Comparative analysis of convolutional neural networks and bilinear interpolation for mobile applications

Aleks Mosisa; Hanna Vlasiuk

Journal: Volume 31, No. 2, 2026

Pages: 27 – 34

DOI: https://doi.org/10.62660/bcstu/2.2026.27

270 Views

Comparative analysis of convolutional neural networks and bilinear interpolation for mobile applications

Aleks Mosisa, Hanna Vlasiuk

Received 08.12.2025

Revised 10.04.2026

Accepted 18.05.2026

Published 26.06.2026

Abstract

The relevance of the study is conditioned by the growing need for efficient image processing algorithms for mobile devices with limited computing resources. The purpose of the study was to comprehensively compare the efficiency of convolutional neural networks and bilinear interpolation to predict the parameters of geometric transformations in mobile applications. The study was conducted on a Motorola G32 mobile device using the dual-input architecture of convolutional neural networks. A total of 120 experiments were conducted using images measuring 224×224 pixels, which included rotation angles ranging from -45° to +45° and scaling factors ranging from 0.5 to 1.5. The CNN model was optimised using TensorFlow Lite with 8-bit quantisation. The PSNR and SSIM metrics were used to evaluate image quality. The statistical analysis included: the Shapiro-Wilk test for normality verification, the Student’s t-test, and the Mann-Whitney U-test for group comparison, the Cohen coefficient for estimating effect size, ANOVA analysis of variance, Pearson and Spearman correlation analysis, and regression analysis. The thermal regime and energy consumption of the device were monitored at the significance level p < 0.05. Convolutional neural networks showed statistically significantly better image quality: the median PSNR value was 45.56 dB compared to 42.42 dB for bilinear interpolation, SSIM 0.953 and 0.910, respectively. Furthermore, bilinear interpolation provided perfect accuracy for predicting geometric parameters (median angle error 0.0°), in contrast to convolutional neural networks (median error 47.95°). The processing time for convolutional neural networks was 447.0 ms versus 358.9 ms for bilinear interpolation of battery consumption: 18.3 ± 4.2 mAh (CNN) versus 16.7 ± 3.9 mAh (bilinear), p > 0.05. The processor temperature increased by 3.2°C (CNN) versus 1.9°C (bilinear). Practical significance. The developed methods can be used in mobile augmented reality applications for optimal selection of algorithms depending on the application requirements

Keywords

deep learning; image processing; mobile computing; transformation parameters; performance metrics; neural architecture

References

Archana, R., & Jeevaraj, P.S.E. (2024). Deep learning models for digital image processing: A review. Artificial Intelligence Review, 57(1), article number 11. doi: 10.1007/s10462-023-10631-z .
Choudhary, T., Mishra, V., Goswami, A., & Sarangapani, J. (2020). A comprehensive survey on model compression and acceleration. Artificial Intelligence Review, 53(7), 5113-5155. doi: 10.1007/s10462-020-09816-7 .
Gou, J., Yu, B., Maybank, S.J., & Tao, D. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6), 1789-1819. doi: 10.1007/s11263-021-01453-z.
Han, S., Pool, J., Tran, J., & Dally, W.J. (2015). Learning both weights and connections for efficient neural network . In Advances in neural information processing systems 28 (NeurIPS 2015) (pp. 1135-1143). Montreal: Neural Information Processing Systems Foundation.
He, Y., & Xiao, L. (2024). Structured pruning for deep convolutional neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 2900-2919. doi: 10.1109/TPAMI.2023.3334614 .
Howard, A., et al. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF international conference on computer vision (ICCV) (pp. 1314-1324). Seoul: IEEE.
Ignatov, A., et al. (2023). Efficient and accurate quantized image super-resolution on mobile NPUs, mobile AI & AIM 2022 challenge: Report. In L. Karlinsky, T. Michaeli & K. Nishino (Eds.), Computer vision – ECCV 2022 workshops (pp. 92-129). Cham: Springer. doi: 10.1007/978-3-031-25066-8_5.
Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015). Spatial transformer networks . In Advances in neural information processing systems 28 (NeurIPS 2015) (pp. 2017-2025). Montreal: Neural Information Processing Systems Foundation.
Li, Z., Li, H., & Meng, L. (2023). Model compression for deep neural networks: A survey. Computers, 12(3), article number 60. doi: 10.3390/computers12030060.
Liu, H., Galindo, M., Xie, H., Wong, L.K., Shuai, H.H., Li, Y.H., & Cheng, W.H. (2024). Lightweight deep learning for resource-constrained environments: A survey. ACM Computing Surveys, 56(10), article number 267. doi: 10.1145/3657282 .
Mehta, S., & Rastegari, M. (2022). MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. In International conference on learning representations (ICLR 2022) (pp. 1-26). Vancouver: ICLR.
Menghani, G. (2023). Efficient deep learning: A survey on making deep learning models smaller, faster, and better. ACM Computing Surveys, 55(12). doi: 10.1145/3578938.
Reddi, V.J., et al. (2022). MLPerf mobile inference benchmark: An industry-standard open-source machine learning benchmark for on-device AI. In Proceedings of the Machine Learning and Systems Conference (MLSys 2022) (pp. 352-364). Baltimore: PMLR.
Rokh, B., Azarpeyvand, A., & Khanteymoori, A. (2023). A comprehensive survey on model quantization for deep neural networks in image classification. ACM Transactions on Intelligent Systems and Technology, 14(6), article number 97. doi: 10.1145/3623402.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4510-4520). Salt Lake City: IEEE. doi: 10.1109/CVPR.2018.00474.
Tan, M., & Le, Q.V. (2021). EfficientNetV2: Smaller models and faster training . In Proceedings of the 38th international conference on machine learning (pp. 10096-10106). Baltimore: PMLR.
Wang, Z., Bovik, A.C., Sheikh, H.R., & Simoncelli, E.P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612. doi: 10.1109/TIP.2003.819861.
Wei, L., Ma, Z., Yang, C., & Yao, Q. (2024). Advances in the neural network quantization: A comprehensive review. Applied Sciences, 14(17), 744. doi: 10.3390/app14177445.
Xiao, Z., Zhang, Z., Hung, K.-W., & Lui, S. (2021). Real-time video super-resolution using lightweight depthwise separable group convolutions with channel shuffling. Journal of Visual Communication and Image Representation, 75, article number 103038. doi: 10.1016/j.jvcir.2021.103038.
Yang, J., Lyu, M., Qi, Z., & Shi, Y. (2023). Deep learning based image quality assessment: A survey. Procedia Computer Science, 221, 1000-1007. doi: 10.1016/j.procs.2023.08.080 .

Suggested citation

Mosisa, A., & Vlasiuk, H. (2026). Comparative analysis of convolutional neural networks and bilinear interpolation for mobile applications. Bulletin of Cherkasy State Technological University, 31(2), 27-34. https://doi.org/10.62660/bcstu/2.2026.27

[1] Archana, R., & Jeevaraj, P.S.E. (2024). Deep learning models for digital image processing: A review. Artificial Intelligence Review, 57(1), article number 11. doi: 10.1007/s10462-023-10631-z .

[2] Choudhary, T., Mishra, V., Goswami, A., & Sarangapani, J. (2020). A comprehensive survey on model compression and acceleration. Artificial Intelligence Review, 53(7), 5113-5155. doi: 10.1007/s10462-020-09816-7 .

[3] Gou, J., Yu, B., Maybank, S.J., & Tao, D. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6), 1789-1819. doi: 10.1007/s11263-021-01453-z.

[4] Han, S., Pool, J., Tran, J., & Dally, W.J. (2015). Learning both weights and connections for efficient neural network . In Advances in neural information processing systems 28 (NeurIPS 2015) (pp. 1135-1143). Montreal: Neural Information Processing Systems Foundation.

[5] He, Y., & Xiao, L. (2024). Structured pruning for deep convolutional neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 2900-2919. doi: 10.1109/TPAMI.2023.3334614 .

[6] Howard, A., et al. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF international conference on computer vision (ICCV) (pp. 1314-1324). Seoul: IEEE.

[7] Ignatov, A., et al. (2023). Efficient and accurate quantized image super-resolution on mobile NPUs, mobile AI & AIM 2022 challenge: Report. In L. Karlinsky, T. Michaeli & K. Nishino (Eds.), Computer vision – ECCV 2022 workshops (pp. 92-129). Cham: Springer. doi: 10.1007/978-3-031-25066-8_5.

[8] Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015). Spatial transformer networks . In Advances in neural information processing systems 28 (NeurIPS 2015) (pp. 2017-2025). Montreal: Neural Information Processing Systems Foundation.

[9] Li, Z., Li, H., & Meng, L. (2023). Model compression for deep neural networks: A survey. Computers, 12(3), article number 60. doi: 10.3390/computers12030060.

[10] Liu, H., Galindo, M., Xie, H., Wong, L.K., Shuai, H.H., Li, Y.H., & Cheng, W.H. (2024). Lightweight deep learning for resource-constrained environments: A survey. ACM Computing Surveys, 56(10), article number 267. doi: 10.1145/3657282 .

[11] Mehta, S., & Rastegari, M. (2022). MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. In International conference on learning representations (ICLR 2022) (pp. 1-26). Vancouver: ICLR.

[12] Menghani, G. (2023). Efficient deep learning: A survey on making deep learning models smaller, faster, and better. ACM Computing Surveys, 55(12). doi: 10.1145/3578938.

[13] Reddi, V.J., et al. (2022). MLPerf mobile inference benchmark: An industry-standard open-source machine learning benchmark for on-device AI. In Proceedings of the Machine Learning and Systems Conference (MLSys 2022) (pp. 352-364). Baltimore: PMLR.

[14] Rokh, B., Azarpeyvand, A., & Khanteymoori, A. (2023). A comprehensive survey on model quantization for deep neural networks in image classification. ACM Transactions on Intelligent Systems and Technology, 14(6), article number 97. doi: 10.1145/3623402.

[15] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4510-4520). Salt Lake City: IEEE. doi: 10.1109/CVPR.2018.00474.

[16] Tan, M., & Le, Q.V. (2021). EfficientNetV2: Smaller models and faster training . In Proceedings of the 38th international conference on machine learning (pp. 10096-10106). Baltimore: PMLR.

[17] Wang, Z., Bovik, A.C., Sheikh, H.R., & Simoncelli, E.P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612. doi: 10.1109/TIP.2003.819861.

[18] Wei, L., Ma, Z., Yang, C., & Yao, Q. (2024). Advances in the neural network quantization: A comprehensive review. Applied Sciences, 14(17), 744. doi: 10.3390/app14177445.

[19] Xiao, Z., Zhang, Z., Hung, K.-W., & Lui, S. (2021). Real-time video super-resolution using lightweight depthwise separable group convolutions with channel shuffling. Journal of Visual Communication and Image Representation, 75, article number 103038. doi: 10.1016/j.jvcir.2021.103038.

[20] Yang, J., Lyu, M., Qi, Z., & Shi, Y. (2023). Deep learning based image quality assessment: A survey. Procedia Computer Science, 221, 1000-1007. doi: 10.1016/j.procs.2023.08.080 .