{ "date_type": "completed", "creators": [ { "name": { "lineage": null, "given": "Mohamad Fajar A'la", "family": "Udin", "honourific": null }, "id": 2213020116 } ], "contact_email": "mohamadfajaralaudin@gmail.com", "department": "KODEPRODI55201#Teknik Informatika", "date": "2026-07-15", "divisions": [ "sch_psy" ], "ispublished": "unpub", "institution": "Universitas Nusantara PGRI Kediri", "pages": 152, "full_text_status": "restricted", "dir": "disk0\/00\/02\/71\/80", "rev_number": 17, "abstract": "Penelitian ini bertujuan untuk mengembangkan sistem cerdas deteksi dan klasifikasi varietas mangga multi-objek berbasis web menggunakan kombinasi OpenCV dan MobileNetV2. Sistem dirancang untuk mendeteksi lebih dari satu objek mangga dalam satu citra melalui segmentasi kontur, kemudian mengklasifikasikan setiap objek hasil deteksi ke dalam lima kelas, yaitu mangga apel, mangga gadung, mangga manalagi, Other, dan mangga podang. OpenCV digunakan pada tahap deteksi objek melalui proses grayscale, Gaussian Blur, Otsu thresholding, operasi morfologi, deteksi kontur, dan pembentukan bounding box, sedangkan MobileNetV2 digunakan sebagai model klasifikasi berbasis transfer learning. Dataset yang digunakan terdiri dari 3.369 citra yang dibagi menjadi data training, validation, dan testing. Model akhir yang diterapkan pada sistem web adalah Skenario 4 dengan data testing sebanyak 501 citra. Berdasarkan hasil pengujian, model memperoleh test loss sebesar 0,0875 dan test accuracy sebesar 0,9661 atau 96,61%. Hasil classification report menunjukkan nilai accuracy sebesar 0,97, serta nilai macro average dan weighted average precision, recall, dan F1-score sebesar 0,97. Sistem yang dikembangkan mampu menampilkan hasil deteksi berupa bounding box, label kelas, nilai confidence, jumlah objek, dan citra hasil anotasi melalui antarmuka web. Meskipun demikian, sistem masih memiliki keterbatasan pada kondisi objek yang saling bertumpuk, saling bersentuhan, atau memiliki pencahayaan kurang merata karena proses deteksi masih berbasis segmentasi kontur", "type": "thesis", "status_changed": "2026-08-06 04:10:48", "subjects": [ 123, 459, 462, 463 ], "metadata_visibility": "show", "documents": [ { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 508906, "filesize": 4972952, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116.pdf", "mtime": "2026-08-06 03:38:25", "hash": "a7370fc167ff092107a9e7ff2d6fe328", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/508906", "objectid": 220848 } ], "pos": 1, "formatdesc": "Full text", "mime_type": "application\/pdf", "placement": 1, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116.pdf", "docid": 220848, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220848" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 508928, "filesize": 1265387, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_SIMILARITY.pdf", "mtime": "2026-08-06 03:40:07", "hash": "cc20cf34771967115ac1d93855a654cd", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/508928", "objectid": 220855 } ], "pos": 2, "formatdesc": "Similarity", "mime_type": "application\/pdf", "placement": 2, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "public", "main": "RAMA_55201_2213020116_SIMILARITY.pdf", "docid": 220855, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220855" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 508980, "filesize": 882789, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_01_front_ref.pdf", "mtime": "2026-08-06 03:43:17", "hash": "a43094a882fe3f233da7b9470b402963", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/508980", "objectid": 220873 } ], "pos": 3, "formatdesc": "Cover sd BAB 1 + References", "mime_type": "application\/pdf", "placement": 3, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "public", "main": "RAMA_55201_2213020116_0723098303_0719068702_01_front_ref.pdf", "docid": 220873, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220873" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509019, "filesize": 626101, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_02.pdf", "mtime": "2026-08-06 03:44:57", "hash": "75607f88f296c0296dac9e7dd8504e50", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509019", "objectid": 220887 } ], "pos": 4, "formatdesc": "BAB 2", "mime_type": "application\/pdf", "placement": 4, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116_0723098303_0719068702_02.pdf", "docid": 220887, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220887" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509038, "filesize": 710750, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_03.pdf", "mtime": "2026-08-06 03:46:22", "hash": "02e1ee398cffd307f4d056e1c9aeb786", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509038", "objectid": 220896 } ], "pos": 5, "formatdesc": "BAB 3", "mime_type": "application\/pdf", "placement": 5, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116_0723098303_0719068702_03.pdf", "docid": 220896, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220896" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509059, "filesize": 946488, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_04.pdf", "mtime": "2026-08-06 03:48:51", "hash": "949ac2d3e96988b9f0492ee47c3911ea", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509059", "objectid": 220903 } ], "pos": 6, "formatdesc": "BAB 4", "mime_type": "application\/pdf", "placement": 6, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116_0723098303_0719068702_04.pdf", "docid": 220903, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220903" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509073, "filesize": 225917, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_05.pdf", "mtime": "2026-08-06 03:50:01", "hash": "953cdee0ecb45b5fc506fb872ccac09e", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509073", "objectid": 220909 } ], "pos": 7, "formatdesc": "BAB 5", "mime_type": "application\/pdf", "placement": 7, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116_0723098303_0719068702_05.pdf", "docid": 220909, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220909" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509116, "filesize": 222043, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_06_ref.pdf", "mtime": "2026-08-06 03:52:31", "hash": "d949a76bf45539391519e2fee21784c4", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509116", "objectid": 220923 } ], "pos": 8, "formatdesc": "References", "mime_type": "application\/pdf", "placement": 8, "content": "bibliography", "format": "text", "rev_number": 4, "eprintid": 27180, "security": "public", "main": "RAMA_55201_2213020116_0723098303_0719068702_06_ref.pdf", "docid": 220923, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220923" }, { "language": "id", "files": [ { "hash_type": "MD5", "datasetid": "document", "fileid": 509133, "filesize": 2999872, "mime_type": "application\/pdf", "filename": "RAMA_55201_2213020116_0723098303_0719068702_07_lamp.pdf", "mtime": "2026-08-06 03:53:29", "hash": "e5039c7f9cc1d8c8719856399ca8b6af", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/file\/509133", "objectid": 220930 } ], "pos": 9, "formatdesc": "Lampiran", "mime_type": "application\/pdf", "placement": 9, "content": "accepted", "format": "text", "rev_number": 2, "eprintid": 27180, "security": "validuser", "main": "RAMA_55201_2213020116_0723098303_0719068702_07_lamp.pdf", "docid": 220930, "license": "cc_public_domain", "uri": "http:\/\/repository.unpkediri.ac.id\/id\/document\/220930" } ], "uri": "http:\/\/repository.unpkediri.ac.id\/id\/eprint\/27180", "thesis_type": "other", "keywords": "Deteksi Multi-Objek, Klasifikasi Citra, Mangga, MobileNetV2, OpenCV", "eprint_status": "archive", "contributors": [ { "name": { "lineage": null, "given": "Daniel", "family": "Swanjaya", "honourific": null }, "type": "http:\/\/www.loc.gov\/loc.terms\/relators\/THS", "id": 723098303 }, { "name": { "lineage": null, "given": "Resty", "family": "Wulanningrum", "honourific": null }, "type": "http:\/\/www.loc.gov\/loc.terms\/relators\/THS", "id": 719068702 } ], "title": "PENGEMBANGAN SISTEM CERDAS DETEKSI VARIETAS MANGGA MULTI-OBJEK DENGAN MOBILENETV2 BERBASIS WEB", "thesis_name": "dphil", "userid": 65157, "eprintid": 27180, "lastmod": "2026-08-06 04:10:48", "referencetext": "Aksa, M., Ranggareksa, A., Aras, M. R. F., Kaswar, A. B., Andayani, D. D., & Intam, R. N. J. S. (2025). Deteksi Tingkat Kematangan Buah Mangga Berdasarkan Fitur Warna Menggunakan Pengolahan Citra Digital. Jurnal Teknik Informatika Dan Sistem Informasi, 11(2), 240–250.\r\nAnhar, A., & Putra, R. A. (2023). Perancangan dan Implementasi Self-Checkout System pada Toko Ritel menggunakan Convolutional Neural Network (CNN). ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, 11(2), 466.\r\nAstuti, W., Trisnaningsih, U., & Budirokhman, D. (2022). PENENTUAN UMUR PANEN BEBERAPA KULTIVAR MANGGA ( Mangifera indica L .) HARVESTING DETERMINATION OF SEVERAL MANGO ( Mangifera indica L .) CULTIVARS. 9(2), 280–292.\r\nAulia, R., & Husna, W. (2025). Klasifikasi Jenis Buah Mangga Menggunakan Convolutional Neural Network (CNN) Berbasis Citra Digital. JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, 6(4), 417–421. https:\/\/doi.org\/10.62527\/jitsi.6.4.473\r\nAzli, P. A., Syahrani, A., & Swara, G. Y. (2025). Jurnal Informatika : Jurnal pengembangan IT Segmentasi Citra Daun Tomat untuk Klasifikasi Penyakit Tanaman Menggunakan Support Vector Machine ( SVM ). Jurnal Informatika: Jurnal Pengembangan IT, 10(4), 997–1008. https:\/\/doi.org\/10.30591\/jpit.v10i4.9404\r\nBaswarsiati, N., & Yuniarti, N. (2007). Karakter Morfologis dan Beberapa Keunggulan Mangga Podang Urang ( Mangifera indica L .). Journal Article \/\/ Buletin Plasma Nutfah, 13(2), 62–69. https:\/\/doi.org\/10.21082\/blpn.v13n2.2007.p62-69\r\nDong, Z., Wang, J., Sun, P., & Ran, W. (2024). Mango variety classification based on convolutional neural network with attention mechanism and near-infrared spectroscopy. Journal of Food Measurement and Characterization, 18(1), 1–11. https:\/\/doi.org\/DOI:10.1007\/s11694-023-02320-w\r\nFitri, Z. E., Aprilia, R., Madjid, A., Mujibtamala, A., & Imron, N. (2022). Ensiklopedia Digital Berdasarkan Klasifikasi Varietas Buah Mangga ( Mangifera spp . ) Menggunakan Algoritma Backpropagation Digital Encyclopedia Based on The Classification of Mango Varieties ( Mangifera spp . ) Using Backpropagation Algorithm. 11(28). https:\/\/doi.org\/10.34010\/komputika.v11i2.5513\r\nHarahap, L. S., & Kembaren, M. F. H. (2025). Klasifikasi Objek Menggunakan Convolutional Neural Network pada Citra Satelit. RIGGS: Journal of Artificial Intelligence and Digital Business, 4(2), 4663–4667.\r\nHartono, A. C., & Muslikh, A. R. (2025). Penerapan Transfer Learning MobileNetV2 Pada Klasifikasi Citra Jenis Buah-Buahan. Journal of Information System and Application Development, 3(2), 103–111.\r\nHastungkoro, A. W., Dwi, A., Wicaksono, P., & Rosita, Y. D. (2024). Klasifikasi Kualitas dan Kematangan Pisang Cavendish Menggunakan Convolutional Neural Network Pisang merupakan Faktor-faktor perorangan. Jurnal Saintekom : Sains, Teknologi, Komputer Dan Manajemen, 14(2), 185–194. https:\/\/doi.org\/https:\/\/doi.org\/10.33020\/saintekom.v14i2.686\r\nKomah, N. N., & Hermanto, D. (2025). Classification of Mango Varieties from Leaf Images Using ResNet-50 CNN Architecture. Brilliance Research of Artificial Intelligence, 5(1), 559–567. https:\/\/doi.org\/10.47709\/brilliance.v5i1.6571\r\nKompaspedia. (2024). Komoditas Mangga: Sejarah, Manfaat, Produsen Dunia, dan Sentra Produksi di Indonesia. Kompaspedia. https:\/\/kompaspedia.kompas.id\/baca\/paparan-topik\/komoditas-mangga-sejarah-manfaat-produsen-dunia-dan-sentra-produksi-di-indonesia\r\nMbaba, P., Anwar, K., Yusrianto, S. R., & Kartawati, A. E. (2022). PENERAPAN METODE CONVOLUTION NEURAL NETWORKS UNTUK MENGIDENTIFIKASI WAJAH KELELAHAN. 1(November), 107–114.\r\nNaghipour, M., Ling, L. S., & Connie, T. (2024). A Review of AI Techniques in Fruit Detection and Classification : Analyzing Data , Features and AI Models Used in Agricultural Industry. International Journal of Technology, 15(October 2023), 585–596. https:\/\/doi.org\/10.14716\/ijtech.v15i3.6404\r\nNugroho, C. W., Nurtanio, I., & Jalil, A. (2025). Determination of Copra Quality Based on Contour Image Using the Canny Edge Detection Method Penentuan Kualitas Kopra Berbasis Citra Kontur Menggunakan Metode Canny Edge Detection. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(January), 436–450. https:\/\/doi.org\/https:\/\/doi.org\/10.57152\/malcom.v5i1.1823\r\nNurcahyati, A. D., Akbar, R. M., & Zahara, S. (2022). Klasifikasi Citra Penyakit pada Daun Jagung Menggunakan Deep learning dengan Metode Convolution Neural Network (CNN). SUBMIT: Jurnal Ilmiah Teknologi Infomasi Dan Sains, 2(1), 43–51.\r\nOktafanda, E., Lubis, A., & Prasiwiningrum, E. (2025). Detection of Oil Palm Seedling Disease Based on Leaf Images Using the MobileNetV2-CNN Architecture. 7(1). https:\/\/doi.org\/10.35842\/ijicom\r\nPurwono, P., Ma’arif, A., Rahmaniar, W., Fathurrahman, H. I. K., Frisky, A. Z. K., & ul Haq, Q. M. (2022). Understanding of convolutional neural network (cnn): A review. International Journal of Robotics and Control Systems, 2(4), 739–748.\r\nPutra, D. R. R., & Saputra, R. A. (2023). Implementasi Convolutional Neural Network (CNN) untuk Mendeteksi Penggunaan Masker pada Gambar. Jurnal Informatika Dan Teknik Elektro Terapan, 11(3).\r\nRahmawati, A., Yulianti, I., & Nurajizah, S. (2023). IMAGE SEGMENTATION ANALYSIS USING OTSU THRESHOLDING AND. JURNAL RISET INFORMATIKA, 6(1). https:\/\/doi.org\/https:\/\/doi.org\/10.34288\/jri.v6i1.261\r\nRismayanti, A., & Rahmadewi, R. (2025). DETEKSI DAN KLASIFIKASI TINGKAT KEMATANGAN BUAH MANGGA HARUM MANIS MENGGUNAKAN YOU ONLY LOOK ONCE ( YOLO ) V8. JATI (Jurnal Mahasiswa Teknik Informatika), 9(3), 3645–3654.\r\nRodhiya, H. R., Data, M., & Fauzi, M. A. (2025). Evaluasi Kinerja Algoritma Pembelajaran Mesin dalam Klasifikasi Data Keystroke Dynamics. Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer, 9(8), 1–9.\r\nSandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520.\r\nSari, V. K., Sa, H., & Rusdiana, R. Y. (2024). Keragaman Mangga ( Mangifera indica L .) di Jawa Timur Berdasarkan Karakter Morfologi : Studi Kasus di Kabupaten Jember Diversity of Mango ( Mangifera indica L .) in East Java Based on Morphological Characteristic : Case Study in Jember District. Jurnal.Ugm.Ac.Id\/Jbp, 13(1), 90–103. https:\/\/doi.org\/https:\/\/doi.org\/10.22146\/veg.84921\r\nSutisna, S. P., Waluyo, R., Aldiansyah, F., & Rahmat, M. (2020). APLIKASI PENGOLAHAN CITRA UNTUK PROSES SORTASI BUAH MANGGA BERDASARKAN DIMENSI DAN BOBOT. Jurnal Ilmiah Rekayasa Pertanian Dan Biosistem, 8(1), 12–19. https:\/\/doi.org\/10.29303\/jrpb.v8i1.151\r\nWardani, K. R., & Leonardi, L. (2023). Klasifikasi Penyakit pada Daun Anggur menggunakan Metode Convolutional Neural Network. Jurnal Tekno Insentif, 17(2), 112–126.\r\nYanto, B., Rouza, E., Fimawahib, L., Hayadi, B. H., & Pratama, R. R. (2023). Penerapan algoritma deep learning convolutional neural network dalam menentukan kematangan buah jeruk manis berdasarkan citra red green blue (RGB). Jurnal Teknologi Informasi Dan Ilmu Komputer, 10(1), 59–66." }