CN106886989A - The automatic optical detection method of keyboard - Google Patents
The automatic optical detection method of keyboard Download PDFInfo
- Publication number
- CN106886989A CN106886989A CN201510919764.5A CN201510919764A CN106886989A CN 106886989 A CN106886989 A CN 106886989A CN 201510919764 A CN201510919764 A CN 201510919764A CN 106886989 A CN106886989 A CN 106886989A
- Authority
- CN
- China
- Prior art keywords
- keyboard
- button
- standard form
- image information
- character
- 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention discloses a kind of automatic optical detection method of keyboard, it is comprised the following steps:The first step, sets up the standard form of keyboard, and image information to each button on the standard form and the character on button is stored;Second step, is shot by camera to the keyboard of actual production, obtains the image information of keyboard;3rd step, is compared the image information of the keyboard of actual production with the image information of standard form by computer, and finds out corresponding discrepancy, the corresponding button of statistical difference dissimilarity;4th step, the button with discrepancy that will be found out is marked, and the bad button in actual production keyboard can be quickly found out for operator, is changed or repaired.The present invention is more convenient, fast, accurate relative to current manual detection method.
Description
Technical field:
The present invention relates to the characterization processes technical field of keyboard production, a kind of easy to use, efficiently keyboard is refered in particular to
The automatic optical detection method of button.
Background technology:
Keyboard is the equipment such as computer indispensability external input device, and according to different products, general keyboard has
101st, the button of the varying numbers such as 108., it is necessary to be detected to keyboard in the production process of keyboard.Should
It is that in same keyboard, the shape of many buttons, size, specification are duplicate, and different is only
Character information on each button is different.In the assembling process of case, it is likely that button is installed to mistake by appearance
Position by mistake.In addition, it is also possible to because the flaw of product, the character on certain or some buttons is caused to be believed
Breath has lacked the button, it is necessary to more renew.
Detection for keyboard at present mainly relies on the observation of artificial naked eyes, finds bad button therein, and
Repaired the latter's replacing.But the maximum problem of manual detection is exactly, operating personnel are very easy to produce vision
Fatigue, causes the efficiency of detection, accuracy to decline.Because, there are more than 100 on a usual keyboard
Button, the shape of many buttons, size are duplicate, and how smaller character information is, and these cases are intensive
Be distributed in a smaller area, detection person be very easy to produce visual fatigue.So in order to improve detection effect
Rate and accuracy, can only increase the quantity of testing staff and increase detection number of times, which adds the life of product
Produce cost.
At present, optical detecting instrument starts application, the work of this optical detecting instrument in many fields
Principle is exactly:The product for needing detection is shot by industrial camera, the image information that then will be shot
Standard form information corresponding with Test database is compared, and corresponding difference is found out by computer
Point, for example:The information such as pixel, coordinate information, color are different, and by Computer display out.This light
Learn detecting instrument, optical gauge to be used in many fields, not only precision is high, detection work effect
Rate is also very fast.The present inventor is by constantly experiment and studies, and with reference to current technology, proposes following technology
Scheme.
The content of the invention:
The technical problems to be solved by the invention are that and overcome the shortcomings of existing manual detection keyboard, there is provided a kind of
Easy to use, efficiently keyboard automatic optical detection method.
In order to solve the above-mentioned technical problem, present invention employs following technical proposals:The automatic light of the keyboard
Detection method is learned to comprise the following steps:The first step, sets up the standard form of keyboard, and to every on the standard form
The image information of the character on individual button and button is stored;Second step, by camera to actual production
Keyboard shot, obtain keyboard image information;3rd step, by computer by the keyboard of actual production
Image information compare with the image information of standard form, and find out corresponding discrepancy, statistical difference dissimilarity
Corresponding button;4th step, the button with discrepancy that will be found out is marked, so that operator can be fast
Speed finds the bad button in actual production keyboard, is changed or repaired.
Furthermore, in above-mentioned technical proposal, in the described first step, when the standard form of keyboard is set up,
The standard form of the multiple samples of foundation is needed, to ensure, when follow-up image information is compared, to retain certain mistake
Difference scope, reduces erroneous judgement.
Furthermore, in above-mentioned technical proposal, in the described first step, to the image information of character on button
During storage, the character information at least coordinate values information including character picture central point on described button.
Furthermore, in above-mentioned technical proposal, in the 3rd described step, by the figure of the keyboard of actual production
When comparing as the image information of information and standard form, first with the character picture of button in standard form
Heart point is anchor point, and the character picture of correspondence button in the keyboard of actual production is positioned therewith, and then this is pressed
The character picture of key is analyzed, if the mark of the button character image of the keyboard of the actual production and all samples
Quasi-mode plate is mismatched, then judge that current button belongs to defective products, in subsequent step, by it in corresponding figure
Marked out as in and.
After adopting the above technical scheme, keyboard is taken pictures by industrial camera and lighting source, and to clapping
The image taken the photograph is pre-processed, and makes picture contrast more obvious.Each button character in the image of shooting is carried
Take out, its press key template image corresponding with standard form is positioned, and be compared, finally lead to
Cross computer and directly search the different information of correlation, and analyse whether to belong to bad button, if just in figure
Marked as in, be provided with the bad button that can be quickly found out for operator in actual production keyboard, be subject to more
Change or repair.
In addition, the present invention establishes multiple sample forms, can strengthen and the differentiated products for printing are made more
Flexible to check, reducing difference causes erroneous judgement, increases the robustness of program.
Brief description of the drawings:
Fig. 1 is flow chart of the invention;
Specific embodiment:
This is that the present invention is a kind of automatic optical detection method of keyboard, and the detection method includes following step
Suddenly:
The first step, sets up the standard form of keyboard, and on each button on the standard form and button
The image information of character is stored;In the described first step, when the standard form of keyboard is set up, it is necessary to build
The standard form of vertical multiple sample, to ensure, when follow-up image information is compared, to retain certain error range,
Reduce erroneous judgement.
In the described first step, when the image information to character on button is stored, character information on described button
At least include the coordinate values information of character picture central point.
Second step, is shot by camera to the keyboard of actual production, obtains the image information of keyboard;
3rd step, is entered the image information of the keyboard of actual production with the image information of standard form by computer
Row is compared, and finds out corresponding discrepancy, the corresponding button of statistical difference dissimilarity;
In the 3rd described step, enter with the image information of standard form by the image information of the keyboard of actual production
Row compare when, the character picture central point with button in standard form first as anchor point, by the key of actual production
The character picture of correspondence button is positioned therewith in disk, and then the character picture to the button is analyzed, if should
The button character image of the keyboard of actual production is mismatched with the standard form of all samples, then judge currently to press
Key belongs to defective products, in subsequent step, it is marked out in corresponding image and is come.
4th step, the button with discrepancy that will be found out is marked, so that operator can be quickly found out reality
Bad button in border production keyboard, is changed or is repaired.
The present invention is described further below in conjunction with the accompanying drawings, and as shown in Figure 1, test process of the invention is such as
Under:
1st, standard form is set up.One is determined first without any bad qualified keyboard, by industrial camera,
Light source is adjusted, the qualified keyboard is taken pictures.In order to the photo for making shooting becomes apparent from, it is easy to follow-up
Compare, can by software to shoot image carry out some process, for example with NI Vision visions storehouse,
The softwares such as lookup Table are pre-processed to image, make picture contrast more obvious.It is easy to follow-up calculating
The comparison of machine.
2nd, the key information of standard form is proposed from corresponding database, and sets up standard form, the standard
Template has corresponding template data information.These information include to each button on the standard form and
The image information of the character on button is stored.
In order to ensure accurate, the qualified keyboard of polylith can be respectively shot, set up the standard form of multiple samples, with
Ensure, when follow-up image information is compared, to retain certain error range, reduce erroneous judgement.
3rd, the product of actual production carries out pipelining, enters detection zone by flowing into equipment, and pass through
Industrial camera is taken pictures to the keyboard product of the actual production of the inflow, obtains the image letter of the actual product
Breath.
4 and then the image information of the keyboard of actual production is entered with the image information of standard form by computer
Row is compared, and finds out corresponding discrepancy, the corresponding button of statistical difference dissimilarity;First with button in standard form
Character picture central point be anchor point, will in the keyboard of actual production correspondence button character picture it is fixed therewith
Position, then the character picture to the button is analyzed.It is the image letter to each button in comparison process
Breath is compared respectively, each button character information will be extracted in standard form, then by the single button
The information such as template image and image center coordinate value, size information key information corresponding with actual product is carried out
Compare, if having difference, be judged as bad button.Certainly, allow to set certain in actually judging
Error range, prevents erroneous judgement.
According to noted earlier, in order to ensure accurate, the standard form for establishing multiple samples of the invention, work as reality
After the standard form information of the key information of product and first sample has differences, standard form is just changed, then
It is secondary to be matched.If the corresponding informance of the information of actual product button and all templates is all mismatched, illustrate
The button is bad products, it is marked out in corresponding image and is come.If the information of actual product button with
The corresponding informance matching of any one template, then illustrate that the product is non-defective unit.
Finally, while showing the sample of standard form and the image of actual product, so that operator can be looked for quickly
Bad button in actual production keyboard, is changed or is repaired.
Certainly, the foregoing is only specific embodiment of the invention, not limit the scope of the present invention,
All equivalent change or modifications done according to construction, feature and principle described in scope of the present invention patent, all should wrap
Include in scope of the present invention patent.
Claims (4)
1. a kind of automatic optical detection method of keyboard, it is characterised in that the detection method includes following
Step:
The first step, sets up the standard form of keyboard, and on each button on the standard form and button
The image information of character is stored;
Second step, is shot by camera to the keyboard of actual production, obtains the image information of keyboard;
3rd step, is entered the image information of the keyboard of actual production with the image information of standard form by computer
Row is compared, and finds out corresponding discrepancy, the corresponding button of statistical difference dissimilarity;
4th step, the button with discrepancy that will be found out is marked, so that operator can be quickly found out reality
Bad button in border production keyboard, is changed or is repaired.
2. the automatic optical detection method of keyboard according to claim 1, it is characterised in that:Institute
In the first step stated, when the standard form of keyboard is set up, it is necessary to set up the standard form of multiple samples, with true
Protect when follow-up image information is compared, retain certain error range, reduce erroneous judgement.
3. the automatic optical detection method of keyboard according to claim 2, it is characterised in that:Institute
In the first step stated, when the image information to character on button is stored, character information is at least wrapped on described button
Include the coordinate values information of character picture central point.
4. the automatic optical detection method of keyboard according to claim 3, it is characterised in that:Institute
In the 3rd step stated, compare with the image information of standard form by the image information of the keyboard of actual production
When, the character picture central point with button in standard form first, will be right in the keyboard of actual production as anchor point
The character picture of button is answered to position therewith, then the character picture to the button is analyzed, if this is actual raw
The button character image of the keyboard of product is mismatched with the standard form of all samples, then judge that current button belongs to
Defective products, in subsequent step, it is marked out in corresponding image and is come.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510919764.5A CN106886989A (en) | 2015-12-11 | 2015-12-11 | The automatic optical detection method of keyboard |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510919764.5A CN106886989A (en) | 2015-12-11 | 2015-12-11 | The automatic optical detection method of keyboard |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106886989A true CN106886989A (en) | 2017-06-23 |
Family
ID=59173858
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510919764.5A Pending CN106886989A (en) | 2015-12-11 | 2015-12-11 | The automatic optical detection method of keyboard |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106886989A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI670683B (en) * | 2018-06-22 | 2019-09-01 | 技嘉科技股份有限公司 | Keyboard inspection method and inspection system same |
CN110658194A (en) * | 2019-09-30 | 2020-01-07 | 联想(北京)有限公司 | Keyboard detection method and keyboard detection equipment |
CN110706195A (en) * | 2018-06-22 | 2020-01-17 | 技嘉科技股份有限公司 | Keyboard detection method and system |
CN110705551A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Key position identification method and device, electronic equipment and storage medium |
CN112634259A (en) * | 2020-12-30 | 2021-04-09 | 凌云光技术股份有限公司 | Automatic modeling and positioning method for keyboard keycaps |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101666616A (en) * | 2008-09-01 | 2010-03-10 | 比亚迪股份有限公司 | Appearance detecting method |
CN101762231A (en) * | 2008-12-26 | 2010-06-30 | 比亚迪股份有限公司 | Device and method for detecting appearance of mobile phone keys |
CN102938077A (en) * | 2012-10-25 | 2013-02-20 | 渭南师范学院 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
CN104568986A (en) * | 2015-01-26 | 2015-04-29 | 中国科学院半导体研究所 | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm |
CN104764712A (en) * | 2015-04-29 | 2015-07-08 | 浙江工业大学 | Method for detecting quality of inner wall of via hole of PCB |
-
2015
- 2015-12-11 CN CN201510919764.5A patent/CN106886989A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101666616A (en) * | 2008-09-01 | 2010-03-10 | 比亚迪股份有限公司 | Appearance detecting method |
CN101762231A (en) * | 2008-12-26 | 2010-06-30 | 比亚迪股份有限公司 | Device and method for detecting appearance of mobile phone keys |
CN102938077A (en) * | 2012-10-25 | 2013-02-20 | 渭南师范学院 | Online AOI (Automatic Optical Inspection) image retrieval method based on double-threshold binaryzation |
CN104568986A (en) * | 2015-01-26 | 2015-04-29 | 中国科学院半导体研究所 | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm |
CN104764712A (en) * | 2015-04-29 | 2015-07-08 | 浙江工业大学 | Method for detecting quality of inner wall of via hole of PCB |
Non-Patent Citations (1)
Title |
---|
管兴坚: "自动光学检测中的键盘缺陷字符关键检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI670683B (en) * | 2018-06-22 | 2019-09-01 | 技嘉科技股份有限公司 | Keyboard inspection method and inspection system same |
CN110706195A (en) * | 2018-06-22 | 2020-01-17 | 技嘉科技股份有限公司 | Keyboard detection method and system |
CN110658194A (en) * | 2019-09-30 | 2020-01-07 | 联想(北京)有限公司 | Keyboard detection method and keyboard detection equipment |
CN110705551A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Key position identification method and device, electronic equipment and storage medium |
CN110705551B (en) * | 2019-10-09 | 2022-05-20 | 北京百度网讯科技有限公司 | Key position identification method and device, electronic equipment and storage medium |
CN112634259A (en) * | 2020-12-30 | 2021-04-09 | 凌云光技术股份有限公司 | Automatic modeling and positioning method for keyboard keycaps |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106886989A (en) | The automatic optical detection method of keyboard | |
CN111028204B (en) | Cloth defect detection method based on multi-mode fusion deep learning | |
CN102521560B (en) | Instrument pointer image identification method of high-robustness rod | |
CN105808416B (en) | A kind of automated testing method and system of man-machine figure interactive interface | |
CN103917987B (en) | Pass through the measurement of the belt wear of the rim detection of raster image | |
CN107657603A (en) | A kind of industrial appearance detecting method based on intelligent vision | |
EP3482192A1 (en) | System and method for combined automatic and manual inspection | |
CN106097361A (en) | A kind of defective area detection method and device | |
CN108416765A (en) | A kind of character defect automatic testing method and system | |
CN110018172B (en) | Product detection system and method | |
CN109429473A (en) | Automatic check method and device with polarity electronic component in circuit board | |
CN113222913B (en) | Circuit board defect detection positioning method, device and storage medium | |
CN110009617A (en) | A kind of shaft forgings online quality control method | |
CN108764134A (en) | A kind of automatic positioning of polymorphic type instrument and recognition methods suitable for crusing robot | |
CN105631458B (en) | A kind of electronic component sample mask method and device | |
WO2019041634A1 (en) | Detection method and device for display panel | |
CN104766310B (en) | light source detection system and detection method | |
CN103150558B (en) | A kind of operation of the display terminal based on machine vision responses match detection method | |
CN108645490A (en) | Cold-water meter vision detection system based on image processing techniques and detection method | |
TW200844426A (en) | On-line mechanical visional inspection system of an object and method thereof | |
CN115599844A (en) | Visual detection method for misloading and neglected loading of airplane airfoil connecting piece | |
CN110290203A (en) | Artificial intelligence cloud computing carries out Noninvasive production defect recognition and information communication to manufactured goods | |
CN110335242A (en) | A kind of tire X-ray defect detection method based on multi-model fusion | |
CN110956656A (en) | Spindle positioning method based on depth target detection | |
CN101199411A (en) | Sight surveymeter |
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: 20170623 |