Evaluating the Role of PCA Dimensionality Reduction in Enhancing CNN-Based Butterfly Image Classification
DOI:
https://doi.org/10.57152/ijatis.v3i2.3095Keywords:
Butterfly Image Classification, Convolutional Neural Network, Dimensionality Reduction, PCAAbstract
Butterfly species classification from digital images is a challenging computer vision task due to high intra-class variability across 75 species. Although Convolutional Neural Networks (CNN) have demonstrated strong performance in biological image classification, high-dimensional image data raises concerns about computational cost and the risk of overfitting. The main novelty of this study is a rigorous empirical evaluation of Principal Component Analysis (PCA) as a dimensionality-reduction preprocessing step in a CNN-based butterfly classification pipeline, a combination that has not been explicitly investigated in this domain. Three comparative experimental scenarios were designed: Scenario A used VGG16 transfer learning without PCA as a baseline; Scenario B applied PCA retaining 95% explained variance before a Multilayer Perceptron (MLP) classifier; and Scenario C applied PCA retaining 99% explained variance with the same MLP architecture. The performance evaluation covered accuracy, precision, recall, F1 Score, training time, inference time, and model size. Results show that Scenario A achieved the highest accuracy of 62.05% (F1-score: 0.6158), while Scenarios B and C reached 35.90% and 36.62% respectively, with training time reduced by up to 98.5% compared to the baseline. These findings reveal a clear accuracy-efficiency trade-off: PCA substantially reduces computational cost but at the expense of classification accuracy when applied as preprocessing before MLP rather than within CNN layers. This study offers practical empirical evidence to guide practitioners in selecting between accuracy-optimized and efficiency-optimized strategies when computational resources are constrained
References
H. Anwar, “Butterflies and benchmarks: a systematic evaluation of deep learning backbones to identify the best model for image-based butterflies species recognition,” Pattern Anal. Appl., vol. 29, no. 1, p. 13, Mar. 2026, doi: 10.1007/s10044-025-01587-7.
F. Rajeena P. P. et al., “A Novel Method for the Classification of Butterfly Species Using Pre-Trained CNN Models,” Electronics, vol. 11, no. 13, p. 2016, Jun. 2022, doi: 10.3390/electronics11132016.
R. F. Mattins, M. V. R. Sarobin, A. A. Aziz, and S. Srivarshan, “Object detection and classification of butterflies using efficient CNN and pre-trained deep convolutional neural networks,” Multimed. Tools Appl., vol. 83, no. 16, pp. 48457–48482, Nov. 2023, doi: 10.1007/s11042-023-17563-4.
M. Teke and G. Elsamoly, “Innovative deep learning solutions for Turkish butterfly species identification: a VGGNet enhancement study,” Signal, Image Video Process., vol. 19, no. 5, p. 396, May 2025, doi: 10.1007/s11760-025-03979-y.
N. T. Sarshar, S. Sadeghi, M. Kamsari, M. Avazpour, S. J. Ghoushchi, and R. Ranjbarzadeh, “Advancing Brain MRI Image Classification: Integrating VGG16 and ResNet50 with a Multi-Verse Optimization Method,” BioMed, vol. 4, no. 4, pp. 499–523, Nov. 2024, doi: 10.3390/biomed4040038.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,” Sustainability, vol. 15, no. 7, p. 5930, Mar. 2023, doi: 10.3390/su15075930.
D. Satria Yudha Kartika and H. Maulana, “Preprosesing dan normalisasi pada dataset kupu-kupu untuk ekstraksi fitur warna, bentuk dan tekstur,” J. Comput. Electron. Telecommun., vol. 1, no. 2, Jan. 2021, doi: 10.52435/complete.v1i2.76.
Nadiyah Hidayati and M. Maulidah, “Ekstraksi Fitur Dengan Color Histogram Dan Classifier Random Forest Pada Citra Kupu-Kupu,” JAMI J. Ahli Muda Indones., vol. 4, no. 2, pp. 148–157, Dec. 2023, doi: 10.46510/jami.v4i2.172.
H. Liu, W. Bi, and N. Mughees, “Enhanced Hyperspectral Image Classification Technique Using PCA-2D-CNN Algorithm and Null Spectrum Hyperpixel Features,” Sensors, vol. 25, no. 18, Sep. 2025, doi: 10.3390/s25185790.
R. Madinakhon, D. Mukhtorov, and Y.-I. Cho, “Integrating Principal Component Analysis and Multi-Input Convolutional Neural Networks for Advanced Skin Lesion Cancer Classification,” Appl. Sci., vol. 14, no. 12, p. 5233, Jun. 2024, doi: 10.3390/app14125233.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
U. Buatoom and M. U. Jamil, “Improving Classification Performance with Statistically Weighted Dimensions and Dimensionality Reduction,” Appl. Sci., vol. 13, no. 3, p. 2005, Feb. 2023, doi: 10.3390/app13032005.
B. Zhao, X. Dong, Y. Guo, X. Jia, and Y. Huang, “PCA Dimensionality Reduction Method for Image Classification,” Neural Process. Lett., vol. 54, no. 1, pp. 347–368, Feb. 2022, doi: 10.1007/s11063-021-10632-5.
I. Garg, P. Panda, and K. Roy, “A Low Effort Approach to Structured CNN Design Using PCA,” IEEE Access, vol. 8, pp. 1347–1360, 2020, doi: 10.1109/ACCESS.2019.2961960.
R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, “A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction,” J. Appl. Sci. Technol. Trends, vol. 1, no. 1, pp. 56–70, May 2020, doi: 10.38094/jastt1224.
C. Xu et al., “Fine-Grained Butterfly Recognition via Peer Learning Network with Distribution-Aware Penalty Mechanism,” Animals, vol. 12, no. 20, p. 2884, Oct. 2022, doi: 10.3390/ani12202884.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474.
Y. Liu and L. J. Durlofsky, “3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels,” Jul. 2020, doi: 10.1016/j.cageo.2020.104676.
A. A. Wani, “Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions,” PeerJ Comput. Sci., vol. 11, p. e3025, Jul. 2025, doi: 10.7717/peerj-cs.3025.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2016, pp. 2818–2826. doi: 10.1109/CVPR.2016.308.
N. Chothani, I. Desai, C. K. chan, S. Singh, D. Varshney, and N. Naik, “PCA and CNN-based detection and classification of faults in distribution network with distributed energy resources,” Appl. Eng. Sci., vol. 25, p. 100300, Mar. 2026, doi: 10.1016/j.apples.2026.100300.
A. Mardiansyah, E. C. Djamal, and F. Nugraha, “Multivariate EEG Signal Using PCA and CNN in Post-Stroke Classification,” in 2020 FORTEI-International Conference on Electrical Engineering (FORTEI-ICEE), IEEE, Sep. 2020, pp. 113–118. doi: 10.1109/FORTEI-ICEE50915.2020.9249880.
O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, Dec. 2015, doi: 10.1007/s11263-015-0816-y.
D. Coelho, A. Madureira, I. Pereira, and R. Gonçalves, “A Review on Dimensionality Reduction for Machine Learning,” 2023, pp. 287–296. doi: 10.1007/978-3-031-27499-2_27.
L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, p. 53, Mar. 2021, doi: 10.1186/s40537-021-00444-8.
D. Anggreani, “Peningkatan Metode YOLOv7 Dengan Proses Augmentasi Image Pada Klasifikasi Jenis Kupu-Kupu YOLOv7 Method Improvement With Image Augmentation Process In Classification of Butterfly species,” 2023.
R. Li, H. Liu, and Y. Hu, “Financial performance evaluation and forecasting of enterprises by the combination of PCA and CNN deep learning,” Dec. 01, 2023, Higher Education Press Limited Company. doi: 10.1007/s11704-023-2494-1.
A. Maftukhah, A. Fadlil, and S. Sunardi, “Butterfly Image Classification using Convolution Neural Network with AlexNet Architecture,” J. INFOTEL, vol. 16, no. 1, Feb. 2024, doi: 10.20895/infotel.v16i1.1004.
E. Hartati, K. Kunci, and K. Kupu, MDP Student Conference (MSC) 2022 Klasifikasi Spesies Kupu Kupu Menggunakan Metode Convolutional Neural Network.
