Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Computing, Performance and Communication Systems
  4. Vol 9, Issue 1, 2025

Simplified Research on Daily Item Image Classification Based on MobileNet

Download as PDF

DOI: 10.23977/cpcs.2025.090112 | Downloads: 2 | Views: 75

Author(s)

Hongru Li 1, Zhitao Wu 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, China

Corresponding Author

Zhitao Wu

ABSTRACT

With the popularization of mobile devices, the demand for mobile-end image classification has been growing increasingly. Traditional deep learning models are difficult to operate efficiently on mobile devices due to their large number of parameters and complex computations. This study takes daily items as the research objects and adopts MobileNet, a lightweight convolutional neural network, to achieve fast classification suitable for mobile devices by simplifying the network structure and applying transfer learning. Experiments were conducted to compare the accuracy difference between transfer learning and training from scratch, and to analyze the impact of different learning rates and batch sizes on model performance. The results show that the MobileNet model based on transfer learning not only ensures the classification accuracy but also significantly reduces the computational cost. It has high practicality in entry-level daily item classification tasks and provides a simplified and feasible solution for mobile-end image classification applications.

KEYWORDS

MobileNet; Image Classification; Transfer Learning; Mobile End; Daily Items

CITE THIS PAPER

Hongru Li, Zhitao Wu, Simplified Research on Daily Item Image Classification Based on MobileNet. Computing, Performance and Communication Systems (2025) Vol. 9: 88-95. DOI: http://dx.doi.org/10.23977/cpcs.2025.090112.

REFERENCES

[1] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.
[2] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
[3] Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314-1324.
[4] Wang W, Li Y, Zou T, et al. A novel image classification approach via dense‐MobileNet models[J]. Mobile Information Systems, 2020, 2020(1): 7602384.
[5] Shahriar T. Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices[J]. arXiv preprint arXiv:2505.03303, 2025.
[6] El Khayati M, Maafiri A, Himeur Y, et al. Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition[J]. IEEE Access, 2025.
[7] Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.
[8] Tan M, Le Q. Efficientnetv2: Smaller models and faster training[C]//International conference on machine learning. PMLR, 2021: 10096-10106.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 3365
Visits: 212234

Sponsors, Associates, and Links

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

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.