{
    "article_id": 774,
    "public_id": "a091ecd4-e84a-49cb-94b3-24828c3a2573",
    "internal_identifier": null,
    "source_identifier": "39:139",
    "status": "published",
    "type": "research_article",
    "title": "Endüstriyel Üretim Tesislerinde Yumurtaların Görsel Analizi Ve Sınıflandırılması İçin Raspberry Pi Tabanlı Gerçek Zamanlı Bir Uygulama",
    "title_secondary": null,
    "abstract": "Gelişen teknoloji ve artan talep nedeniyle yumurta üretim tesisleri büyümüş ve üretim miktarları artmış ve yumurta kalitesi\r\nön plana çıkmıştır. Kusurlu (kirli-kırık) yumurtaların belirlenip ayrılması ve kalan yumurtaların belirli standartlarda\r\nsınıflandırılıp paketlenmesi işlemine yumurta tasnif işlemi denilmektedir. Görüntü işleme, son zamanlarda birçok alanda\r\nkullanımı hızla artan bir teknolojidir. Giderek yaygınlaşan bu teknoloji endüstriyel uygulamalarda kullanılarak üretim\r\ngüvenilirliğini ve verimi artırılabilmektedir. Yumurta tasnif işleminde görüntü işleme tekniği kullanılarak, insan gücü ile yapılan\r\nsınıflandırma işlemlerinde yapılan hataları minimize etmek, işçi maliyetlerini ve insan gücüne olan bağlılığı azaltmak\r\nhedeflenmektedir. Bu çalışmada yumurtaların hem kusur tespiti hem de hacimsel olarak sınıflandırılması görüntü işleme\r\nyöntemleriyle yapılmıştır. Bu yöntemlerden bazıları, kameradan alınan görüntünün kırpılması, arka plan bastırma işlemi ve\r\nçeşitli filtreler yardımıyla alınan görüntüde ki gürültülerin yok edilmesi şeklindedir. Günümüzde tek kart bilgisayarların (single\r\nboard computer) yaygınlaşmasıyla görüntü işleme uygulamaları tek kart bilgisayarlar üzerinden gerçekleştirilebilir hale\r\ngelmiştir. Gerçekleştirilen bu çalışmada kullanılan sistem, kameradan alınan görüntünün Raspberry Pi kartının üzerinde\r\nçalıştırılan görüntü işleme algoritmaları ile yumurta tasnif işleminin tamamlanması şeklindedir. Bu sistem ile bilgisayar tabanlı\r\nklasik sistemlere göre maliyeti daha az ve endüstriyel olarak üretim sistemlerine uygulanabilir bir çözüm önerilmiştir. Yapılan\r\nçalışmada 100 adet yumurta görüntüsü (otuz adet kirli yumurta ve yetmiş adet temiz yumurta) kullanılmıştır. Söz konusu\r\nyumurtaların tamamının doğru bir şekilde kirli ve temiz olarak ayırt edildiği gözlenmiştir. Çalışmanın ikinci aşamasında, 70 adet\r\nyumurtanın hacimsel sınıflandırılması yapılmış olup gerçek ağırlık ölçümleriyle karşılaştırıldığında 66 adet yumurtanın\r\nbüyüklük sınıfına (S, M, L, XL) uygun olarak tasnif edildiği 4 adet yumurtanın hatalı ölçüldüğü tespit edilmiştir. Buna göre %\r\n94,29 başarı elde edilmiştir. Bu çalışma kapalı bir ortamda sabit ışık kaynağı kullanılarak yapılmış olup sistemin başarı oranı\r\nışık kaynağına ve bant hızına bağlı olarak değişmektedir.  ",
    "language": "tr",
    "english_title": "A Raspberry Pi-Based Real-Time Application for Visual Analysis and Classification of Eggs in Industrial Production Facilities",
    "english_abstract": "Due to developing technology and increasing demand, egg production facilities have grown, production quantities have increased, and egg quality has become paramount. The process of identifying and separating defective (dirty-broken) eggs and classifying and packaging the remaining eggs according to certain standards is called egg sorting. Image processing is a technology whose use has rapidly increased in many fields recently. This increasingly widespread technology can be used in industrial applications to increase production reliability and efficiency. By using image processing techniques in egg sorting, the aim is to minimize errors made in classification processes performed by human labor, reduce labor costs, and decrease reliance on human labor. In this study, both defect detection and volumetric classification of eggs were performed using image processing methods. Some of these methods include cropping the image taken from the camera, background suppression, and eliminating noise in the image using various filters. Today, with the widespread use of single-board computers, image processing applications can be performed on single-board computers. The system used in this study is to complete the egg sorting process by running image processing algorithms on a Raspberry Pi board from the image taken from the camera. With this system, a solution that is less expensive than computer-based classical systems and applicable to industrial production systems has been proposed. In the study, 100 egg images (thirty dirty eggs and seventy clean eggs) were used. It was observed that all of the eggs were correctly distinguished as dirty and clean. In the second stage of the study, volumetric classification of 70 eggs was performed, and when compared with actual weight measurements, it was determined that 66 eggs were classified according to size class (S, M, L, XL) and 4 eggs were incorrectly measured. Accordingly, a success rate of 94.29% was achieved. This study was conducted in a closed environment using a fixed light source, and the success rate of the system varies depending on the light source and the tape speed.",
    "doi": null,
    "doi_url": null,
    "resource_url": "https://www.set-science.com/a/a091ecd4-e84a-49cb-94b3-24828c3a2573",
    "pdf_url": "https://www.set-science.com/a/a091ecd4-e84a-49cb-94b3-24828c3a2573/pdf",
    "og_image": "https://www.set-science.com/assets/img/og-card-v2.png",
    "authors": [
        {
            "public_id": "0b809da4-3739-47e3-a0a4-8677f46e3627",
            "given": "Murat",
            "family": "Ozan",
            "full": "Murat Ozan",
            "literal": null,
            "orcid": null,
            "orcid_url": null,
            "email": "muratozan23@gmail.com",
            "corresponding": true,
            "sequence": "first",
            "affiliations": [
                {
                    "name": "Konya Technical University",
                    "department": null,
                    "country": null,
                    "country_code": null,
                    "ror": null,
                    "ror_url": null
                }
            ]
        },
        {
            "public_id": "5be97669-dcda-4ba1-bc85-4b5e66b2d0fe",
            "given": "Murat",
            "family": "Ceylan",
            "full": "Murat Ceylan",
            "literal": null,
            "orcid": null,
            "orcid_url": null,
            "email": "muratozan23@gmail.com",
            "corresponding": false,
            "sequence": "additional",
            "affiliations": [
                {
                    "name": "Konya Technical University",
                    "department": null,
                    "country": null,
                    "country_code": null,
                    "ror": null,
                    "ror_url": null
                }
            ]
        }
    ],
    "keywords": [],
    "translations": [
        {
            "language": "en",
            "title": "A Raspberry Pi-Based Real-Time Application for Visual Analysis and Classification of Eggs in Industrial Production Facilities",
            "abstract": "Due to developing technology and increasing demand, egg production facilities have grown, production quantities have increased, and egg quality has become paramount. The process of identifying and separating defective (dirty-broken) eggs and classifying and packaging the remaining eggs according to certain standards is called egg sorting. Image processing is a technology whose use has rapidly increased in many fields recently. This increasingly widespread technology can be used in industrial applications to increase production reliability and efficiency. By using image processing techniques in egg sorting, the aim is to minimize errors made in classification processes performed by human labor, reduce labor costs, and decrease reliance on human labor. In this study, both defect detection and volumetric classification of eggs were performed using image processing methods. Some of these methods include cropping the image taken from the camera, background suppression, and eliminating noise in the image using various filters. Today, with the widespread use of single-board computers, image processing applications can be performed on single-board computers. The system used in this study is to complete the egg sorting process by running image processing algorithms on a Raspberry Pi board from the image taken from the camera. With this system, a solution that is less expensive than computer-based classical systems and applicable to industrial production systems has been proposed. In the study, 100 egg images (thirty dirty eggs and seventy clean eggs) were used. It was observed that all of the eggs were correctly distinguished as dirty and clean. In the second stage of the study, volumetric classification of 70 eggs was performed, and when compared with actual weight measurements, it was determined that 66 eggs were classified according to size class (S, M, L, XL) and 4 eggs were incorrectly measured. Accordingly, a success rate of 94.29% was achieved. This study was conducted in a closed environment using a fixed light source, and the success rate of the system varies depending on the light source and the tape speed.",
            "keywords": [
                "görüntü işleme, yumurta tasnifi, sınıflandırma, kusurlu yumurta, raspberry pi"
            ]
        }
    ],
    "subjects": [],
    "subject_names": [],
    "published_date": "2018-12-31",
    "published_year": "2018",
    "received_date": null,
    "accepted_date": null,
    "volume": "3",
    "issue": null,
    "page_first": "727",
    "page_last": "731",
    "article_number": null,
    "conference": {
        "short_name": "ISAS2018-Winter",
        "full_title": "2nd International Symposium on Innovative Approaches in Scientific Studies",
        "name": "2nd International Symposium on Innovative Approaches in Scientific Studies",
        "acronym": "ISAS2018-Winter",
        "location": "Samsun, Türkiye",
        "start_date": "2018-11-30",
        "end_date": null,
        "public_id": "b8a703cc-09f7-4d5b-ae60-eb31a1050720"
    },
    "proceedings": {
        "title": "2nd International Symposium on Innovative Approaches in Scientific Studies",
        "series_title": "Setsci conference indexing system",
        "publisher": "SET Technology",
        "isbn": null,
        "eisbn": null,
        "issn": "2618-6446",
        "eissn": null,
        "doi": null,
        "doi_prefix": null,
        "slug": "setsci-volume-3-2018-legacy-39",
        "public_id": "641f522e-9cf0-4c89-be17-c6037f3d1bca",
        "url": "https://www.set-science.com/p/setsci-volume-3-2018-legacy-39"
    },
    "license": {
        "name": "CC BY 4.0",
        "url": "https://creativecommons.org/licenses/by/4.0/",
        "code": "CC-BY-4.0",
        "open_access": true
    },
    "copyright": {
        "holder": "SET Technology",
        "year": "2018"
    },
    "funding_statement": null,
    "funders": [],
    "references": [
        {
            "order": 1,
            "raw": "Gıda, Tarım ve Hayvancılık Bakanlığından:TÜRK GIDA KODEKSİ YUMURTA TEBLİĞİ (2014/55)",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 2,
            "raw": "Elster RT. and Goodrum JW., 1991, Detection of cracks in eggs using machine vision, Transactions of the Asae, 35(4): 307-312p",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 3,
            "raw": "Elster RT. and Goodrum JW., 1992, Machine vision for crack detection in rotating eggs, Transactions of the Asae, 34(1): 1323-1328p",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 4,
            "raw": "Han, Y. J. and Y. Feng (1994). Egg shell inspection using global image analysis. American Society ofAgricuLturaL Engineers. 10(1), 109-114.",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 5,
            "raw": "Garcia-Alegre MC., Ribeiro A., Guinea D. and Cristobal G.., 1996, Eggshell defects detection based on color processing, Instituto de Optice, Spanish Council for Scientific Research, Madrid-Spain",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 6,
            "raw": "Dehrouyeh MH., Omid M., Ahmadi H., Mohtasebi SS. and Jamzad M., 2010, Grading and quality inspection of defected eggs using machine vision, International Journal of Advance Science and Technology, vol.16",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 7,
            "raw": "Patel VC., McClendon RW. and Goodrum JW.,1994, Crack detection in eggs using computer vision and neural networks, AI Applications, 8(2):21-31p",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 8,
            "raw": "Mertens K., De Ketelaere B. and Kamers B., 2005, Dirt detection on Brown eggs by means of color computer vision, Poultry Science, 1653-1659p",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        },
        {
            "order": 9,
            "raw": "(2018) The Raspberry Pi website. [Online]. Available:\r\nhttps://www.raspberrypi.org/help/what-%20is-a-raspberry-pi/\r\nhttps://www.raspberrypi.org/products/raspberry-pi-3-model-b-plus/\r\nhttps://www.raspberrypi.org/products/camera-module-v2/",
            "doi": null,
            "title": null,
            "authors": null,
            "source": null,
            "year": null,
            "volume": null,
            "pages": null
        }
    ],
    "statements": {
        "acknowledgements": null,
        "conflict_of_interest": null,
        "data_availability": null,
        "ai_disclosure": null
    },
    "credit": [],
    "history": {
        "published": "2018-12-31"
    }
}