solid-liquid point
From based on, the industrial filter cloth of broad sense also includes various metal material mesh grids such as stainless steel wire, nickel wire, brass wire.
Presently, there is a little weak point, undue dependence in existing commercial cloth open defect detecting system
High performance computer hardware, does not have enough attention to software algorithm.In the prior art, it is general to use feature area field method
Filter cloth open defect is detected, is base when detection identification is carried out to filter cloth open defect using this feature surface area method
In the principle of broken hole printing opacity, its damaged recall rate for penetrability classification is up to 95.46%, and for the breakage for classification of wearing and tearing
Verification and measurement ratio be less than 20%, testing result show for wear and tear classification Detection results it is poor, there is cloth open defect detection and identification
Ability is not high, can only recognize the damaged more obvious, cloth that veining structure structure is uncomplicated, color is dull.
The content of the invention
In order to overcome the deficiencies in the prior art, an object of the present invention is to provide a kind of based on the breakage inspection of filter cloth defect
Survey method, it can solve the problem that detects to filter cloth open defect in the prior art, there is filter cloth open defect detection and identification energy
The problem of power is low.
The second object of the present invention is offer a kind of electronic equipment, and it can solve the problem that lacks to filter cloth breakage in the prior art
Capable detection is trapped into, there is the problem of filter cloth open defect detection and identification ability is low.
The third object of the present invention is to provide a kind of computer-readable recording medium, and it can solve the problem that right in the prior art
Filter cloth open defect is detected there is the problem of filter cloth open defect detection and identification ability is low.
An object of the present invention adopts the following technical scheme that realization：
One kind is based on filter cloth defect damage testing method, comprises the following steps：
Image texture extraction step：The image texture characteristic of filter cloth is extracted, and forms database；
Analyze judgment step：The image texture characteristic in database is divided using the detection of classifier modellings of SVM bis-
Analysis, and sentence whether the disconnected image texture characteristic area in filter cloth is defect damage zone.
Further, image texture extraction step：The image texture characteristic of filter cloth is carried using gray level co-occurrence matrixes
Take, and form database.
Further, the detection of classifier modellings of SVM bis-, if gray level image is F, tonal gradation is L, then calculates gray scale and be total to
The step of raw matrix, is as follows：
(1) the size L of gray level co-occurrence matrixes is calculated according to the tonal gradation of gray level image2；
(2) appoint the point K (x, y) taken in gray level image F, another point Q (x+a, y+b) is taken, by the gray scale of the pixel pair
Value is designated as (i, j)；
(3) order point K is moved on gray level image F, then records (i, j) and distance of each obtained pixel pair
Value；
(4) it is apart in statistical picture FPixel to the frequency N (i, j) of appearance；
(5) the joint frequency N (i, j) that statistics is obtained into every a pair (i, j) appearance is arranged in a square H (i, j), wherein i
It is required gray level co-occurrence matrixes with ith row and jth column, matrix H (i, j) in j difference representing matrixs, or, at normalization
Co-occurrence matrix is built after reason again.
Further, if the sample in database is linear separability, the detection of classifier modellings of SVM bis- are in database
Image texture characteristic directly analyzed.
Further, will using non-linear map if the image texture characteristic in database is linearly inseparable
The sample of low-dimensional linearly inseparable is transformed into high-dimensional feature space, to make its linear separability, then the detection of classifier moulds of SVM bis-
Type method is directly analyzed the image texture characteristic in database.
Further, image texture extraction step：The image texture characteristic of filter cloth is carried out using local binary pattern
Extract, and form database.
The second object of the present invention adopts the following technical scheme that realization：
A kind of electronic equipment, including：Processor；
Memory；And program, its Program is stored in memory, and is configured to by computing device, journey
Sequence includes being used to perform above-mentioned described method.
The third object of the present invention adopts the following technical scheme that realization：
A kind of computer-readable recording medium, is stored thereon with computer program, and the program is executed by processor above-mentioned institute
The method of description.
Compared with prior art, the beneficial effects of the present invention are：
The image texture characteristic of filter cloth is extracted in the present invention, and forms database, using the detection of classifier of SVM bis-
Modelling is analyzed the image texture characteristic in database, and sentences whether the disconnected image texture characteristic area in filter cloth is defect
Damage zone, can accurately recognize the breakage in filter cloth, improve detection and identification ability, can solve to examine filter cloth open defect
Survey, there is the problem of filter cloth open defect detection and identification ability is low.
Brief description of the drawings
Fig. 1 is provided based on a kind of schematic process flow diagram of embodiment in filter cloth defect damage testing method for the present invention；
Fig. 2 is the module schematic block diagram based on damage testing in filter cloth defect damage testing method shown in Fig. 1.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of afoul, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
Embodiment
The filter cloth defect damage testing method of the present invention is mainly used in damage testing field, presently, existing business
There is a little weak point, the high performance computer hardware of undue dependence, to software with cloth open defect detecting system
Algorithm does not have enough attention.In the prior art, it is general that filter cloth open defect is detected using feature area field method, adopt
It is the principle based on broken hole printing opacity, for penetrating when carrying out detection identification to filter cloth open defect with this feature surface area method
Property classification its damaged recall rate be up to 95.46%, and the damage testing rate for classification of wearing and tearing is less than 20%, testing result table
The bright Detection results for classification of wearing and tearing are poor, and it is not high to there is cloth open defect detection and identification ability, can only recognize breakage compared with
For cloth obvious, that veining structure structure is uncomplicated, color is dull.The breakage in filter cloth how is accurately recognized, detection is improved
The problem of identification capability is one extremely difficult, in view of the above-mentioned problems, as shown in figure 1, the invention provides a kind of filter cloth defect
Damage testing method, it comprises the following steps：
Step S1：The image texture characteristic of filter cloth is extracted using gray level co-occurrence matrixes, and forms database, or
Person, is extracted, and form database using local binary pattern to the image texture characteristic of filter cloth.
Step S2：The image texture characteristic in database is analyzed using the detection of classifier modellings of SVM bis-, if number
It is linear separability according to the sample in storehouse, then the detection of classifier modellings of SVM bis- are directly entered to the image texture characteristic in database
Row analysis；It is using non-linear map that low-dimensional is linear not if the image texture characteristic in database is linearly inseparable
The sample that can divide is transformed into high-dimensional feature space, to make its linear separability, and then the detection of classifier modellings of SVM bis- are to data
Image texture characteristic in storehouse is directly analyzed；And sentence whether the disconnected image texture characteristic area in filter cloth is defect damage zone.
Wherein, the detection of classifier modellings of SVM bis-, if gray level image is F, tonal gradation is L, then calculates gray scale symbiosis square
The step of battle array, is as follows：
(1) the size L of gray level co-occurrence matrixes is calculated according to the tonal gradation of gray level image2；
(2) appoint the point K (x, y) taken in gray level image F, another point Q (x+a, y+b) is taken, by the gray scale of the pixel pair
Value is designated as (i, j)；
(3) order point K is moved on gray level image F, then records (i, j) and distance of each obtained pixel pair
Value；
(4) it is apart in statistical picture FPixel to the frequency N (i, j) of appearance；
(5) the joint frequency N (i, j) that statistics is obtained into every a pair (i, j) appearance is arranged in a square H (i, j), wherein i
It is required gray level co-occurrence matrixes with ith row and jth column, matrix H (i, j) in j difference representing matrixs, or, at normalization
Co-occurrence matrix is built after reason again.
The invention discloses a kind of electronic equipment, including processor, memory and program, its Program, which is stored in, to be deposited
In reservoir, and it is configured to by computing device, program includes being used to perform the above method, or the method for the present invention is stored
On readable storage medium, and this method program can be executed by processor.
As shown in Fig. 2 the invention provides a kind of breakage detection system, it includes：
Extraction module and processing module, extraction module are extracted to the image texture characteristic of filter cloth, and form database；
Processing module is analyzed the image texture characteristic in database using the detection of classifier modellings of SVM bis-, and
Whether the disconnected image texture characteristic area sentenced in filter cloth is defect damage zone.
Above-mentioned embodiment is only the preferred embodiment of the present invention, it is impossible to limit the scope of protection of the invention with this,
The change and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed scope.
Claims (8)
1. one kind is based on filter cloth defect damage testing method, it is characterised in that comprise the following steps：
Image texture extraction step：The image texture characteristic of filter cloth is extracted, and forms database；
Analyze judgment step：The image texture characteristic in database is analyzed using the detection of classifier modellings of SVM bis-, and
Whether the disconnected image texture characteristic area sentenced in filter cloth is defect damage zone.
2. based on filter cloth defect damage testing method, it is characterised in that comprise the following steps：Described image texture extracting step：Adopt
The image texture characteristic of filter cloth is extracted with gray level co-occurrence matrixes, and forms database.
3. filter cloth defect damage testing method is based on as claimed in claim 2, it is characterised in that：The detection of classifier of SVM bis-
Modelling, if gray level image is F, tonal gradation is L, then the step of calculating gray level co-occurrence matrixes is as follows：
(1) the size L of gray level co-occurrence matrixes is calculated according to the tonal gradation of gray level image2；
(2) appoint the point K (x, y) taken in gray level image F, take another point Q (x+a, y+b), the gray value of the pixel pair is remembered
For (i, j)；
(3) order point K is moved on gray level image F, then records (i, j) and distance value of each obtained pixel pair；
(4) it is apart in statistical picture FPixel to the frequency N (i, j) of appearance；
(5) the joint frequency N (i, j) that statistics is obtained into every a pair (i, j) appearance is arranged in a square H (i, j), and wherein i and j divide
Ith row and jth column in other representing matrix, matrix H (i, j) is required gray level co-occurrence matrixes, or, after normalized
Co-occurrence matrix is built again.
4. filter cloth defect damage testing method is based on as claimed in claim 1, it is characterised in that：If the sample in database is line
Property can divide, then the detection of classifier modellings of SVM bis- are directly analyzed the image texture characteristic in database.
5. filter cloth defect damage testing method is based on as claimed in claim 1, it is characterised in that：If the image texture in database
Linearly inseparable is characterized as, then it is empty the sample of low-dimensional linearly inseparable to be transformed into high dimensional feature using non-linear map
Between, to make its linear separability, then the detection of classifier modellings of SVM bis- are directly carried out to the image texture characteristic in database
Analysis.
6. filter cloth defect damage testing method is based on as claimed in claim 1, it is characterised in that：Described image texture blending is walked
Suddenly：The image texture characteristic of filter cloth is extracted using local binary pattern, and forms database.
7. a kind of electronic equipment, it is characterised in that including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to be held by processor
OK, described program includes being used for the method in perform claim requirement 1-6 described in any one.
8. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that：The program is held by processor
Method of the row as described in any one in claim 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710440961.8A CN107274394A (en) | 2017-06-13 | 2017-06-13 | One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710440961.8A CN107274394A (en) | 2017-06-13 | 2017-06-13 | One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107274394A true CN107274394A (en) | 2017-10-20 |
Family
ID=60067147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710440961.8A Pending CN107274394A (en) | 2017-06-13 | 2017-06-13 | One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107274394A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108682003A (en) * | 2018-04-04 | 2018-10-19 | 睿视智觉（厦门）科技有限公司 | A kind of product quality detection method |
| CN112884748A (en) * | 2021-03-02 | 2021-06-01 | 江苏海洋大学 | Non-woven fabric surface small defect detection method based on multi-core support vector machine |
-
2017
- 2017-06-13 CN CN201710440961.8A patent/CN107274394A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108682003A (en) * | 2018-04-04 | 2018-10-19 | 睿视智觉（厦门）科技有限公司 | A kind of product quality detection method |
| CN112884748A (en) * | 2021-03-02 | 2021-06-01 | 江苏海洋大学 | Non-woven fabric surface small defect detection method based on multi-core support vector machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rasheed et al. | Fabric defect detection using computer vision techniques: a comprehensive review | |
| Gui et al. | Color co-occurrence matrix based froth image texture extraction for mineral flotation | |
| CN108647681A (en) | A kind of English text detection method with text orientation correction | |
| CN106909941A (en) | Multilist character recognition system and method based on machine vision | |
| CN114723704B (en) | Textile quality evaluation method based on image processing | |
| CN101930549B (en) | Second generation curvelet transform-based static human detection method | |
| CN103729856B (en) | A kind of Fabric Defects Inspection detection method utilizing S-transformation signal extraction | |
| CN102654464A (en) | Copper strip surface defect detection system based on multi-feature fuzzy recognition | |
| CN108090429A (en) | Face bayonet model recognizing method before a kind of classification | |
| CN110223267A (en) | The recognition methods of refractory brick deep defects based on height histogram divion | |
| CN102169544A (en) | Face-shielding detecting method based on multi-feature fusion | |
| CN104463204B (en) | Destination number statistical method | |
| CN102226920A (en) | Cutting-resistant JPEG image compression history and synthetic tamper detection method | |
| Wang et al. | Video inter-frame forgery identification based on optical flow consistency | |
| CN111402236B (en) | Hot rolled strip steel surface defect grading method based on image gray value | |
| CN103593668B (en) | Automatic crack identification method in metal plate stamping connector mechanical property test | |
| CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| Chaabouni et al. | Multi-fractal modeling for on-line text-independent writer identification | |
| CN111242899A (en) | Image-based flaw detection method and computer-readable storage medium | |
| CN101251896A (en) | Object detecting system and method based on multiple classifiers | |
| CN107274394A (en) | One kind is based on filter cloth defect damage testing method, electronic equipment and storage medium | |
| Dong et al. | Fusing multilevel deep features for fabric defect detection based NTV-RPCA | |
| Zhang et al. | The density fraction estimation of coarse coal by use of the kernel method and machine vision | |
| CN107256551A (en) | A kind of method, storage medium and the device of filter cloth defect damage testing | |
| Zhang et al. | Fabric defect detection based on visual saliency map and SVM |
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: 20171020 |