Visual Classification of Spirulina Microalgae Maturity Stages Based on Color Using Convolutional Neural Networks
##plugins.themes.bootstrap3.article.main##
Abstract
Manual assessment of microalgae maturity is subjective and does not scale well. This study evaluates whether a convolutional neural network can classify Spirulina microalgae into five visual maturity stages (dead, unripe, under-ripe, medium-ripe, ripe) using color alone. From 5,005 images collected over three months at a single facility, byte-exact duplicates accounted for 41.9% of the dataset; after removal, 2,909 unique images remained. To prevent near-duplicate images from the same session leaking across folds, evaluation used a group-stratified 5-fold cross-validation scheme, with groups defined via perceptual-hash clustering. An ablation across four preprocessing configurations found that combining CLAHE with augmentation, the original proposed method, was numerically weakest (94.74% ± 2.15% accuracy versus 97.43% ± 0.89% with no preprocessing), differing significantly from CLAHE alone (p = 0.021) though not from the plain baseline at this sample size (p = 0.085). A separate comparison, matching fine-tuning depth (last 30 layers) and preprocessing across a custom CNN, MobileNetV2, and ResNet50, found ResNet50 highest at 99.52% ± 0.18% accuracy, significantly ahead of the custom CNN (97.06% ± 1.39%; p = 0.024), while MobileNetV2 showed severe fold-to-fold instability. The custom CNN's advantage lay in efficiency: 54.8 times fewer parameters and roughly 3.5 times faster inference than ResNet50, for only a small accuracy trade-off. A brief, unlabeled field test on six images outside the lab setting showed frequent disagreement among the three models, suggesting limited transfer from controlled to field conditions. Grad-CAM maps are presented as an indication of model attention, not evidence of underlying chlorophyll degradation biochemistry
##plugins.themes.bootstrap3.article.details##
How to Cite
Hermawan, D., & Fahmi Zuhri, H. (2026). Visual Classification of Spirulina Microalgae Maturity Stages Based on Color Using Convolutional Neural Networks. International Journal of Basic and Applied Science, 15(2), 33–51. https://doi.org/10.35335/ijobas.v15i2.875
References
[1] H. Mundhada et al., "Fruit detection and three-stage maturity grading using CNN," Int. J. Next-Gener. Comput., vol. 14, no. 1, 2023, doi: 10.47164/ijngc.v14i1.1099.
[2] L. Chuquimarca, B. Vintimilla, and S. Velastin, "Banana ripeness level classification using a simple CNN model trained with real and synthetic datasets," arXiv:2504.08568, 2025, doi: 10.48550/arXiv.2504.08568.
[3] J. Pyo et al., "Drone-borne sensing of major and accessory pigments in algae using deep learning modeling," GISci. Remote Sens., vol. 59, no. 1, pp. 310–332, 2022, doi: 10.1080/15481603.2022.2027120.
[4] S. Shan et al., "Automated red tide algae recognition by the color microscopic image," in Proc. 2020 13th Int. Congr. Image Signal Process. BioMed. Eng. Inform. (CISP-BMEI), 2020, pp. 852–861, doi: 10.1109/CISP-BMEI51763.2020.9263574.
[5] Y. Zhang et al., "Blue-green algae recognition based on rotation invariant uniform LBP and color information," in Proc. 2020 IEEE 5th Int. Conf. Signal Image Process. (ICSIP), 2020, pp. 46–50, doi: 10.1109/ICSIP49896.2020.9339427.
[6] Y. Guo, L. Gao, and X. Li, "A deep learning model for green algae detection on SAR images," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–14, 2022, doi: 10.1109/TGRS.2022.3215895.
[7] G. S. Kim et al., "Classification technique of algae using hyperspectral images of algae culture media," Appl. Sci., vol. 13, no. 7, p. 4631, 2023, doi: 10.3390/app13074631.
[8] P. Otálora et al., "Microalgae classification based on machine learning techniques," Algal Res., vol. 55, p. 102256, 2021, doi: 10.1016/j.algal.2021.102256.
[9] L. Nicolás-Sáenz et al., "Abanicco: A new color space for multi-label pixel classification and color analysis," Sensors, vol. 23, no. 6, p. 3338, 2023, doi: 10.3390/s23063338.
[10] A. Gijsenij, T. Gevers, and J. van de Weijer, "Computational color constancy: Survey and experiments," IEEE Trans. Image Process., vol. 20, no. 9, pp. 2475–2489, 2011, doi: 10.1109/TIP.2011.2118224.
[11] B. Büyükarıkan and E. Ülker, "Using convolutional neural network models illumination estimation according to light colors," Optik, vol. 271, Art. no. 170058, 2022, doi: 10.1016/j.ijleo.2022.170058.
[12] D. J. Steele, "Cellular viability and the occurrence and significance of chlorophyll allomers during phytoplankton turnover," Ph.D. dissertation, Fac. Sci. Technol., Bournemouth Univ., Poole, U.K., 2014. [Online]. Available: https://eprints.bournemouth.ac.uk/21777/
[13] L. Ma et al., "Prediction of banana maturity based on the sweetness and color values of different segments during ripening," Curr. Res. Food Sci., vol. 5, pp. 1808–1817, 2022, doi: 10.1016/j.crfs.2022.08.024.
[14] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444, 2015, doi: 10.1038/nature14539.
[15] D. M. Madkour, M. I. Shapiai, S. E. Mohamad, H. Aly, Z. H. Ismail, and M. Z. Ibrahim, "A systematic review of deep learning microalgae classification and detection," IEEE Access, vol. 11, pp. 57529–57555, 2023, doi: 10.1109/ACCESS.2023.3280410.
[16] A. Kamilaris and F. X. Prenafeta-Boldú, "A review of the use of convolutional neural networks in agriculture," J. Agric. Sci., vol. 156, no. 3, pp. 312–322, 2018, doi: 10.1017/S0021859618000436.
[17] M. M. Taye, "Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions," Computation, vol. 11, no. 3, p. 52, 2023, doi: 10.3390/computation11030052.
[18] Z. Xian, R. Huang, D. Towey, and C. Yue, "Convolutional neural network image classification based on different color space," Tsinghua Sci. Technol., vol. 30, no. 1, pp. 402–417, 2025, doi: 10.26599/TST.2024.9010001.
[19] L. Chen et al., "Review of image classification algorithms based on convolutional neural networks," Remote Sens., vol. 13, no. 22, p. 4712, 2021, doi: 10.3390/rs13224712.
[20] D. Sahoo et al., Eds., The Algae World. Dordrecht, The Netherlands: Springer, 2015, doi: 10.1007/978-94-017-7321-8.
[21] S. Banayan, M. Jahadi, and K. Khosravi-Darani, "Pigment productions by Spirulina platensis as a renewable resource," J. Appl. Biotechnol. Rep., vol. 9, no. 2, pp. 614–621, 2022, doi: 10.30491/JABR.2021.292076.1406.
[22] K. A. Riihiaho et al., "Photobioreactor design utilizing procedural three-dimensional modelling and ray tracing," J. R. Soc. Interface., vol. 22, no. 222, p. 20240451, 2025, doi: 10.1098/rsif.2024.0451.
[23] K. Price and I. H. Farag, "Resources conservation in microalgae biodiesel production," Int. J. Eng. Tech. Res., vol. 1, no. 8, pp. 49–56, 2013. [Online]. Available: https://www.researchgate.net/publication/259868136_Resources_Conservation_in_Microalgae_Biodiesel_Production
[24] T. Lafarga et al., "Spirulina for the food and functional food industries," Food Res. Int., vol. 137, p. 109356, 2020, doi: 10.1016/j.foodres.2020.109356.
[25] N. Yusuf, N. M. Athirah, and A. Suhaila, "Antioxidative responses of Chlorella vulgaris under different growth phases," Squalen Bull. Mar. Fish. Postharvest Biotechnol., vol. 17, no. 3, pp. 111–120, 2022, doi: 10.15578/squalen.692.
[26] S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in Proc. 32nd Int. Conf. Mach. Learn. (ICML), 2015, pp. 448–456. [Online]. Available: https://proceedings.mlr.press/v37/ioffe15.html
[27] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014. [Online]. Available: https://jmlr.org/papers/v15/srivastava14a.html
[28] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.
[29] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
[30] J. Cohen, "A coefficient of agreement for nominal scales," Educ. Psychol. Meas., vol. 20, no. 1, pp. 37–46, 1960, doi: 10.1177/001316446002000104.
[31] B. W. Matthews, "Comparison of the predicted and observed secondary structure of T4 phage lysozyme," Biochim. Biophys. Acta, vol. 405, no. 2, pp. 442–451, 1975, doi: 10.1016/0005-2795(75)90109-9.
[32] D. J. Hand and R. J. Till, "A simple generalisation of the area under the ROC curve for multiple class classification problems," Mach. Learn., vol. 45, pp. 171–186, 2001, doi: 10.1023/A:1010920819831.
[33] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual explanations from deep networks via gradient-based localization," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 618–626, doi: 10.1109/ICCV.2017.74.
[34] P. Linli, T. W. Sen, H. Fahmi, and R. Roestam, "Tomato pest and disease identification based on improved deep residual network and transfer learning," Indonesian Journal of Artificial Intelligence and Data Mining, vol. 8, no. 1, pp. 187-200, 2025, doi: 10.24014/ijaidm.v8i1.34038.
[35] R. Setiawan, Y. Yunita, F. F. Rahman, and H. Fahmi, "BISINDO (Bahasa Isyarat Indonesia) sign language recognition using deep learning," IT for Society, vol. 9, no. 1, pp. 17-21, 2024, doi: 10.33021/itfs.v9i1.5076.
[36] Rosalina, G. Sahuri, H. Fahmi, J. W. Moerland, and R. Mandala, "Personality analysis based on the handwriting shape using integration of image processing and machine learning algorithm," in Proc. 2023 7th Int. Conf. New Media Stud. (CONMEDIA), 2023, pp. 27-32, doi: 10.1109/CONMEDIA60526.2023.10428228.
[37] M. Rustam, A. Brotokuncoro, W. H. Utomo, and H. Fahmi, "Deblurring photos with Lucy-Richardson and Wiener filter algorithm in RGBA color," Jurnal Media Infotama, vol. 21, no. 1, pp. 21-25, 2025, doi: 10.37676/jmi.v21i1.6709.
[38] F. O. Paranhos, M. L. C. M. dos Reis, J. dos S. Azevedo, and F. de S. Dias, "Convolutional neural networks for evaluating Spirulina (Arthrospira spp.) adulteration through digital images," Food Anal. Methods, vol. 18, no. 8, pp. 1789–1799, 2025, doi: 10.1007/s12161-025-02826-7.
[39] A. Maali, R. Gheshlaghi, and M. A. Mahdavi, "Maximizing key biochemical products of Spirulina platensis: Optimal light quantities and best harvesting time," OCL, vol. 31, art. no. 21, 2024, doi: 10.1051/ocl/2024019.
[2] L. Chuquimarca, B. Vintimilla, and S. Velastin, "Banana ripeness level classification using a simple CNN model trained with real and synthetic datasets," arXiv:2504.08568, 2025, doi: 10.48550/arXiv.2504.08568.
[3] J. Pyo et al., "Drone-borne sensing of major and accessory pigments in algae using deep learning modeling," GISci. Remote Sens., vol. 59, no. 1, pp. 310–332, 2022, doi: 10.1080/15481603.2022.2027120.
[4] S. Shan et al., "Automated red tide algae recognition by the color microscopic image," in Proc. 2020 13th Int. Congr. Image Signal Process. BioMed. Eng. Inform. (CISP-BMEI), 2020, pp. 852–861, doi: 10.1109/CISP-BMEI51763.2020.9263574.
[5] Y. Zhang et al., "Blue-green algae recognition based on rotation invariant uniform LBP and color information," in Proc. 2020 IEEE 5th Int. Conf. Signal Image Process. (ICSIP), 2020, pp. 46–50, doi: 10.1109/ICSIP49896.2020.9339427.
[6] Y. Guo, L. Gao, and X. Li, "A deep learning model for green algae detection on SAR images," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–14, 2022, doi: 10.1109/TGRS.2022.3215895.
[7] G. S. Kim et al., "Classification technique of algae using hyperspectral images of algae culture media," Appl. Sci., vol. 13, no. 7, p. 4631, 2023, doi: 10.3390/app13074631.
[8] P. Otálora et al., "Microalgae classification based on machine learning techniques," Algal Res., vol. 55, p. 102256, 2021, doi: 10.1016/j.algal.2021.102256.
[9] L. Nicolás-Sáenz et al., "Abanicco: A new color space for multi-label pixel classification and color analysis," Sensors, vol. 23, no. 6, p. 3338, 2023, doi: 10.3390/s23063338.
[10] A. Gijsenij, T. Gevers, and J. van de Weijer, "Computational color constancy: Survey and experiments," IEEE Trans. Image Process., vol. 20, no. 9, pp. 2475–2489, 2011, doi: 10.1109/TIP.2011.2118224.
[11] B. Büyükarıkan and E. Ülker, "Using convolutional neural network models illumination estimation according to light colors," Optik, vol. 271, Art. no. 170058, 2022, doi: 10.1016/j.ijleo.2022.170058.
[12] D. J. Steele, "Cellular viability and the occurrence and significance of chlorophyll allomers during phytoplankton turnover," Ph.D. dissertation, Fac. Sci. Technol., Bournemouth Univ., Poole, U.K., 2014. [Online]. Available: https://eprints.bournemouth.ac.uk/21777/
[13] L. Ma et al., "Prediction of banana maturity based on the sweetness and color values of different segments during ripening," Curr. Res. Food Sci., vol. 5, pp. 1808–1817, 2022, doi: 10.1016/j.crfs.2022.08.024.
[14] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444, 2015, doi: 10.1038/nature14539.
[15] D. M. Madkour, M. I. Shapiai, S. E. Mohamad, H. Aly, Z. H. Ismail, and M. Z. Ibrahim, "A systematic review of deep learning microalgae classification and detection," IEEE Access, vol. 11, pp. 57529–57555, 2023, doi: 10.1109/ACCESS.2023.3280410.
[16] A. Kamilaris and F. X. Prenafeta-Boldú, "A review of the use of convolutional neural networks in agriculture," J. Agric. Sci., vol. 156, no. 3, pp. 312–322, 2018, doi: 10.1017/S0021859618000436.
[17] M. M. Taye, "Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions," Computation, vol. 11, no. 3, p. 52, 2023, doi: 10.3390/computation11030052.
[18] Z. Xian, R. Huang, D. Towey, and C. Yue, "Convolutional neural network image classification based on different color space," Tsinghua Sci. Technol., vol. 30, no. 1, pp. 402–417, 2025, doi: 10.26599/TST.2024.9010001.
[19] L. Chen et al., "Review of image classification algorithms based on convolutional neural networks," Remote Sens., vol. 13, no. 22, p. 4712, 2021, doi: 10.3390/rs13224712.
[20] D. Sahoo et al., Eds., The Algae World. Dordrecht, The Netherlands: Springer, 2015, doi: 10.1007/978-94-017-7321-8.
[21] S. Banayan, M. Jahadi, and K. Khosravi-Darani, "Pigment productions by Spirulina platensis as a renewable resource," J. Appl. Biotechnol. Rep., vol. 9, no. 2, pp. 614–621, 2022, doi: 10.30491/JABR.2021.292076.1406.
[22] K. A. Riihiaho et al., "Photobioreactor design utilizing procedural three-dimensional modelling and ray tracing," J. R. Soc. Interface., vol. 22, no. 222, p. 20240451, 2025, doi: 10.1098/rsif.2024.0451.
[23] K. Price and I. H. Farag, "Resources conservation in microalgae biodiesel production," Int. J. Eng. Tech. Res., vol. 1, no. 8, pp. 49–56, 2013. [Online]. Available: https://www.researchgate.net/publication/259868136_Resources_Conservation_in_Microalgae_Biodiesel_Production
[24] T. Lafarga et al., "Spirulina for the food and functional food industries," Food Res. Int., vol. 137, p. 109356, 2020, doi: 10.1016/j.foodres.2020.109356.
[25] N. Yusuf, N. M. Athirah, and A. Suhaila, "Antioxidative responses of Chlorella vulgaris under different growth phases," Squalen Bull. Mar. Fish. Postharvest Biotechnol., vol. 17, no. 3, pp. 111–120, 2022, doi: 10.15578/squalen.692.
[26] S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in Proc. 32nd Int. Conf. Mach. Learn. (ICML), 2015, pp. 448–456. [Online]. Available: https://proceedings.mlr.press/v37/ioffe15.html
[27] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014. [Online]. Available: https://jmlr.org/papers/v15/srivastava14a.html
[28] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.
[29] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
[30] J. Cohen, "A coefficient of agreement for nominal scales," Educ. Psychol. Meas., vol. 20, no. 1, pp. 37–46, 1960, doi: 10.1177/001316446002000104.
[31] B. W. Matthews, "Comparison of the predicted and observed secondary structure of T4 phage lysozyme," Biochim. Biophys. Acta, vol. 405, no. 2, pp. 442–451, 1975, doi: 10.1016/0005-2795(75)90109-9.
[32] D. J. Hand and R. J. Till, "A simple generalisation of the area under the ROC curve for multiple class classification problems," Mach. Learn., vol. 45, pp. 171–186, 2001, doi: 10.1023/A:1010920819831.
[33] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual explanations from deep networks via gradient-based localization," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 618–626, doi: 10.1109/ICCV.2017.74.
[34] P. Linli, T. W. Sen, H. Fahmi, and R. Roestam, "Tomato pest and disease identification based on improved deep residual network and transfer learning," Indonesian Journal of Artificial Intelligence and Data Mining, vol. 8, no. 1, pp. 187-200, 2025, doi: 10.24014/ijaidm.v8i1.34038.
[35] R. Setiawan, Y. Yunita, F. F. Rahman, and H. Fahmi, "BISINDO (Bahasa Isyarat Indonesia) sign language recognition using deep learning," IT for Society, vol. 9, no. 1, pp. 17-21, 2024, doi: 10.33021/itfs.v9i1.5076.
[36] Rosalina, G. Sahuri, H. Fahmi, J. W. Moerland, and R. Mandala, "Personality analysis based on the handwriting shape using integration of image processing and machine learning algorithm," in Proc. 2023 7th Int. Conf. New Media Stud. (CONMEDIA), 2023, pp. 27-32, doi: 10.1109/CONMEDIA60526.2023.10428228.
[37] M. Rustam, A. Brotokuncoro, W. H. Utomo, and H. Fahmi, "Deblurring photos with Lucy-Richardson and Wiener filter algorithm in RGBA color," Jurnal Media Infotama, vol. 21, no. 1, pp. 21-25, 2025, doi: 10.37676/jmi.v21i1.6709.
[38] F. O. Paranhos, M. L. C. M. dos Reis, J. dos S. Azevedo, and F. de S. Dias, "Convolutional neural networks for evaluating Spirulina (Arthrospira spp.) adulteration through digital images," Food Anal. Methods, vol. 18, no. 8, pp. 1789–1799, 2025, doi: 10.1007/s12161-025-02826-7.
[39] A. Maali, R. Gheshlaghi, and M. A. Mahdavi, "Maximizing key biochemical products of Spirulina platensis: Optimal light quantities and best harvesting time," OCL, vol. 31, art. no. 21, 2024, doi: 10.1051/ocl/2024019.
Copyright and Licensing
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.