Enhanced InceptionV3 Transfer Learning with Augmentation Strategy  for Multi-Class Fruit Classification

Abdul Karim; Fakhri  Lambardo; Rizqi Elmuna  Hidayah

doi:10.29207/resti.v10i3.7531

Authors

Abdul Karim Universitas Labuhanbatu
Fakhri Lambardo Universitas Sjakhyakirti
Rizqi Elmuna Hidayah Universitas Islam Kalimantan Muhammad Arsyad Al-Banjari Banjarmasin

DOI:

https://doi.org/10.29207/resti.v10i3.7531

Keywords:

CNN, fruit classification, image classification, InceptionV3, transfer learning

Abstract

Fruit variety recognition using digital images is an important component in developing automated systems for agricultural handling and food-industry processing. The task is difficult because different fruit types may present nearly identical visual patterns, while image acquisition factors such as illumination, viewing position, and image quality can reduce classification reliability. To address this issue, this study designed a deep learning model for 131 fruit classes by adapting InceptionV3 through a transfer learning scheme. The pre-trained feature extraction layers were retained without retraining, while the original output structure was replaced with task-specific layers consisting of global average pooling, a 1024-unit dense layer with ReLU activation, and a softmax classifier. The image data were standardized to 224 × 224 pixels, augmented to increase visual variation, and divided into training, validation, and testing subsets using an 80:10:10 ratio. The proposed model produced an accuracy of 99.80%, with precision, recall, and F1-score values of 0.9900. These results exceeded the performance of GoogLeNet, ResNet, and VGGNet, showing that the use of pre-trained InceptionV3 features, customized classification layers, and augmentation can improve prediction consistency and reduce classification errors. Further evaluation on unconstrained real-world images and optimization for real-time use are recommended for future development.

Downloads

Download data is not yet available.

References

R. A. Saputra and K. M. Lhaksmana, “Prediction Retweet Using User-Based and Content-Based with Artificial Neural Network-Harmony Search,” vol. 5, no. 2, pp. 407–413, 2023, doi: 10.47065/bits.v5i2.4079.

Z. Khan, “Modeling and simulation of Maxwell nanofluid flows in the presence of Lorentz and Darcy–Forchheimer forces: toward a new approach on Buongiorno’s model using artificial neural network (ANN),” European Physical Journal Plus, vol. 138, no. 1, 2023, doi: 10.1140/epjp/s13360-022-03583-w.

A. P. Windarto, T. Herawan, and P. Alkhairi, “Prediction of Kidney Disease Progression Using K-Means Algorithm Approach on Histopathology Data,” in Artificial Intelligence, Data Science and Applications, Cham: Springer Nature Switzerland, 2024, pp. 492–497. doi: https://doi.org/10.1007/978-3-031-48465-0_66.

M. V Appalanaidu, “Rice plant nutrient deficiency classification using modified MOBILENET convolutional neural network,” International Journal of Modeling, Simulation, and Scientific Computing, vol. 14, no. 1, 2023, doi: 10.1142/S1793962322430036.

I. Shafi, “Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet,” Measurement: Journal of the International Measurement Confederation, vol. 202, 2022, doi: 10.1016/j.measurement.2022.111836.

S. Hossain, “Comparison of YOLO (V3,V5) and MobileNet-SSD (V1,V2) for Person Identification Using Ear-Biometrics,” International Journal of Computing and Digital Systems, vol. 15, no. 1, pp. 1259–1271, 2024, doi: 10.12785/ijcds/150189.

K. Lavanya, “Real Time Digital Face Mask Detection using MobileNet-V2 and SSD with Apache Spark,” International Journal of Performability Engineering, vol. 18, no. 8, pp. 598–604, 2022, doi: 10.23940/ijpe.22.08.p8.598604.

S. Defit, A. P. Windarto, and P. Alkhairi, “Comparative Analysis of Classification Methods in Sentiment Analysis: The Impact of Feature Selection and Ensemble Techniques Optimization,” Telematika, vol. 17, no. 1, pp. 52–67, 2024, doi: http://dx.doi.org/10.35671/telematika.v17i1.2824.

P. Alkhairi and A. P. Windarto, “Classification Analysis of Back propagation-Optimized CNN Performance in Image Processing,” Journal of Systems Engineering and Information Technology (JOSEIT), vol. 2, no. 1, pp. 8–15, 2023, doi: https://doi.org/10.29207/joseit.v2i1.5015.

A. E. K. Gunawan, “Stock Price Movement Classification Using Ensembled Model of Long Short-Term Memory (LSTM) and Random Forest (RF),” International Journal on Informatics Visualization, vol. 7, no. 4, pp. 2255–2262, 2023, doi: 10.30630/joiv.7.4.1640.

E. Rahimi, “The Efficiency of Long Short-Term Memory (LSTM) in Phenology-Based Crop Classification,” Korean Journal of Remote Sensing, vol. 40, no. 1, pp. 57–69, 2024, doi: 10.7780/kjrs.2024.40.1.6.

I. Ranggadara, U. M. Buana, A. Ratnasari, and U. M. Buana, “Backpropagation Neural Network for Predict Sugarcane Stock Availability,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 9, no. 5, pp. 8279–8284, 2020, doi: 10.30534/ijatcse/2020/197952020.

W. Chen, “Identification Rice Varieties and Broken Rice Based on GoogLeNet,” Journal of the Chinese Cereals and Oils Association, vol. 38, no. 2, pp. 146–152, 2023, doi: 10.1016/j.lwt.2024.117175.

B. Gunawan, M. E. Al-rivan, P. S. Informatika, U. Multi, and D. Palembang, “2ND Mdp Student Conference (MSC) 2023 E-Issn: 2985-7406 Klasifikasi Jenis Beras Putih Menggunakan CNN Residual Network Optimizer SGD,” pp. 128–132, 2023, doi: https://jurnal.mdp.ac.id/index.php/msc/article/view/4305

V. Choudhary, P. Guha, G. Pau, R. K. Dhanaraj, and S. Mishra, “Automatic Classification of Cowpea Leaves Using Deep Convolutional Neural Network,” Smart Agricultural Technology, p. 100209, 2023, doi: 10.1016/j.atech.2023.100209.

Windarto, A.P., Herawan, T., Alkhairi, P. (2024). Early Detection of Breast Cancer Based on Patient Symptom Data Using Naive Bayes Algorithm on Genomic Data. In: Farhaoui, Y., Hussain, A., Saba, T., Taherdoost, H., Verma, A. (eds) Artificial Intelligence, Data Science and Applications. ICAISE 2023. Lecture Notes in Networks and Systems, vol 837. Springer, Cham. https://doi.org/10.1007/978-3-031-48465-0_64.

P. Alkhairi, A. P. Windarto, and M. M. Efendi, “Optimasi LSTM Mengurangi Overfitting untuk Klasifikasi Teks Menggunakan Kumpulan Data Ulasan Film Kaggle IMDB,” vol. 6, no. 2, pp. 1142–1150, 2024, doi: 10.47065/bits.v6i2.5850.

W. Al-Khater, “Using 3D-VGG-16 and 3D-Resnet-18 deep learning models and FABEMD techniques in the detection of malware,” Alexandria Engineering Journal, vol. 89, pp. 39–52, 2024, doi: https://doi.org/10.1016/j.aej.2023.12.061.

T. A. T. K. Azaharan, “Investigation of VGG-16, ResNet-50 and AlexNet Performance for Brain Tumor Detection,” International journal of online and biomedical engineering, vol. 19, no. 8, pp. 97–109, 2023, doi: https://doi.org/10.3991/ijoe.v19i08.38619.

T. Tang, “Integration of VGGNet-Driven Precipitation Similarity Analysis and Hydrological Modeling for Enhanced Streamflow Forecasting,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 14543–14555, 2024, doi: 10.1109/JSTARS.2024.3441550.

J. Shedbalkar, “Deep transfer learning model for brain tumor segmentation and classification using UNet and chopped VGGNet,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 33, no. 3, pp. 1405–1415, 2024, doi: 10.11591/ijeecs.v33.i3.pp1405-1415.

A. Sharma, “Multilevel detection and classification of diseased plant leaf images using high-resolution superlet transform and E-ResNet,” International Journal of Information Technology (Singapore), vol. 16, no. 5, pp. 3135–3147, 2024, doi: 10.1007/s41870-024-01822-0.

H. Sahli, “ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification,” Journal of X-Ray Science and Technology, vol. 31, no. 1, pp. 27–48, 2023, doi: https://doi.org/10.3233/XST-221240.

S. Shivadekar, “Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 using a Deep CNN and ResNet 50,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 1, pp. 241–250, 2023, doi: 10.1016/j.bspc.2022.103977.

S. Wang, “Multi-sensor fusion rolling bearing intelligent fault diagnosis based on VMD and ultra-lightweight GoogLeNet in industrial environments,” Digital Signal Processing: A Review Journal, vol. 145, 2024, doi: 10.1016/j.dsp.2023.104306.

P. Samundeeswari, “An Efficient Fully Automated Lung Cancer Classification Model Using GoogLeNet Classifier,” Journal of Circuits, Systems and Computers, vol. 32, no. 14, 2023, doi: 10.1142/S0218126623502468.

F. B. N. Barber, “Human exons and introns classification using pre-trained Resnet-50 and GoogleNet models and 13-layers CNN model,” Journal of Genetic Engineering and Biotechnology, vol. 22, no. 1, 2024, doi: 10.1016/j.jgeb.2024.100359.

W. Luo, “Identification of the Reflected Signal in the COSMIC-2 Occultation Signal Using the Improved GoogLeNet Deep Learning Model,” Chinese Journal of Atmospheric Sciences, vol. 47, no. 3, pp. 631–641, 2023, doi: 10.3878/j.issn.1006-9895.2202.21096.

F. Edderbali, “Mobilenet, inception ResNet and GoogleNet for epilepsy detection using spectrogram images,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 34, no. 2, pp. 870–877, 2024, doi: 10.11591/ijeecs.v34.i2.pp870-877.

X. Huang, “Improved Model Based on GoogLeNet and Residual Neural Network ResNet,” International Journal of Cognitive Informatics and Natural Intelligence, vol. 16, no. 1, 2022, doi: 10.4018/IJCINI.313442.

X. Lin, “Application of Data Mining Technology with Improved Clustering Algorithm in Library Personalized Book Recommendation System,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 11, pp. 494–504, 2023, doi: 10.14569/IJACSA.2023.0141151.

H. J. Kweon, “Influence of Summer Pruning Time on Shoot Growth and Fruit Quality of ‘Fuji’/M.9 Apple Tree Damaged by the Low Air Temperature at Flowering Period,” Korean Journal of Environmental Agriculture, vol. 41, no. 4, pp. 328–334, 2022, doi: https://doi.org/10.5338/KJEA.2022.41.4.38.

H. Wang, “GAN-STD: small target detection based on generative adversarial network,” Journal of Real-Time Image Processing, vol. 21, no. 3, 2024, doi: 10.1007/s11554-024-01446-4.

H. C. Chang, “Classification of the implant-ridge relationship utilizing the MobileNet architecture,” Journal of Dental Sciences, vol. 19, no. 1, pp. 411–418, 2024, doi: 10.1016/j.jds.2023.08.002.

E. M. Senan, F. W. Alsaade, M. I. A. Al-Mashhadani, T. H. H. Aldhyani, and M. H. Al-Adhaileh, “Classification of histopathological images for early detection of breast cancer using deep learning,” Journal of Applied Science and Engineering (Taiwan), vol. 24, no. 3, pp. 323–329, 2021, doi: 10.6180/jase.202106_24(3).0007.

A. Choudhury, “PSSO: Political Squirrel Search Optimizer-Driven Deep Learning for Severity Level Detection and Classification of Lung Cancer,” International Journal of Information Technology and Decision Making, 2023, doi: 10.1142/S0219622023500189.

P. Yadlapalli, “Intelligent classification of lung malignancies using deep learning techniques,” International Journal of Intelligent Computing and Cybernetics, vol. 15, no. 3, pp. 345–362, 2022, doi: 10.1108/IJICC-07-2021-0147.

M. A. Lubis, D. G. S. Saragih, I. D. Anastasia, A. P. Windarto, and P. Alkhairi, “Application of the ANN Algorithm to Predict Access to Drinkable Water in North Sumatra Regency/City,” International Journal of Informatics and Data Science, vol. 1, no. 1, pp. 18–25, 2023, doi: https://doi.org/10.64366/ijids.v1i1.16.

M. Mingzhu, “The value of MobileNet in classification of bedside chest radiograph,” Chinese Journal of Radiology (China), vol. 57, no. 12, pp. 1325–1330, 2023, doi: https://www.mdpi.com/2076-3417/11/6/2751

R. Chen, “Rapid Detection of Multi-QR Codes Based on Multistage Stepwise Discrimination and a Compressed MobileNet,” IEEE Internet of Things Journal, vol. 10, no. 18, pp. 15966–15979, 2023, doi: 10.1109/JIOT.2023.3268636.

O. Bouazizi, “Road Object Detection using SSD-MobileNet Algorithm: Case Study for Real-Time ADAS Applications,” Journal of Robotics and Control (JRC), vol. 5, no. 2, pp. 551–560, 2024, doi: 10.18196/jrc.v5i2.21145.

A. Zhang, “2DDSRU-MobileNet: an end-to-end cloud-noiserobust lightweight convolution neural network,” Journal of Applied Remote Sensing, vol. 18, no. 2, p. 24511, 2024, doi: 10.1117/1.JRS.18.024511.

F. Valeri, “UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images,” Journal of Medical Imaging, vol. 10, 2023, doi: 10.1117/1.JMI.10.S1.S11904.

C. Mai, “MobileNet-Based IoT Malware Detection with Opcode Features,” Journal of Communications and Information Networks, vol. 8, no. 3, pp. 221–230, 2023, doi: 10.23919/JCIN.2023.10272350.

B. Ruhani, “Hydrogen production via renewable-based energy system: Thermoeconomic assessment and Long Short-Term Memory (LSTM) optimization approach,” International Journal of Hydrogen Energy, vol. 52, pp. 505–519, 2024, doi: 10.1016/j.ijhydene.2023.03.456.

S. Liu, “New onset delirium prediction using machine learning and long short-Term memory (LSTM) in electronic health record,” Journal of the American Medical Informatics Association, vol. 30, no. 1, pp. 120–131, 2023, doi: 10.1093/jamia/ocac210.