Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images
Machine vision is playing an increasingly important role in industrial applications, and the automated design of image recognition systems has been a subject of intense research. This study has proposed a system for automatically designing the field-of-view (FOV) of a camera, the illumination streng...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/5/1656 |
| _version_ | 1798040682880827392 |
|---|---|
| author | Yibing Chen Taiki Ogata Tsuyoshi Ueyama Toshiyuki Takada Jun Ota |
| author_facet | Yibing Chen Taiki Ogata Tsuyoshi Ueyama Toshiyuki Takada Jun Ota |
| author_sort | Yibing Chen |
| collection | DOAJ |
| description | Machine vision is playing an increasingly important role in industrial applications, and the automated design of image recognition systems has been a subject of intense research. This study has proposed a system for automatically designing the field-of-view (FOV) of a camera, the illumination strength and the parameters in a recognition algorithm. We formulated the design problem as an optimisation problem and used an experiment based on a hierarchical algorithm to solve it. The evaluation experiments using translucent plastics objects showed that the use of the proposed system resulted in an effective solution with a wide FOV, recognition of all objects and 0.32 mm and 0.4° maximal positional and angular errors when all the RGB (red, green and blue) for illumination and R channel image for recognition were used. Though all the RGB illumination and grey scale images also provided recognition of all the objects, only a narrow FOV was selected. Moreover, full recognition was not achieved by using only G illumination and a grey-scale image. The results showed that the proposed method can automatically design the FOV, illumination and parameters in the recognition algorithm and that tuning all the RGB illumination is desirable even when single-channel or grey-scale images are used for recognition. |
| first_indexed | 2024-04-11T22:10:57Z |
| format | Article |
| id | doaj.art-a302f15a865d4fdaacec42955b497f11 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:10:57Z |
| publishDate | 2018-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a302f15a865d4fdaacec42955b497f112022-12-22T04:00:34ZengMDPI AGSensors1424-82202018-05-01185165610.3390/s18051656s18051656Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and ImagesYibing Chen0Taiki Ogata1Tsuyoshi Ueyama2Toshiyuki Takada3Jun Ota4Department of Precision Engineering, the University of Tokyo, Tokyo 113-8656, JapanResearch into Artifacts, Center for Engineering (RACE), The University of Tokyo, Chiba 277-8568, JapanDenso Wave Incorporated, Aichi 470-2298, JapanDenso Wave Incorporated, Aichi 470-2298, JapanResearch into Artifacts, Center for Engineering (RACE), The University of Tokyo, Chiba 277-8568, JapanMachine vision is playing an increasingly important role in industrial applications, and the automated design of image recognition systems has been a subject of intense research. This study has proposed a system for automatically designing the field-of-view (FOV) of a camera, the illumination strength and the parameters in a recognition algorithm. We formulated the design problem as an optimisation problem and used an experiment based on a hierarchical algorithm to solve it. The evaluation experiments using translucent plastics objects showed that the use of the proposed system resulted in an effective solution with a wide FOV, recognition of all objects and 0.32 mm and 0.4° maximal positional and angular errors when all the RGB (red, green and blue) for illumination and R channel image for recognition were used. Though all the RGB illumination and grey scale images also provided recognition of all the objects, only a narrow FOV was selected. Moreover, full recognition was not achieved by using only G illumination and a grey-scale image. The results showed that the proposed method can automatically design the FOV, illumination and parameters in the recognition algorithm and that tuning all the RGB illumination is desirable even when single-channel or grey-scale images are used for recognition.http://www.mdpi.com/1424-8220/18/5/1656automated designvision systemFOVilluminationrecognition algorithm |
| spellingShingle | Yibing Chen Taiki Ogata Tsuyoshi Ueyama Toshiyuki Takada Jun Ota Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images Sensors automated design vision system FOV illumination recognition algorithm |
| title | Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images |
| title_full | Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images |
| title_fullStr | Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images |
| title_full_unstemmed | Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images |
| title_short | Automated Field-of-View, Illumination, and Recognition Algorithm Design of a Vision System for Pick-and-Place Considering Colour Information in Illumination and Images |
| title_sort | automated field of view illumination and recognition algorithm design of a vision system for pick and place considering colour information in illumination and images |
| topic | automated design vision system FOV illumination recognition algorithm |
| url | http://www.mdpi.com/1424-8220/18/5/1656 |
| work_keys_str_mv | AT yibingchen automatedfieldofviewilluminationandrecognitionalgorithmdesignofavisionsystemforpickandplaceconsideringcolourinformationinilluminationandimages AT taikiogata automatedfieldofviewilluminationandrecognitionalgorithmdesignofavisionsystemforpickandplaceconsideringcolourinformationinilluminationandimages AT tsuyoshiueyama automatedfieldofviewilluminationandrecognitionalgorithmdesignofavisionsystemforpickandplaceconsideringcolourinformationinilluminationandimages AT toshiyukitakada automatedfieldofviewilluminationandrecognitionalgorithmdesignofavisionsystemforpickandplaceconsideringcolourinformationinilluminationandimages AT junota automatedfieldofviewilluminationandrecognitionalgorithmdesignofavisionsystemforpickandplaceconsideringcolourinformationinilluminationandimages |