Implementing Deep Learning Vision for Crystal Guava Quality Grading

DOI

10.2991/978-94-6463-854-7_6How to use a DOI?

Keywords

Automatic Fruit Grading; Image Processing; Deep Learning Vision

Abstract

This study explores the application of a deep learning-based approach using the YOLO architecture for automated quality grading of crystal guava. Traditional manual inspection methods, while widely used, suffer from limitations such as subjectivity, inconsistency, and slower processing times. The proposed deep learning model addresses these issues by achieving high accuracy (89%) and consistency (90%) in classifying guava into high, medium, and low-quality categories. Despite these advantages, the study finds that manual inspection still outperforms the deep learning model in terms of speed, highlighting the need for further optimization of the model’s processing capabilities. The results indicate that the deep learning model is particularly well-suited for environments where precision and standardization are critical, although it may require enhancements to compete with manual methods in high-speed processing scenarios. This research underscores the potential of deep learning to revolutionize quality assessment in agriculture, offering a scalable and reliable alternative to manual inspection, with future work focusing on improving inference speed and exploring hybrid approaches for optimal performance.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Raden Arief Setyawan
AU  - Muhammad Aziz Muslim
AU  - Zainul Abidin
AU  - Chong Yung Wey
AU  - Rizal Setya Perdana
PY  - 2025
DA  - 2025/11/11
TI  - Implementing Deep Learning Vision for Crystal Guava Quality Grading
BT  - Proceedings of the 2024 Brawijaya International Conference (BIC 2024)
PB  - Atlantis Press
SP  - 59
EP  - 70
SN  - 3091-4442
UR  - https://doi.org/10.2991/978-94-6463-854-7_6
DO  - 10.2991/978-94-6463-854-7_6
ID  - Setyawan2025
ER  -