Optimizing Bit Depth for Longan Seedling Identification Using ANN and GLCM

Rizki Andika; Gasim Gasim; Zaid Romegar Mair

doi:10.47709/brilliance.v5i2.6811

Authors

Rizki Andika Universitas Indo Global Mandiri, Indonesia
Gasim Universitas Indo Global Mandiri, Indonesia
Zaid Romegar Mair Universitas Indo Global Mandiri, Indonesia

DOI:

https://doi.org/10.47709/brilliance.v5i2.6811

Keywords:

Artificial Neural Network, Bit depth, Feature Extraction, GLCM, Longan

Abstract

Accurate identification of longan (Dimocarpus longan) seedling varieties is essential for agribusiness to select cultivars meeting market and environmental needs, but manual identification is error-prone due to similar leaf textures. This study optimizes grayscale image bit depth using Artificial Neural Networks (ANN) and Gray Level Co-occurrence Matrix (GLCM) to enhance longan seedling classification accuracy, addressing a gap in texture-based identification efficiency. Leaf images from five longan varieties (Itoh, Pingpong, Merah, Matalada, Diamond River) were captured with a USB digital microscope and converted to grayscale at bit depths of 4 (0–15), 5 (0–31), 6 (0–63), 7 (0–127), and 8 (0–255). Texture features (contrast, correlation, energy, homogeneity, entropy, standard deviation) were extracted using MATLAB. An ANN model, trained with the traingdx algorithm on 800 training and 200 test images, classified the varieties. The 6-bit and 4-bit depths yielded the highest accuracy (84.5%), followed by 7-bit (84.0%), 5-bit (83.5%), and 8-bit (82.0%), with Matalada achieving 90.0% accuracy. The 8-bit depth introduced texture noise, reducing performance. A 6-bit depth is optimal for longan leaf texture classification, though distinguishing similar varieties like Itoh and Pingpong remains challenging. Future research should incorporate color or morphological features to improve agricultural image processing.

References

Abdi Wahyu Nugroho. (2024). KERAGAMAN FENETIK BEBERAPA VARIETAS KELENGKENG (Dimocarpus longan L.) BERDASARKAN KARAKTER BATANG DAN DAUN. UNIVERSITAS ISLAM NEGERI MAULANA MALIK IBRAHIM MALANG.

Aini, N., Setyati, D., & Umiyah. (2014). STRUKTUR ANATOMI DAUN LENGKENG (DIMOCARPUS LONGAN LOUR.) KULTIVAR LOKAL, ITOH, PINGPONG DAN DIAMOND RIVER.

Al Wajieh, M. W. (2023). Klasifikasi Jenis Kelengkeng Berdasarkan Morfologi Daun Dengan Ekstraksi Ciri RGB, GLCM, dan Bentuk Menggunakan Metode BPNN. Jurnal Aplikasi Teknologi Informasi Dan Manajemen (JATIM), 4(2), 183–193. https://doi.org/10.31102/jatim.v4i2.2341

Anggraini, C. (2024). KLASIFIKASI DAUN KELENGKENG MENGGUNAKAN METODE GRAY LEVEL CO- OCCURRENCE MATRIX ( GLCM ) DAN K- NEAREST NEIGHBOR ( KNN ). 11(2), 72–78. https://doi.org/10.30656/jsii.v11i2.9157

Arnita, Marpaung, F., Aulia, F., & Nabila, R. C. (2022). Computer Vision Dan Pengolahan Citra Digital (Ahmad Baharuddin Surya (ed.); 1st ed.). PUSTAKA AKSARA. www.pustakaaksara.co.id

Gasim, G., Heriansyah, R., Puspasari, S., Irfani, M. H., Purnamasari, E., Permatasari, I., & Samsuryadi, S. (2025). Improving the Accuracy of Concrete Mix Type Recognition with ANN and GLCM Features Based on Image Resolution. Jurnal Infotel, 17(1), 96–110. https://doi.org/10.20895/infotel.v17i1.1201

Hasanah, S. H., & Permatasari, S. M. (2020). METODE KLASIFIKASI JARINGAN SYARAF TIRUAN BACKPROPAGATION PADA MAHASISWA STATISTIKA UNIVERSITAS TERBUKA. BAREKENG?: Jurnal Ilmu Matematika Dan Terapan, 14(1), 243–252. https://doi.org/https://doi.org/10.30598/barekengvol14iss2pp243-252

Khaidir, Reyna Buryani Al’Safinat, A. Muhammad Fuad Fadhlurrahman, By Tri Agung Nusantara Kr. J. Tompong, & Jessica Crisfin Lapendy. (2024). Klasifikasi Tingkat Kesegaran Sayur Bayam Berdasarkan Tekstur Daunnya Berbasis Citra Digital. Journal of Deep Learning, Computer Vision and Digital Image Processing, 2022, 88–99. https://doi.org/10.61255/decoding.v2i2.549

Mahbod, A., Schaefer, G., Löw, C., Dorffner, G., Ecker, R., & Ellinger, I. (2021). Investigating the impact of the bit depth of fluorescence-stained images on the performance of deep learning-based nuclei instance segmentation. Diagnostics, 11(6). https://doi.org/10.3390/diagnostics11060967

MathWorks. (2024). Matlab Documentation. https://www.mathworks.com/products/matlab.html?s_tid=hp_products_matlab

Nafiiyah, N., & Prasetyo, P. R. (2023). Klasifikasi Jenis Kelengkeng Berdasarkan Daun Menggunakan Convolutional Neural Network Multilayer Perceptron. Jurnal Telematika, 17(2), 75–79. https://doi.org/10.61769/telematika.v17i2.496

Nugraha, D. S. (2023). PENGARUH PENCAHAYAAN PADA PEMOTRETAN URAT DAUN PADA IDENTIFIKASI JENIS BIBIT KELENGKENG DENGAN METODE PENGENALAN JST-PB DAN FITUR GLCM.

Srg, S. A. R., Irhamna, Aldi, M. F., Ramadhan, M., & Siregar, N. L. (2023). Ekstraksi Fitur Citra Berdasarkan Tekstur Dengan Glcm (Gray Level Co-Occurrence). JUTISAL (Jurnal Teknik Informatika Komputer Universal), 3(1), 44–51.

Syam, A. A., Rifka, S., & Aulia, S. (2021). Implementasi Pengolahan Citra Untuk Identifikasi Daun Tanaman Obat Menggunakan Levenberg-Marquardt Backpropagation. Elektron?: Jurnal Ilmiah, 13, 1–8. https://doi.org/10.30630/eji.0.0.176

Wilsen, E. B., Gasim, G., & Teguh, R. (2021). Perbandingan Akurasi Pengenalan Kadar Semen Berdasarkan Tingkat Pencahayaan Menggunakan Jaringan Syaraf Tiruan. Jurnal Algoritme, 2(1), 55–61.