Identification of Soursop Leaves Image Based On RGB Color Features Extraction and Gabor Filter Using Backpropagation Artificial Neural Networks

DOI

10.2991/978-94-6463-480-8_17How to use a DOI?

Keywords

Backpropagation; Neural Network; Gabor Filter; RGB Filter

Abstract

Soursop leaves have a myriad of uses, including boosting the immune system, helping fight cancer cells. The leaf, which has the scientific name Annona Muricata, has become the target of residents who choose alternative paths in natural medicine. Soursop leaves grow abundantly across Indonesia, from lowlands up to 1,000 meters above sea level. Generally, identifying the type of leaf is done visually. Moreover, the shape and colour are very similar to avocado leaves. Therefore, a study was conducted to identify soursop leaves based on RGB color feature extraction. The method chosen in this study was backpropagation neural network as one of the best algorithms that perform well in image identification. In this study, two backpropagation neural network models were utilized to compare the performance between the training and testing systems. The results obtained the best combination of parameter settings which were 6 for the input layers and 5 for the output layer. And the best combination for the Gabor filter was 45º for orientation angle and 8 for wavelength. Thus, this study was able to achieve an average accuracy of 90%. For future works, we recommend using other feature extraction techniques, such as geometry, KK-Nearest Neighbour, histogram, and PCA to then be compared with Gabor filter extraction.

Copyright

© 2024 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  - Laily Muntasiroh
AU  - Hendriansyah
AU  - Fitriyani
PY  - 2024
DA  - 2024/07/29
TI  - Identification of Soursop Leaves Image Based On RGB Color Features Extraction and Gabor Filter Using Backpropagation Artificial Neural Networks
BT  - Proceedings of the 2nd Lawang Sewu Internasional Symposium on Engineering and Applied Sciences (LEWIS-EAS 2023)
PB  - Atlantis Press
SP  - 210
EP  - 220
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-480-8_17
DO  - 10.2991/978-94-6463-480-8_17
ID  - Muntasiroh2024
ER  -