Görüntü İşleme ve Robot Kol Tabanlı Çikolata Toplama ve Paketleme Sistemi
Year 2021,
Issue: 30, 79 - 82, 15.12.2021
Muhammed Ali Yılmaz
,
Cemil Sungur
Abstract
Bu çalışmada bir konveyör bant üzerinden akan çikolatalar bir kamera yardımıyla toplanmıştır. Rastgele ve dağınık şekilde gelen çikolatalar konveyör bant üzerine yerleştirilmiş bir kamera ile tespit edilmiştir. Tespit edilen çikolataların merkez koordinatları robot kola gönderilmiştir. Robot kol gelen çikolata koordinatları ile konveyör banta bağlı enkoder bilgisini kullanarak sistemi durdurmadan çikolata toplama ve paketleme işlemini gerçekleştirmiştir. Görüntü işleme aşamasında HSV dönüşümü, kenar tespiti ve moment yöntemleri kullanılarak çikolatalar yüksek doğrulukla tespit edilmiştir. Kamera – robot kol birbirine kalibre edilerek toplama işlemini hatasız yapan bir otomasyon sistemi kurulmuştur. Görüntü işleme donanımı olarak bilgisayar kullanılmıştır. Bilgisayar-robot kol arasındaki haberleşme işlemi Modbus TCP/IP yöntemi ile yüksek hızda gerçekleştirilmiştir.
References
- Li, Y., Zhao, W., & Pan, J. (2016). Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Transactions on Automation Science and Engineering, 14(2), 1256-1264.
- Elbehiery, H., Hefnawy, A., & Elewa, M. (2005). Surface defects detection for ceramic tiles using image processing and morphological techniques.
- Ozdemir, R., & Koc, M. (2019, September). A quality control application on a smart factory prototype using deep learning methods. In 2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT) (Vol. 1, pp. 46-49). IEEE.
- Villalba-Diez, J., Schmidt, D., Gevers, R., Ordieres-Meré, J., Buchwitz, M., & Wellbrock, W. (2019). Deep learning for industrial computer vision quality control in the printing industry 4.0. Sensors, 19(18), 3987.
- Korkmaz, M., & Barstuğan, M. (2020). A Deep Learning-Based Quality Control Application. Avrupa Bilim ve Teknoloji Dergisi, 332-336.
- Ozkava, U., Ozturk, S., Akdemir, B., & Sevfi, L. (2018, October). An efficient retinal blood vessel segmentation using morphological operations. In 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 1-7). IEEE.
Chocolate Picking and Packaging System with Robotic Arm based on Image Processing
Year 2021,
Issue: 30, 79 - 82, 15.12.2021
Muhammed Ali Yılmaz
,
Cemil Sungur
Abstract
In this study, chocolates flowing over a conveyor belt were collected with the help of a camera. Random and scattered chocolates were detected with a camera placed on the conveyor belt. The center coordinates of the detected chocolates were sent to the robot arm. The robot arm carried out the chocolate collection and packaging process without stopping the system by using the incoming chocolate coordinates and the encoder information connected to the conveyor belt. Chocolates were detected with high accuracy by using HSV transform, edge detection and moment methods in the image processing stage. An automation system has been established that makes the collection process error-free by calibrating the camera and robot arm to each other. Computer was used as image processing hardware. The communication process between the computer and the robot arm was carried out at high speed using the Modbus TCP/IP method.
References
- Li, Y., Zhao, W., & Pan, J. (2016). Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Transactions on Automation Science and Engineering, 14(2), 1256-1264.
- Elbehiery, H., Hefnawy, A., & Elewa, M. (2005). Surface defects detection for ceramic tiles using image processing and morphological techniques.
- Ozdemir, R., & Koc, M. (2019, September). A quality control application on a smart factory prototype using deep learning methods. In 2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT) (Vol. 1, pp. 46-49). IEEE.
- Villalba-Diez, J., Schmidt, D., Gevers, R., Ordieres-Meré, J., Buchwitz, M., & Wellbrock, W. (2019). Deep learning for industrial computer vision quality control in the printing industry 4.0. Sensors, 19(18), 3987.
- Korkmaz, M., & Barstuğan, M. (2020). A Deep Learning-Based Quality Control Application. Avrupa Bilim ve Teknoloji Dergisi, 332-336.
- Ozkava, U., Ozturk, S., Akdemir, B., & Sevfi, L. (2018, October). An efficient retinal blood vessel segmentation using morphological operations. In 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 1-7). IEEE.