TY - JOUR
T1 - Revealing GLCM Metric Variations across a Plant Disease Dataset
T2 - A Comprehensive Examination and Future Prospects for Enhanced Deep Learning Applications
AU - Kabir, Masud
AU - Unal, Fatih
AU - Akinci, Tahir Cetin
AU - Martinez-Morales, Alfredo A.
AU - Ekici, Sami
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/6
Y1 - 2024/6
N2 - This study highlights the intricate relationship between Gray-Level Co-occurrence Matrix (GLCM) metrics and machine learning model performance in the context of plant disease identification. It emphasizes the importance of rigorous dataset evaluation and selection protocols to ensure reliable and generalizable classification outcomes. Through a comprehensive examination of publicly available plant disease datasets, focusing on their performance as measured by GLCM metrics, this research identified dataset_2 (D2), a database of leaf images, as the top performer across all GLCM analyses. These datasets were then utilized to train the DarkNet19 deep learning model, with D2 exhibiting superior performance in both GLCM analysis and DarkNet19 training (achieving about 91% testing accuracy) according to performance metrics such as accuracy, precision, recall, and F1-score. The datasets other than dataset_1 and 2 exhibited significantly low classification performance, particularly in supporting GLCM analysis. The findings underscore the need for transparency and rigor in dataset selection, particularly given the abundance of similar datasets in the literature and the growing trend of utilizing deep learning methods in future scientific research.
AB - This study highlights the intricate relationship between Gray-Level Co-occurrence Matrix (GLCM) metrics and machine learning model performance in the context of plant disease identification. It emphasizes the importance of rigorous dataset evaluation and selection protocols to ensure reliable and generalizable classification outcomes. Through a comprehensive examination of publicly available plant disease datasets, focusing on their performance as measured by GLCM metrics, this research identified dataset_2 (D2), a database of leaf images, as the top performer across all GLCM analyses. These datasets were then utilized to train the DarkNet19 deep learning model, with D2 exhibiting superior performance in both GLCM analysis and DarkNet19 training (achieving about 91% testing accuracy) according to performance metrics such as accuracy, precision, recall, and F1-score. The datasets other than dataset_1 and 2 exhibited significantly low classification performance, particularly in supporting GLCM analysis. The findings underscore the need for transparency and rigor in dataset selection, particularly given the abundance of similar datasets in the literature and the growing trend of utilizing deep learning methods in future scientific research.
KW - DarkNet19
KW - GLCM metrics
KW - deep learning
KW - open datasets
KW - plant diseases
UR - http://www.scopus.com/inward/record.url?scp=85197268776&partnerID=8YFLogxK
U2 - 10.3390/electronics13122299
DO - 10.3390/electronics13122299
M3 - Article
AN - SCOPUS:85197268776
SN - 2079-9292
VL - 13
JO - Electronics (Switzerland)
JF - Electronics (Switzerland)
IS - 12
M1 - 2299
ER -