Characterising colour feature descriptors for Ficus carica L. ripeness classification based on Artificial Neural Network (ANN)

Iylia Adhwa Mazni and Samsul Setumin and Mohamed Syazwan Osman and Muhammad Khusairi Osman and Mohd Subri Tahir (2023) Characterising colour feature descriptors for Ficus carica L. ripeness classification based on Artificial Neural Network (ANN). Pertanika Journal of Science & Technology (Malaysia), 31 (2). pp. 759-780. ISSN 2231-8526

Excessive feature dimensions impact the effectiveness of machine learning, computationally expensive and the analysis of feature correlations in the engineering area. This paper uses the colour descriptor to get the most optimal feature to improve time consumption and efficiency. This study investigated Ficus carica L. (figs) with three classification stages. The ripening classification of fig was examined using colour features descriptor with two different colour models, RGB and HSV. In addition, the machine learning classification model based on Artificial Neural Network (ANN) that utilised the Feed-Forward Neural Network (FFNN) model to classify the ripeness of fig is considered in this characterisation. Five different numbers of binning were characterised for RGB and HSV. Both colour feature descriptors were compared in terms of accuracy, sensitivity, precision, and time consumption to identify the dimension of the optimal feature. Based on the result, reducing the size of images will improve the time consumption with comparable accuracy. Moreover, the reduction of features dimension cannot be too small or too big due to inequitable enough to differentiate the ripeness stages and lead to a false error state. The optimal features dimension in binning for RGB was 8 (R/G/B) bins with 96.7% accuracy. Meanwhile, 96.7% accuracy for HSV at 15, 5, and 5 (H, S, V) bins as optimal colour features.

Full text available from: Official URL: http://www.pertanika.upm.edu.my/resources/files/Pe...

Abstract

Excessive feature dimensions impact the effectiveness of machine learning, computationally expensive and the analysis of feature correlations in the engineering area. This paper uses the colour descriptor to get the most optimal feature to improve time consumption and efficiency. This study investigated Ficus carica L. (figs) with three classification stages. The ripening classification of fig was examined using colour features descriptor with two different colour models, RGB and HSV. In addition, the machine learning classification model based on Artificial Neural Network (ANN) that utilised the Feed-Forward Neural Network (FFNN) model to classify the ripeness of fig is considered in this characterisation. Five different numbers of binning were characterised for RGB and HSV. Both colour feature descriptors were compared in terms of accuracy, sensitivity, precision, and time consumption to identify the dimension of the optimal feature. Based on the result, reducing the size of images will improve the time consumption with comparable accuracy. Moreover, the reduction of features dimension cannot be too small or too big due to inequitable enough to differentiate the ripeness stages and lead to a false error state. The optimal features dimension in binning for RGB was 8 (R/G/B) bins with 96.7% accuracy. Meanwhile, 96.7% accuracy for HSV at 15, 5, and 5 (H, S, V) bins as optimal colour features.

[error in script]

Item Type:	Article
AGROVOC Term:	figs
AGROVOC Term:	maturity
AGROVOC Term:	ripening
AGROVOC Term:	neural networks
AGROVOC Term:	artificial intelligence
AGROVOC Term:	fruit colour
AGROVOC Term:	classification
AGROVOC Term:	systems research
AGROVOC Term:	efficiency
Geographical Term:	Malaysia
Uncontrolled Keywords:	ANN, colour descriptor, colour features, FFNN, fig, histogram, HSV, RGB, ripening
Depositing User:	Ms. Azariah Hashim
Date Deposited:	27 Jan 2025 01:41
Last Modified:	27 Jan 2025 02:29
URI:	http://webagris.upm.edu.my/id/eprint/1891

Actions (login required)

View Item