Fruit Ripeness Analysis Using Colour Transition Matrix and Eigenvalues
DOI:
https://doi.org/10.30871/jaic.v10i2.12382Keywords:
Banana Ripeness, eigenvalue, image processing, Colour Dominant Transition MatrixAbstract
Fruit ripeness classification plays an important role in maintaining fruit quality, reducing post-harvest losses, and ensuring consistent grading in agricultural supply chains. Bananas, particularly the Cavendish variety, are widely traded globally and require reliable methods for determining ripeness levels during distribution and storage. However, conventional visual inspection methods remain subjective and often lead to inconsistent evaluations. This study proposes an interpretable mathematical approach for fruit ripeness analysis based on the Colour Dominant–Transition Matrix (CDTM) combined with eigenvalue analysis. The dataset consists of 3,495 real images of Cavendish bananas obtained from an open-access dataset. Image preprocessing includes object segmentation, colour normalization, and noise reduction to ensure illumination consistency. Dominant colour features are extracted using K-Means clustering in the CIELAB colour space, and the CDTM is constructed to model spatial colour transition probabilities. The second-largest eigenvalue (λ₂) is used as a quantitative indicator of colour stability and homogeneity. Experimental results show that optimally ripe bananas produce the lowest λ₂ value (0.1045), indicating high colour uniformity, while unripe bananas exhibit the highest λ₂ value (0.7972). Using λ₂ as a single feature, an SVM classifier achieved an accuracy of 64%. Although the classification performance remains moderate, the proposed CDTM-based eigenvalue feature provides an interpretable and computationally efficient indicator suitable for non-destructive fruit ripeness monitoring systems.
Downloads
References
[1] J. Blasco, N. Aleixos, and E. Moltó, “Machine Vision System for Automatic Quality Grading of Fruit,” Biosyst Eng, vol. 85, no. 4, pp. 415–423, Aug. 2003, doi: 10.1016/S1537-5110(03)00088-6.
[2] D. Lorente, N. Aleixos, J. Gómez-Sanchis, S. Cubero, O. L. García-Navarrete, and J. Blasco, “Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment,” May 2012. doi: 10.1007/s11947-011-0725-1.
[3] S. Hira and S. Lande, “Detection of fruit ripeness using image processing,” Int J Health Sci (Qassim), pp. 3874–3886, Jul. 2022, doi: 10.53730/ijhs.v6nS6.10146.
[4] L. E. Chuquimarca, B. X. Vintimilla, and S. A. Velastin, “A review of external quality inspection for fruit grading using CNN models,” Artificial Intelligence in Agriculture, vol. 14, pp. 1–20, Dec. 2024, doi: 10.1016/J.AIIA.2024.10.002.
[5] D. D. Andayani, A. N. A. Rafii, K. Mahdar, W. A. Ahmad, and M. Mustamin, “Papaya Fruit Quality Classification Based on Lab Colour and Texture Features Using Artificial Neural Networks (ANN),” INTEK: Jurnal Penelitian, vol. 10, no. 1, pp. 15–21, Jun. 2023, doi: 10.31963/intek.v9i2.4246.
[6] W. Wijaya Widiyanto and E. Purwanto, “Classification Of Mango Fruit Quality Based On Texture Characteristics Of Glcm (Gray Level Co-Occurrence Matrices) With Algorithm K-NN (K-Nearest Neighbors),” vol. 20, no. 1, pp. 31–40, 2019, [Online]. Available: http://jurnalnasional.ump.ac.id/index.php/Techno
[7] T. Y. Prahudaya and A. Harjoko, “Metode Klasifikasi Mutu Jambu Biji Menggunakan Knn Berdasarkan Fitur Warna Dan Tekstur,” Jurnal Teknosains, vol. 6, no. 2, p. 113, Aug. 2017, doi: 10.22146/teknosains.26972.
[8] S. Choirunisa and S. -, “Klasifikasi Tingkat Kematangan Citra Buah Tomat Menggunakan Densenet-121,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 3, Jul. 2025, doi: 10.23960/jitet.v13i3.6652.
[9] R. K. Yadav and R. K. Goyal, Post Harvest Technology of Horticultural Crops. Jodhpur, India: Agrobios (India), 2012.
[10] Y. Chang and N. Mukai, “Colour Feature Based Dominant Colour Extraction,” IEEE Access, vol. 10, pp. 93055–93061, 2022, doi: 10.1109/ACCESS.2022.3202632.
[11] Y. Kynash and M. Semeniv, “New Approach to Dominant and Prominent Colour Extraction in Images with a Wide Range of Hues,” Technologies (Basel), vol. 13, no. 6, Jun. 2025, doi: 10.3390/technologies13060230.
[12] B. M. Nicolaï et al., “Spatio-temporal dynamics of the metabolome of climacteric fruit during ripening and post-harvest storage,” Oct. 31, 2023, Oxford University Press. doi: 10.1093/jxb/erad230.
[13] C. Theoharatos, “Colour image segmentation using Laplacian eigenmaps,” J Electron Imaging, vol. 18, Apr. 2009, doi: 10.1117/1.3122369.
[14] M. Gao, C. Song, Q. Zhang, X. Zhang, Y. Li, and F. Yuan, “Research Progress on Colour Image Quality Assessment,” Sep. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/jimaging11090307.
[15] S. Lafon and A. B. Lee, “Diffusion Maps and Coarse-Graining: A Unified Framework for Dimensionality Reduction, Graph Partitioning and Data Set Parameterization.”
[16] L. E. Chuquimarca, B. X. Vintimilla, and S. A. Velastin, “Banana Ripeness Level Classification Using a Simple CNN ModeTrained with Real and Synthetic Datasets,” in Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications, Lda, 2023, pp. 536–543. doi: 10.5220/0011654600003417.
[17] F. Garcia-Lamont, J. Cervantes, A. López, and L. Rodriguez, “Segmentation of images by colour features: A survey,” Neurocomputing, vol. 292, pp. 1–27, May 2018, doi: 10.1016/J.NEUCOM.2018.01.091.
[18] P. Dhiman, A. Kaur, V. R. Balasaraswathi, Y. Gulzar, A. A. Alwan, and Y. Hamid, “Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review,” Sustainability (Switzerland), vol. 15, no. 12, Jun. 2023, doi: 10.3390/su15129643.
[19] G. Sharma, W. Wu, and E. N. Dalal, “The CIEDE2000 Colour-Difference Formula: Implementation Notes, Supplementary Test Data, and Mathematical Observations,” Col Res Appl, vol. 30, pp. 21–30, 2005, doi: 10.1002/col.
[20] R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural Features for Image Classification,” IEEE Trans. Syst. Man Cybern., 1973.
[21] D. A. Levin, Y. Peres, and E. L. Wilmer, “Markov Chains and Mixing Times, second edition.”
[22] M. Rizzo, M. Marcuzzo, A. Zangari, A. Gasparetto, and A. Albarelli, “Fruit ripeness classification: A survey,” Artificial Intelligence in Agriculture, vol. 7, pp. 44–57, Mar. 2023, doi: 10.1016/J.AIIA.2023.02.004.
[23] C. S. Nandi, B. Tudu, and C. Koley, “A Machine Vision-Based Maturity Prediction System for Sorting of Harvested Mangoes,” IEEE Trans Instrum Meas, vol. 63, no. 7, pp. 1722–1730, 2014, doi: 10.1109/TIM.2014.2299527.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Septiana Sulastri Septi, Yufis Azhar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
