Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing
Glass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 mm<sup>2</sup>...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/11192 |
| _version_ | 1827647267807428608 |
|---|---|
| author | Arantza Bereciartua-Perez Gorka Duro Jone Echazarra Francico Javier González Alberto Serrano Liher Irizar |
| author_facet | Arantza Bereciartua-Perez Gorka Duro Jone Echazarra Francico Javier González Alberto Serrano Liher Irizar |
| author_sort | Arantza Bereciartua-Perez |
| collection | DOAJ |
| description | Glass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 mm<sup>2</sup> in size in glass bottles as they are being manufactured, 24 h per day and 7 days per week. The bottles move along the conveyor belt at 50 m/min, at a production rate of 250 bottles/min. This new proposed method includes deep learning-based artificial intelligence techniques and classical image processing on images acquired with a high-speed line camera. The algorithm comprises three stages. First, the bottle is identified in the input image. Next, an algorithm based in thresholding and morphological operations is applied on this bottle region to locate potential candidates for seeds. Finally, a deep learning-based model can classify whether the proposed candidates are real seeds or not. This method manages to filter out most of false positives due to stains in the glass surface, while no real seeds are lost. The F1 achieved is 0.97. This method reveals the advantages of deep learning techniques for problems where classical image processing algorithms are not sufficient. |
| first_indexed | 2024-03-09T19:16:47Z |
| format | Article |
| id | doaj.art-14ae041077f249b5abcaac72566d3378 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:16:47Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-14ae041077f249b5abcaac72566d33782023-11-24T03:39:33ZengMDPI AGApplied Sciences2076-34172022-11-0112211119210.3390/app122111192Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle ManufacturingArantza Bereciartua-Perez0Gorka Duro1Jone Echazarra2Francico Javier González3Alberto Serrano4Liher Irizar5TECNALIA, Basque Research and Technology Alliance (BRTA), Parque Tecnológico de Bizkaia, Astondo Bidea, Edificio 700, 48160 Derio, Bizkaia, SpainTECNALIA, Basque Research and Technology Alliance (BRTA), Parque Tecnológico de Bizkaia, Astondo Bidea, Edificio 700, 48160 Derio, Bizkaia, SpainTECNALIA, Basque Research and Technology Alliance (BRTA), Parque Tecnológico de Bizkaia, Astondo Bidea, Edificio 700, 48160 Derio, Bizkaia, SpainVIDRALA, Barrio Munegazo, 22, 01400 Laudio, Araba, SpainVIDRALA, Barrio Munegazo, 22, 01400 Laudio, Araba, SpainVIDRALA, Barrio Munegazo, 22, 01400 Laudio, Araba, SpainGlass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 mm<sup>2</sup> in size in glass bottles as they are being manufactured, 24 h per day and 7 days per week. The bottles move along the conveyor belt at 50 m/min, at a production rate of 250 bottles/min. This new proposed method includes deep learning-based artificial intelligence techniques and classical image processing on images acquired with a high-speed line camera. The algorithm comprises three stages. First, the bottle is identified in the input image. Next, an algorithm based in thresholding and morphological operations is applied on this bottle region to locate potential candidates for seeds. Finally, a deep learning-based model can classify whether the proposed candidates are real seeds or not. This method manages to filter out most of false positives due to stains in the glass surface, while no real seeds are lost. The F1 achieved is 0.97. This method reveals the advantages of deep learning techniques for problems where classical image processing algorithms are not sufficient.https://www.mdpi.com/2076-3417/12/21/11192seeds countingquality controldeep learningimage processingobject detectionclassification |
| spellingShingle | Arantza Bereciartua-Perez Gorka Duro Jone Echazarra Francico Javier González Alberto Serrano Liher Irizar Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing Applied Sciences seeds counting quality control deep learning image processing object detection classification |
| title | Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing |
| title_full | Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing |
| title_fullStr | Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing |
| title_full_unstemmed | Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing |
| title_short | Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing |
| title_sort | deep learning based method for accurate real time seed detection in glass bottle manufacturing |
| topic | seeds counting quality control deep learning image processing object detection classification |
| url | https://www.mdpi.com/2076-3417/12/21/11192 |
| work_keys_str_mv | AT arantzabereciartuaperez deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing AT gorkaduro deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing AT joneechazarra deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing AT francicojaviergonzalez deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing AT albertoserrano deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing AT liheririzar deeplearningbasedmethodforaccuraterealtimeseeddetectioninglassbottlemanufacturing |