CN114494671A - Multispectral light source control device for visual identification - Google Patents
Multispectral light source control device for visual identification Download PDFInfo
- Publication number
- CN114494671A CN114494671A CN202111010528.3A CN202111010528A CN114494671A CN 114494671 A CN114494671 A CN 114494671A CN 202111010528 A CN202111010528 A CN 202111010528A CN 114494671 A CN114494671 A CN 114494671A
- Authority
- CN
- China
- Prior art keywords
- light source
- visual
- recognition
- source control
- identification
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 63
- 230000003595 spectral effect Effects 0.000 claims abstract description 24
- 238000007405 data analysis Methods 0.000 claims abstract description 20
- 238000001228 spectrum Methods 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000005286 illumination Methods 0.000 claims description 18
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009713 electroplating Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a multispectral light source control device for visual identification, which comprises a light source control unit, a light source, a visual identification device and a data analysis unit, wherein the light source control unit is used for controlling the light source control unit; the visual recognition equipment is used for acquiring image data, submitting the image data to an algorithm model of a training library to complete a recognition process and generating recognition data; the data analysis unit is connected with the visual recognition equipment during working and is used for receiving a recognition result and corresponding equipment parameters transmitted by the visual equipment; the light source control unit is electrically connected with the light source, the light source control unit is connected with the visual recognition equipment, and the visual recognition equipment shoots the light source to obtain light source irradiation image information. According to the invention, manual intervention for switching the light sources is not required, the light sources are continuously switched in all spectral ranges supported by the light sources under the automatic control of the light source control unit, and the parameter determination of the required optimal spectrum or light source combination lighting effect is realized when a certain specific sample is subjected to visual identification.
Description
Technical Field
The invention relates to the technical field of light sources, in particular to a multispectral light source control device for visual identification.
Background
When defects of different target objects are detected in industrial production, besides a camera and an identification algorithm, a light source is also a key influence factor, the target object is generally irradiated by the light source, the defects are made to be clearly visible through the light source, and therefore the problem to be solved is that the light source with the best illumination effect is selected in different defect detection scenes.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a multispectral light source control device for visual identification.
A multispectral light source control device for visual identification comprises a light source control unit, a light source, a visual identification device and a data analysis unit; the visual recognition equipment is used for acquiring image data, submitting the image data to an algorithm model of a training library to complete a recognition process and generating recognition data; the data analysis unit is used for storing all known sample characteristic types to be evaluated, is connected with the visual identification equipment during working, and is used for receiving the identification result and corresponding equipment parameters transmitted by the visual equipment, completing storage and statistics of the known samples and generating a visual identification success rate sequencing list of all sample characteristics under the combination of each spectral band and light source; the light source control unit is electrically connected with the light source, the light source control unit is connected with the visual recognition equipment, and the visual recognition equipment shoots the light source to obtain light source irradiation image information.
Further, the light source may be one or more, and the light source may be a single spectrum light source and/or a multispectral light source.
Furthermore, the visual recognition device comprises a camera, a camera holder and an image recognition workstation configured with a recognition algorithm based on deep learning, wherein one or more cameras can be configured according to the requirements of a recognition scene, the camera is arranged on the camera holder, the camera is connected with the image recognition workstation in a LAN/USB (local area network/universal serial bus) mode or the like, and the workstation can be a special image server, a desktop computer or a high-performance industrial computer.
Further, the light source control unit controls the light emission of different spectral sections of a single multispectral light source and the sequential and random out-of-order light emission control of a plurality of different single spectral light sources, obtains the light source illumination image result of the largest different spectral illumination combination number, runs for a period of time, and controls all combinations of illumination effects of all light sources to obtain a plurality of rounds of identification results and corresponding parameter data of the light sources.
Further, the data analysis unit gives the optimal light source irradiation result sequencing of the visual scene and the corresponding light source parameter display through data statistics and analysis of the recognition result recording table.
Further, the identification workstation controls and guarantees that the image identification effect of the spectrum combination and the lighting combination of all the light sources obtains full coverage through a circulation control program.
Further, the data analysis unit comprises a sample image feature classification unit, a comparison unit for comparing the image recognition features with the sample features, and a comparison result storage statistics and reality data information processing unit.
The invention has the following beneficial effects:
1. the light source is continuously switched in all spectral ranges supported by the light source under the automatic control of the light source control unit without manual intervention for switching the light source, all possible spectral and light source working combinations are completed, working parameters of the corresponding light source are automatically recorded, and the parameter determination of the required optimal spectral or light source combination lighting effect is realized when a certain specific sample is subjected to visual identification.
2. The labor and the time are saved, and the labor intensity of workers and the cost of a company are reduced.
Drawings
FIG. 1 is a block diagram of 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.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention; the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, and furthermore, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
A multispectral light source control device for visual identification comprises a light source control unit, a light source, a visual identification device and a data analysis unit; the visual recognition equipment is used for acquiring image data, submitting the image data to an algorithm model of a training library to complete a recognition process and generating recognition data; the data analysis unit is used for storing all known sample characteristic types to be evaluated, is connected with the visual identification equipment during working, and is used for receiving the identification result and corresponding equipment parameters transmitted by the visual equipment, completing storage and statistics of the known samples and generating a visual identification success rate sequencing list of all sample characteristics under the combination of each spectral band and light source; the light source control unit is electrically connected with the light source, the light source control unit is connected with the visual identification device, and the visual identification device shoots the light source to obtain light source irradiation image information.
In particular, the light source may be one or more, and the light source may be a single-spectrum light source and/or a multi-spectrum light source.
Specifically, the visual recognition device comprises a camera, a camera holder and an image recognition workstation configured with a recognition algorithm based on deep learning, wherein the camera can be configured with one or more cameras according to the requirements of a recognition scene, the camera is arranged on the camera holder, the camera is connected with the image recognition workstation in a LAN/USB (local area network/universal serial bus) mode and the like, and the workstation can be a special image server, a desktop computer or a high-performance industrial computer.
Specifically, the light source control unit controls the light emission of different spectral sections of a single multispectral light source and the sequential and random out-of-order light emission control of a plurality of different single-spectral light sources, obtains the light source illumination image result of the largest different spectral illumination combination number, runs for a period of time, and controls all combinations of all light source illumination effects to obtain a plurality of rounds of identification results and corresponding parameter data of the light source.
Specifically, the data analysis unit gives the optimal light source irradiation result sequencing of the visual scene and the corresponding light source parameter display through data statistics and analysis of the recognition result recording table.
Specifically, the identification workstation controls and guarantees the image identification effect of the spectrum combination and the lighting combination of all the light sources to obtain full coverage through a circulation control program.
Specifically, the data analysis unit comprises a sample image feature classification unit, a comparison unit for comparing image recognition features with sample features, and a data information processing unit for storing statistics, reality and the like of comparison results.
The data analysis unit implementation will store a large amount of sample image data of the same type, whose features are homogeneous. And starting a light source testing process, running for 1 whole day, 2 whole days and even for longer time, wherein the number of times of circulating tests of all light sources and spectrums can be hundreds of times, thousands of times, tens of thousands of times and even hundreds of thousands of times, and the like, and when the recognition results of all spectrum combinations and light source combination effects are viewed, the light source combination with the highest recognition success rate and corresponding parameters are the optimal light source parameters for characteristic extraction of the sample.
The light source control unit controls the light emission of different spectral sections of the same multispectral light source and controls the sequential and random out-of-order light emission of a plurality of different single-spectral light sources, the light source illumination image result of the largest different spectral illumination combination number is obtained, the operation is carried out for a period of time, the multi-round data are obtained by controlling all combinations of the illumination effects of all the light sources, the artificial intelligence and the deep learning algorithm are combined, the identification effect of the light source control unit is fed back to the multispectral light source control, the process is an automatic process, manual intervention is not needed, the result is automatically recorded, and finally the result is used for selecting the spectral value of the light source. For example, if the spectral value is 360nm, a 360nm light source is purchased.
For example, if the surface of a certain target object has flaws, the equipment is operated for one night according to different flaws, the result is observed the next day, and the best light source is determined, and then the best light source is selected, and the test is not manually carried out.
The visual identification flaw detection is applied to detection of surface flaws of semitransparent plastic products, needle tubes of medical instruments, needle caps of needle points of syringes, surface electroplating and medical packaging containers.
The irradiation control of various spectrums of the multispectral light source is associated with the artificial vision recognition and the recognition result based on the deep learning algorithm, then a closed loop is formed, and finally the result is output and recorded. For example, a scene using red light for the light source, the contrast of the defect is low, the features are invisible, and the effect is good using blue light or white light. The greater the contrast between the defect and the background, the better, and this is achieved by adjusting the light source.
The visual identification equipment selects industrial cameras, the cameras adopted for different scenes are different, the workstation is identified, the performance is high, and the effect is judged. For example, ten target objects with defects are set, when the operation is carried out for more than ten hours, if one target object without defects is found to be unidentified, the result caused by the fact that the target object is irradiated by the certain spectrum can be checked, and then the picture stored at the moment is looked at, so that the spectrum is not applicable to the scene.
The data analysis unit simply lists the data, then sorts the data, the auxiliary program of the workstation identifies the table, for example, the table is queued, a plurality of rounds are run, perhaps tens of thousands of rounds are run in a hundred hours, then the sort is sorted out, the success rate is the highest for observing which spectrum, the success rate of illumination is low for which spectrum, and finally the result is given, the success rate in the range is 100%, and ninety percent in the range is the analysis result, and the light source is selected through the process; for example, a light source may support multiple spectral range modes of operation, red, green, blue and violet, one support, or another support, such as providing a violet light source, a red light source, a white light source, out of order random semaphores, each of which is known, controlling which amount, and then recording its parameters to form a single-source multi-spectral light source, which is a comprehensive multi-spectral light source, or each of which is single-spectral, which is combined to see which combination is the most effective, and there are mainly two such support.
Referring to fig. 1, fig. 1 illustrates a block diagram of the present invention, which includes a light source control unit, a light source, a visual recognition device, and a data analysis unit; the visual recognition equipment is used for acquiring image data, submitting the image data to an algorithm model of a training library to complete a recognition process and generating recognition data; the data analysis unit is used for storing all known sample characteristic types to be evaluated, is connected with the visual identification equipment during working, and is used for receiving the identification result and corresponding equipment parameters transmitted by the visual equipment, completing storage and statistics of the known samples and generating a visual identification success rate sequencing list of all sample characteristics under the combination of each spectral band and light source; the light source control unit is electrically connected with the light source, the light source control unit is connected with the visual recognition equipment, and the visual recognition equipment shoots the light source to obtain light source irradiation image information.
The working principle is as follows: the light source control unit controls light emission of different spectral bands of the same multispectral light source and controls light emission of a plurality of different single spectral light sources in a random disorder sequence, the visual identification equipment shoots the light source to obtain light source illumination image information, obtains a light source illumination image result with the largest different spectral illumination combination number, runs for a period of time, controls all combinations of illumination effects of all the light sources to obtain multi-turn data, the visual identification equipment transmits the data to the data analysis unit, the data analysis unit receives the image data, compares the image data with the model data, generates visual identification data and feeds the visual identification data back to the visual identification equipment, and the data identification equipment feeds back the light source control unit to finally determine the optimal light source.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (7)
1. A multispectral light source control device for visual identification, comprising: the system comprises a light source control unit, a light source, a visual recognition device and a data analysis unit; the visual recognition equipment is used for acquiring image data, submitting the image data to a training library algorithm model to complete a recognition process and generating recognition data; the data analysis unit is used for storing all known sample characteristic types to be evaluated, is connected with the visual identification equipment during working, and is used for receiving the identification result and corresponding equipment parameters transmitted by the visual equipment, completing storage and statistics of the known samples and generating a visual identification success rate sequencing list of all sample characteristics under the combination of each spectral band and light source; the light source control unit is electrically connected with the light source, the light source control unit is connected with the visual recognition equipment, and the visual recognition equipment shoots the light source to obtain light source irradiation image information.
2. The multispectral light source control device for visual identification as recited in claim 1, wherein: the light source may be one or more, and the light source may be a single spectrum light source and/or a multi-spectrum light source.
3. The multispectral light source control device for visual identification according to claim 1, wherein: the visual recognition equipment comprises a camera, a camera holder and an image recognition workstation configured with a recognition algorithm based on deep learning, wherein the camera can be configured with one or more cameras according to the requirements of a recognition scene, the camera is arranged on the camera holder, the camera is connected with the image recognition workstation in a LAN/USB (local area network/universal serial bus) mode and the like, and the workstation can be a special image server, a desktop computer or a high-performance industrial computer.
4. The multispectral light source control device for visual identification as recited in claim 1, wherein: the light source control unit controls the light emission of different spectral sections of a single multispectral light source and the sequential and random out-of-order light emission control of a plurality of different single spectral light sources, obtains the light source illumination image result of the largest different spectral illumination combination number, and controls all combinations of the illumination effects of all light sources to obtain a plurality of rounds of identification results and corresponding parameter data of the light sources.
5. The multispectral light source control device for visual identification as recited in claim 1, wherein: and the data analysis unit gives the optimal light source irradiation result sequencing of the visual scene and the corresponding light source parameter display through data statistics and analysis of the recognition result record table.
6. The multispectral light source control device for visual identification as recited in claim 3, wherein: the identification workstation controls and guarantees that the image identification effects of the spectrum combination and the lighting combination of all the light sources are fully covered through a circulation control program.
7. The multispectral light source control device for visual identification as recited in claim 1, wherein: the data analysis unit comprises a sample image feature classification unit, a comparison unit for comparing image recognition features with sample features, and a data information processing unit for storing, counting, reality and the like of comparison results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111010528.3A CN114494671A (en) | 2021-08-31 | 2021-08-31 | Multispectral light source control device for visual identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111010528.3A CN114494671A (en) | 2021-08-31 | 2021-08-31 | Multispectral light source control device for visual identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494671A true CN114494671A (en) | 2022-05-13 |
Family
ID=81491706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111010528.3A Pending CN114494671A (en) | 2021-08-31 | 2021-08-31 | Multispectral light source control device for visual identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494671A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040105261A1 (en) * | 1997-12-17 | 2004-06-03 | Color Kinetics, Incorporated | Methods and apparatus for generating and modulating illumination conditions |
| CN102177767A (en) * | 2008-10-10 | 2011-09-07 | 皇家飞利浦电子股份有限公司 | Methods and apparatus for controlling multiple light sources via a single regulator circuit to provide variable color and/or color temperature light |
| CN204389408U (en) * | 2015-02-09 | 2015-06-10 | 华中农业大学 | The potato transmission high spectrum image collector that light source parameters is adjustable |
| US20170318178A1 (en) * | 2016-04-28 | 2017-11-02 | University Of Southern California | Multispectral lighting reproduction |
| CN109001112A (en) * | 2017-12-29 | 2018-12-14 | 北京林业大学 | A kind of light source for defects detection determines method and system |
| CN109451624A (en) * | 2018-10-26 | 2019-03-08 | 中国建筑科学研究院有限公司 | Spectrum adjusting method of multi-channel LED illuminating system |
| CN111259883A (en) * | 2020-01-14 | 2020-06-09 | 广东南方视觉文化传媒有限公司 | Image recognition device and image recognition method |
-
2021
- 2021-08-31 CN CN202111010528.3A patent/CN114494671A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040105261A1 (en) * | 1997-12-17 | 2004-06-03 | Color Kinetics, Incorporated | Methods and apparatus for generating and modulating illumination conditions |
| CN102177767A (en) * | 2008-10-10 | 2011-09-07 | 皇家飞利浦电子股份有限公司 | Methods and apparatus for controlling multiple light sources via a single regulator circuit to provide variable color and/or color temperature light |
| CN204389408U (en) * | 2015-02-09 | 2015-06-10 | 华中农业大学 | The potato transmission high spectrum image collector that light source parameters is adjustable |
| US20170318178A1 (en) * | 2016-04-28 | 2017-11-02 | University Of Southern California | Multispectral lighting reproduction |
| CN109001112A (en) * | 2017-12-29 | 2018-12-14 | 北京林业大学 | A kind of light source for defects detection determines method and system |
| CN109451624A (en) * | 2018-10-26 | 2019-03-08 | 中国建筑科学研究院有限公司 | Spectrum adjusting method of multi-channel LED illuminating system |
| CN111259883A (en) * | 2020-01-14 | 2020-06-09 | 广东南方视觉文化传媒有限公司 | Image recognition device and image recognition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shearer et al. | Color and defect sorting of bell peppers using machine vision | |
| US9367765B2 (en) | Method and apparatus for automatic detection of features in an image and method for training the apparatus | |
| US11913877B2 (en) | Real-time spectral analysis through high-speed spectral classification | |
| US20110106845A1 (en) | Information search and retrieval system | |
| US7526116B2 (en) | Automated microscopic sperm identification | |
| CN110199172A (en) | For detecting the haemolysis of sample, jaundice, piarhemia or method, equipment and the quality inspection module of normality | |
| CN109120919B (en) | A kind of automatic analysis system and method for the evaluation and test of picture quality subjectivity | |
| RU2669527C2 (en) | Network of intelligent machines | |
| CN109557396B (en) | Electromagnetic field radiation immunity video automatic detection system and detection method | |
| WO2011058529A4 (en) | Method and system for the real-time automatic analysis of the quality of samples of processed fish meat based on the external appearance thereof, said samples travelling on a conveyor belt such that surface defects can be detected and the fish meat can be sorted according to quality standards | |
| Saldaña et al. | Computer vision system in real-time for color determination on flat surface food | |
| CN109714591A (en) | Based on the picture quality subjective evaluation method and system to assessment label | |
| CN105744261A (en) | System and method for testing set top box front panels | |
| CN114494671A (en) | Multispectral light source control device for visual identification | |
| CN109596317B (en) | Detection method and device for panel lamp | |
| WO2018078582A1 (en) | Method for distinguishing fresh meat from meat subjected to freezing by means of analysis of images of muscle tissue and corresponding system arranged to execute said method | |
| WO2019152424A1 (en) | Systems and methods for quantitative phenotype analysis | |
| CN114663341A (en) | Quantitative detection method for glare defect of optical lens | |
| CN115546141A (en) | Small sample Mini LED defect detection method and system based on multi-dimensional measurement | |
| CN108984734B (en) | Subjective evaluation method and system for quality of large-sample-volume image | |
| CN112630153A (en) | Method, equipment and storage medium for detecting defects of lens cover glass | |
| Punthumast et al. | Non-destructive Identification of unmilled rice using digital image analysis | |
| KR20000050719A (en) | Automatic inspection system for quality of connection cable | |
| US11982627B2 (en) | Systems and methods for quantitative phenotype analysis | |
| JP3249216B2 (en) | How to check the illuminance of lighting equipment |
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 |