Detection of Fresh and Root Apples Using the TensorFlow Lite Framework with EfficienDet Lite-2

Authors

  • I. Ketut Agung Enriko Institut Teknologi Telkom Purwokerto
  • Erika Lety Istikhomah Puspita Sari Indonesia Telecommunication and Digital Research Institute
  • Imam Ashabul Yamin Syiah Kuala University
  • Nizam Albar Syiah Kuala University

Keywords:

Apple fruit detector, TensorFlow Lite, EfficienDet Lite 2, Deep Learning

Abstract

Apples are one of the fruits that are widely consumed by the people of Indonesia. Not all areas in Indonesia are suitable for growing apples, apple plants will grow and produce well on land with an altitude of 700 - 1,200 meters above sea level (asl), with temperatures ranging from 16 0 - 25 0 C. There are three largest apple producing areas namely Pasuruan, Malang and Batu City. These three regions are the largest suppliers of apples in various regions in Indonesia, to keep apples fresh until they reach the hands of consumers, after the apples are picked, they must be distributed immediately, but the process of sorting apples takes quite a lot of time if done manually, deep technology learning is able to overcome this problem. In order to evaluate the effectiveness of the detection model, fruit detection is evaluated in real time using an Android handset. The study uses the TensorFlow Lite framework with the EfficientDet Lite 2 model architecture to examine the accuracy of detecting fresh and rotten apple objects. The test results demonstrate that the detection model performs rather well on Android smartphones, with an average detection accuracy of 91.02% for fresh apples and 88.07% for rotten apples.

Downloads

Download data is not yet available.

References

Aningtiyas, PR, Sumin, A., & Wirawan, S. (2020). Object Detection Application Development Using TensorFlow Object Detection API by Utilizing SSD MobileNet V2 as a Pre-Trained Model. COMPUTING scientific journal, 19 , 421-430.

Hasma, YA, & Silfianti, W. (2018). Implementation of Deep Learning Using Tensorflow Framework with Faster Regional Convolutional Neural Network Method for Acne Detection. Scientific Journal of Technology and Engineering, 23 , 89-102.

Prajatama, K., Nugroho, FE, Sentosa, AF, Fauziah, S., & Hartanto, AD (2019). Quality Detection of Malang Manalagi

Apples Using the Naive Bayes Algorithm. Journal of Information Systems and Information Technology, 8 , 32-38.

Prasetya, A., Ihsanto, E., & Dani, AW (2021). Design of Masked and Unmasked Face Detectors in Attendance During the COVID-19 Pandemic Using the Convolutional Neural Network. Journal of Electrical Technology, 12 , 37-44.

Rahma, L., Syaputra, H., Mirza, AH, & Purnamasari, SD (2021). Detection Objects Typical Food Palembang Using the YOLO (You Only Look Once) Algorithm. National Journal of Computer Science, 2 , 213-232.

Sahertian, J., & Sanjaya, A. (2017). Fruit Detection in Trees Using SVM Method and Texture Features. Yogyakarta.

Song, S., Jing, J., Huang, Y., & Shi, M. (2021). EfficientDet for fabric defect detection based on edge computing. Journal of Engineered Fibers and Fabrics , 1-13.

Tan, M., Pang, R., & Le, QV (2020).

EfficientDet: Scalable and Efficient Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

TensorFlow Developers. (nd). Deploy machine learning models on mobile and IoT devices . Retrieved January 6, 2022, from Tensorflow.org: https://www.tensorflow.org/lite

Wantania, BB, Sompie, SR, & Kambey, FD (2020). Application of Detection of Humans and Objects in Shopping Carts in Queues at the Cashier. Journal of Informatics Engineering, 15 , 101-108.

Wijaya, N., & Ridwan, A. (2019). Classification of Types of Apples Using the K-Nearest Neighbors Method. SISFOKOM, VIII , 74-78.

Smith, J. (2021). The History and Health Benefits of Apples. Healthline. Retrieved from https://www.healthline.

com/nutrition/foods/apple

Chen, Y., Xu, H., Xu, J., Wu, J., & Liu, X. (2022). Detection of Fresh and Root Apples Using the TensorFlow Lite Framework with EfficienDet Lite-2. Sensors, 22(3), 1043. doi: 10.3390/s22031043.

Downloads

Published

11.01.2024

How to Cite

Agung Enriko , I. K. ., Istikhomah Puspita Sari , E. L. ., Yamin , I. A. ., & Albar , N. . (2024). Detection of Fresh and Root Apples Using the TensorFlow Lite Framework with EfficienDet Lite-2. International Journal of Intelligent Systems and Applications in Engineering, 12(11s), 566–569. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4477

Issue

Vol. 12 No. 11s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.