DOI : https://doi.org/10.18517/ijaseit.15.2.20637

Volume Prediction of Axisymmetric Fruits Using Optimized Convolutional Neural Networks with Transfer Learning Strategy

Vincentius Christian Wariky (1), Joko Siswantoro (2), Njoto Benarkah (3)
(1) Department of Informatics Engineering, University of Surabaya, Surabaya, Indonesia
(2) Department of Informatics Engineering, University of Surabaya, Surabaya, Indonesia
(3) Department of Informatics Engineering, University of Surabaya, Surabaya, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
V. C. Wariky, J. Siswantoro, and N. Benarkah, “Volume Prediction of Axisymmetric Fruits Using Optimized Convolutional Neural Networks with Transfer Learning Strategy”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 2, pp. 436–443, Apr. 2025.
Citation Format :
Accurate volume measurement of fruits is key in the agricultural and food industries, supporting better logistics, quality assessment, and processing decisions. However, traditional methods for measuring volume are often manual and labor-intensive, creating bottlenecks in high-scale operations. This study presents a novel approach that utilizes convolutional neural networks (CNNs) combined with a transfer learning strategy to predict the volume of axisymmetric fruit from images, offering a more automated and efficient solution. To achieve this, five pretrained CNN architectures, including MobileNetV2, VGG-16, DenseNet201, ResNet50, and EfficientNetV2B0, were employed by modifying the fully connected layers and optimized through a random search process, allowing for optimal hyperparameter selection. Only the fully connected layers were fine-tuned, while the pretrained convolutional layers retained their original weights, enabling the models to focus on relevant image features without extensive retraining. The methodology encompassed dataset creation, image preprocessing, and segmentation, with training supported by the Adam optimizer and evaluated using mean squared error and mean absolute error. The performance of CNNs was assessed through metrics like mean absolute relative error (ARE) and the coefficient of determination (R²). Experimental results demonstrate that ResNet50 achieved the highest prediction accuracy with a mean ARE of 3.76% and an R² of 0.9721, outperforming other models and several existing methods from previous research. This study’s findings highlight the potential of CNN-based models, especially ResNet50, for precise axisymmetric fruit volume estimation. Future research may extend this method to encompass diverse fruit types and real-time applications, advancing automated processing technologies in the industry.

S. M. H. Mousavi and S. M. H. Mosavi, “Automatic Infrared-Based Volume and Mass Estimation System for Agricultural Products: Along with Major Geometrical Properties,” in 2021 11th International Conference on Computer Engineering and Knowledge (ICCKE), 2021, pp. 140–149, doi:10.1109/ICCKE54056.2021.9721526.

J. Siswantoro, E. Asmawati, and M. Z. F. N. Siswantoro, “A rapid and accurate computer vision system for measuring the volume of axi-symmetric natural products based on cubic spline interpolation,” J. Food Eng., vol. 333, p. 111139, 2022, doi:10.1016/j.jfoodeng.2022.111139.

I. Nyalala et al., “Weight and volume estimation of single and occluded tomatoes using machine vision,” Int. J. Food Prop., vol. 24, no. 1, pp. 818–832, 2021, doi: 10.1080/10942912.2021.1933024.

Y. Han, S. Xu, Q. Zhang, H. Lu, X. Liang, and C. Fan, “Non-destructive detection method and experiment of pomelo volume and flesh content based on image fusion,” Postharvest Biol. Technol., vol. 213, p. 112953, 2024, doi: 10.1016/j.postharvbio.2024.112953.

I. Nyalala, C. Okinda, C. Kunjie, T. Korohou, L. Nyalala, and Q. Chao, “Weight and volume estimation of poultry and products based on computer vision systems: a review,” Poult. Sci., vol. 100, no. 5, p. 101072, 2021, doi: 10.1016/j.psj.2021.101072.

H. Fitriyah, “Accuracy of Various Methods to Estimate Volume and Weight of Symmetrical and Non-Symmetrical Fruits using Computer Vision.,” J. ICT Res. Appl., vol. 16, no. 3, 2022, doi:10.5614/itbj.ict.res.appl.2022.16.3.2.

Y. Zhu, S. Cao, T. Song, Z. Xu, and Q. Jiang, “3D reconstruction and volume measurement of irregular objects based on RGB-D camera,” Meas. Sci. Technol., vol. 35, no. 12, p. 125010, 2024, doi:10.1088/1361-6501/ad7621.

J. Xu, Y. Lu, E. Olaniyi, and L. Harvey, “Online volume measurement of sweetpotatoes by A LiDAR-based machine vision system,” J. Food Eng., vol. 361, p. 111725, 2024, doi:10.1016/j.jfoodeng.2023.111725.

S. Luo, J. Tang, J. Peng, and H. Yin, “A novel approach for measuring the volume of Pleurotus eryngii based on depth camera and improved circular disk method,” Sci. Hortic. (Amsterdam)., vol. 336, p. 113382, 2024, doi: 10.1016/j.scienta.2024.113382.

Y. S. Gan, L. Wei, Y. Han, C. Zhang, Y.-C. Huang, and S.-T. Liong, “A statistical approach in enhancing the volume prediction of ellipsoidal ham,” J. Food Eng., vol. 290, p. 110186, 2021, doi:10.1016/j.jfoodeng.2020.110186.

Y. A. Sari and A. Gofuku, “Measuring food volume from RGB-Depth image with point cloud conversion method using geometrical approach and robust ellipsoid fitting algorithm,” J. Food Eng., vol. 358, p. 111656, 2023, doi: 10.1016/j.jfoodeng.2023.111656.

J. Li, M. Wu, and H. Li, “3D reconstruction and volume estimation of jujube using consumer-grade RGB-depth sensor,” IEEE Access, vol. 11, pp. 61502–61512, 2023, doi:10.1109/access.2023.3285713.

M. T. Nair, “Definite Integral BT - Calculus of One Variable,” M. T. Nair, Ed. Cham: Springer International Publishing, 2021, pp. 173–249, doi: .10.1007/978-3-030-88637-0

H. M. Tran, K. T. Pham, T. M. Vo, T.-H. Le, T. T. M. Huynh, and S. V. T. Dao, “A new approach for estimation of physical properties of irregular shape fruit,” IEEE Access, vol. 11, pp. 46550–46560, 2023, doi: 10.1109/access.2023.3273777.

T. Mon and N. ZarAung, “Vision based volume estimation method for automatic mango grading system,” Biosyst. Eng., vol. 198, pp. 338–349, 2020, doi: 10.1016/j.biosystemseng.2020.08.021.

T. Huynh, L. Tran, and S. Dao, “Real-Time Size and Mass Estimation of Slender Axi-Symmetric Fruit/Vegetable Using a Single Top View Image,” Sensors, vol. 20, no. 18, p. 5406, Sep. 2020, doi:10.3390/s20185406.

M. Soltani, M. Omid, and R. Alimardani, “Egg volume prediction using machine vision technique based on pappus theorem and artificial neural network,” J. Food Sci. Technol., vol. 52, no. 5, pp. 3065–3071, 2015, doi: 10.1007/s13197-014-1350-6.

S. Jana, R. Parekh, and B. Sarkar, “A De novo approach for automatic volume and mass estimation of fruits and vegetables,” Optik (Stuttg)., vol. 200, p. 163443, Jan. 2020, doi:10.1016/j.ijleo.2019.163443.

F. Rahman et al., “Prediction of Potato Volume by Neural Network Regression Model,” J. Agric. Mach. Bioresour. Eng., vol. 8, no. 2, pp. 40–52, 2024, doi: 10.61361/jambe.v8i2.124.

S. M. Mansuri, P. V. Gautam, D. Jain, and C. Nickhil, “Computer vision model for estimating the mass and volume of freshly harvested Thai apple ber (Ziziphus mauritiana L.) and its variation with storage days,” Sci. Hortic. (Amsterdam)., vol. 305, p. 111436, 2022, doi:10.1016/j.scienta.2022.111436.

A. Saikumar, C. Nickhil, and L. S. Badwaik, “Physicochemical characterization of elephant apple (Dillenia indica L.) fruit and its mass and volume modeling using computer vision,” Sci. Hortic. (Amsterdam)., vol. 314, p. 111947, 2023, doi:10.1016/j.scienta.2023.111947.

Z. Xie, J. Wang, Y. Yang, P. Mao, J. Guo, and M. Sun, “Image processing based modeling for Rosa roxburghii fruits mass and volume estimation,” Sci. Rep., vol. 14, no. 1, p. 15507, 2024, doi:10.1038/s41598-024-65321-9.

R. Dalai, N. Dalai, and K. K. Senapati, “An accurate volume estimation on single view object images by deep learning based depth map analysis and 3D reconstruction,” Multimed. Tools Appl., vol. 82, no. 18, pp. 28235–28258, 2023, doi: 10.1007/s11042-023-14615-7.

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.

S. Ajala, H. Muraleedharan Jalajamony, M. Nair, P. Marimuthu, and R. E. Fernandez, “Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force,” Sci. Rep., vol. 12, no. 1, pp. 1–17, 2022, doi: 10.1038/s41598-022-16114-5.

T. Lu, B. Han, L. Chen, F. Yu, and C. Xue, “A generic intelligent tomato classification system for practical applications using DenseNet-201 with transfer learning,” Sci. Rep., vol. 11, no. 1, p. 15824, 2021, doi: 10.1038/s41598-021-95218-w.

E. A. Tsvetkov and R. A. Krymov, “Pure random search with virtual extension of feasible region,” J. Optim. Theory Appl., vol. 195, no. 2, pp. 575–595, 2022, doi: 10.1007/s10957-022-02097-w.

W. Burger and M. J. Burge, Digital Image Processing An Algorithmic Introduction. Cham, Switzerland: Springer Nature Switzerland AG, 2022.

Y. Gulzar, “Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique,” Sustainability, vol. 15, no. 3. 2023, doi: 10.3390/su15031906.

X. Li, Z. Liu, T. Zhai, and X. Yang, “Fruit Classification Identification Research Based on VGG16 Network,” in 2024 IEEE 2nd International Conference on Image Processing and Computer Applications (ICIPCA), 2024, pp. 387–391, doi:10.1109/icipca61593.2024.10709233.

M. S. Morshed, S. Ahmed, T. Ahmed, M. U. Islam, and A. B. M. A. Rahman, “Fruit Quality Assessment with Densely Connected Convolutional Neural Network,” in 2022 12th International Conference on Electrical and Computer Engineering (ICECE), 2022, pp. 1–4, doi: 10.1109/icece57408.2022.10088873.

A. Doshi, P. Khatri, V. Dodiya, S. Muni, and M. Narvekar, “PikFresh - Fruit Quality Detection using ResNet50,” in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2023, pp. 1–5, doi:10.1109/icccnt56998.2023.10308324.

G. Singh, K. Guleria, and S. Sharma, “A Pre-trained EfficientNetV2B0 Model for the Accurate classification of Fake and Real Images,” in 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2024, pp. 1082–1086, doi:10.1109/iceca63461.2024.10801011.

H. Salem, A. E. Kabeel, E. M. S. El-Said, and O. M. Elzeki, “Predictive modelling for solar power-driven hybrid desalination system using artificial neural network regression with Adam optimization,” Desalination, vol. 522, p. 115411, 2022, doi:10.1016/j.desal.2021.115411.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. 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.
    3. 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).