TY  - JOUR
AU  - Zafar, Mehwish
AU  - Khan, Fadia Ali
PY  - 2026
DA  - 2026/06/01
TI  - Maize Leaf Disease Classification Using a Hybrid Framework Integrated with Color and CNN-Derived Features
JO  - ICCK Journal of Image Analysis and Processing
T2  - ICCK Journal of Image Analysis and Processing
JF  - ICCK Journal of Image Analysis and Processing
VL  - 2
IS  - 3
SP  - 141
EP  - 152
DO  - 10.62762/JIAP.2026.176232
UR  - https://www.icck.org/article/abs/JIAP.2026.176232
KW  - maize leaf
KW  - disease classification
KW  - plant disease
KW  - deep learning
KW  - color features
KW  - features fusion
AB  - Early recognition of maize leaf disorders and applying precautionary measures on time may help to increase the yield and quality. This study introduces an architecture for the recognition and categorization of maize leaf diseases based on the deep Inception-v3 and maximum value-based color features. The core steps of the designed framework include data acquisition, feature extraction, fusion, and classification. The maize leaf image dataset is utilized, which is publicly available on Kaggle, comprising four classes. The deep learning features are collected by applying the transfer learning approach to the pre-trained Inception-v3 model. In addition to the deep features, maximum value-based color features are computed from RGB, HSV, and LAB color spaces. After that, both deep and color attributes are merged using a serial-based strategy. Finally, the fused vector is fed to the various machine learning classifiers for the recognition of disorders. The designed approach achieves an accuracy of 99% on the Ensemble Subspace Discriminant (ESD) classifier. The results showed that the proposed approach achieved promising disease recognition performance.
SN  - 3068-6679
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Zafar2026Maize,
  author = {Mehwish Zafar and Fadia Ali Khan},
  title = {Maize Leaf Disease Classification Using a Hybrid Framework Integrated with Color and CNN-Derived Features},
  journal = {ICCK Journal of Image Analysis and Processing},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {141-152},
  doi = {10.62762/JIAP.2026.176232},
  url = {https://www.icck.org/article/abs/JIAP.2026.176232},
  abstract = {Early recognition of maize leaf disorders and applying precautionary measures on time may help to increase the yield and quality. This study introduces an architecture for the recognition and categorization of maize leaf diseases based on the deep Inception-v3 and maximum value-based color features. The core steps of the designed framework include data acquisition, feature extraction, fusion, and classification. The maize leaf image dataset is utilized, which is publicly available on Kaggle, comprising four classes. The deep learning features are collected by applying the transfer learning approach to the pre-trained Inception-v3 model. In addition to the deep features, maximum value-based color features are computed from RGB, HSV, and LAB color spaces. After that, both deep and color attributes are merged using a serial-based strategy. Finally, the fused vector is fed to the various machine learning classifiers for the recognition of disorders. The designed approach achieves an accuracy of 99\% on the Ensemble Subspace Discriminant (ESD) classifier. The results showed that the proposed approach achieved promising disease recognition performance.},
  keywords = {maize leaf, disease classification, plant disease, deep learning, color features, features fusion},
  issn = {3068-6679},
  publisher = {Institute of Central Computation and Knowledge}
}