Multimodal Visual Features on Rhizome Image Classification using Support Vector Machines

Hamdani, Sania Kamelia, Fahmi, Hisyam ORCID: https://orcid.org/0000-0002-2665-1536, Khudzaifah, Muhammad ORCID: https://orcid.org/0000-0001-8500-1843, Kusumastuti, Ari ORCID: https://orcid.org/0000-0003-3883-4310, Jauhari, Mohammad Nafie ORCID: https://orcid.org/0000-0002-0909-1821 and Sari, Wina Permana ORCID: https://orcid.org/0000-0003-3289-2640 (2024) Multimodal Visual Features on Rhizome Image Classification using Support Vector Machines. Presented at 2024 12th International Conference on Information and Communication Technology (ICoICT), 7 - 8 August 2024, Bandung.

Preview

Text ICoICT_1571036301.pdf Download (2MB) | Preview

Abstract

This paper explores the use of multimodal visual features, including color, texture, and shape, for the classification of rhizome images using Support Vector Machines (SVM). Rhizomes, such as turmeric and curcuma, exhibit distinct visual characteristics that can be leveraged for identification. The study highlights the advantages of SVM in handling complex classification tasks, even with limited training data, making it a suitable approach for rhizome image recognition. The integration of color, texture, and shape features provides a comprehensive understanding of the visual data, leading to enhanced classification accuracy and robustness. The proposed methodology outlines the steps involved in extracting and combining these visual features and employing SVM for effective rhizome image recognition. The findings of this research contribute to advancements in agricultural practices and botanical studies by enabling accurate identification of different rhizome plant species using color, texture, and shape features with an accuracy score of 83%.

Item Type:	Conference (Paper)
Keywords:	multimodal visual features; rhizome images; SVM; classification; segmentation
Subjects:	01 MATHEMATICAL SCIENCES > 0103 Numerical and Computational mathematics > 010303 Optimisation 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Divisions:	Faculty of Mathematics and Sciences > Department of Mathematics
Depositing User:	Hisyam Fahmi
Date Deposited:	11 Dec 2025 14:47

Downloads

Origin of downloads

Actions (login required)

View Item