Multi-Device Image Dataset With Manual And Python-Based Augmentations For Cross-Device Robustness In Image Classification Research
Article Metrics
Abstract view : 71 timesAbstract
This study presents a multi-device image collection and a reproducible VSCode/Python pipeline for analyzing image classification and the effects of data augmentation under real hardware variation. Images were captured at the Galeri Inovasi Institut Teknologi Sepuluh Nopember (GRITS) using four devices Infinix Note 4, LG G6, Samsung S23+, and Xiaomi Pad 6s Pro with 31 images per device. We applied manual and Python-based augmentations (rotation, flips, brightness, sharpening, contrast) and organized outputs by device and augmentation type for controlled comparisons. Using stratified 80:20 splits, we evaluated Logistic Regression (LR), SVM (RBF), and KNN. Results: LR reached accuracy 0.90 (macro-F1 0.88; weighted-F1 0.90), SVM 0.89 (macro-F1 0.88; weighted-F1 0.89), and KNN 0.67 (macro-F1 0.65; weighted-F1 0.68). Augmentation enhanced robustness and cross-device generalization, though Xiaomi Pad 6s Pro remained the most challenging class, indicating a persistent device-specific shift. The dataset and scripts provide a transparent, baseline-ready testbed for research on image classification, cross-device variability, and the impact of augmentation.
References
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy. BMC Genomics, 21, 6. DOI: 10.1186/s12864 019 6413 7
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2020). Randaugment: Practical Automated Data Augmentation With A Reduced Search Space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)., 3008–3017,DOI: 10.1109/CVPRW50498.2020.00359
Fang, Y., Li, X., Liu, J., Wang, X., & Zhang, Y. (2024). Source-free unsupervised domain adaptation: A survey. Neural Networks, 172, 106176. https://doi.org/10.1016/j.neunet.2024.10617
Howard, A. G., Sandler, M., Chen, B., Wang, W., & Chen, L. C. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 1314–1324, DOI: 10.1109/ICCV.2019.00140
Kalbasi, M., & Nikmehr, H. (2020). Noise-robust, reconfigurable Canny edge detection and its hardware realization. IEEE Access, 8, 39934–39945. DOI: 10.1109/ACCESS.2020.2976860
Kou, F., Li, Z. G., Wen, C., & Chen, W. (2018). Edge‑preserving smoothing pyramid based multi‑scale exposure fusion. Journal of Visual Communication and Image Representation, 53, 235–244. https://doi.org/10.1016/j.jvcir.2018.03.020
Nguyen, T. T., Nguyen, H. T., & Kim, H. (2021). Cross-device domain adaptation for robust image classification. IEEE Transactions on Image Processing, 30, 7683–7696.
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60.
Tharwat, A. (2020). Classification assessment methods. Applied Computing and Informatics, 17(1), 168–192. https://doi.org/10.1016/j.aci.2018.08.003
Wang, M., & Deng, W. (2018). Deep visual domain adaptation: A survey. Neurocomputing, 312, 135–153. DOI: 10.1016/j.neucom.2018.05.083
Wang, R., Wei, S., & Chen, Z. (2019). Adaptive unsharp masking for contrast enhancement. Multimedia Tools and Applications, 78, 21935–21958.
Wang, C., Chen, X., Chen, B., Nie, F., Wang, B., & Ming, Z (2021). Impact of resampling operators on image classification robustness. Information Sciences, 579, 700–716. https://doi.org/10.1016/j.ins.2021.07.087
Xiang, H., Zhang, L., & Wang, Z. (2021). Multi-scale image fusion with Gaussian/Laplacian pyramids: A review. Information Fusion, 72, 28–47. (Please confirm exact details from the journal.)
Xu, M., Yoon, S., Fuentes, A., & Park, D. S. (2023). A Comprehensive Survey Of Image Augmentation Techniques For Deep Learning. Pattern Recognition, 137, 109347. https://doi.org/10.1016/j.patcog.2023.109347
Zhou, S., Li, J., & Wang, Y. (2023). Random Interpolation Resize: A free image data augmentation. Expert Systems with Applications, 214, 120355. https://doi.org/10.1016/j.eswa.2023.120355
Copyright (c) 2025 Erika Putri, Imam Yuadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
