International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 45 |
Published: October 2024 |
Authors: G.G. Rajput, Vanita Bhimappa Doddamani |
![]() |
G.G. Rajput, Vanita Bhimappa Doddamani . Pigeon pea Leaf Disease Classification Using BoVW and DSIFT. International Journal of Computer Applications. 186, 45 (October 2024), 44-49. DOI=10.5120/ijca2024924096
@article{ 10.5120/ijca2024924096, author = { G.G. Rajput,Vanita Bhimappa Doddamani }, title = { Pigeon pea Leaf Disease Classification Using BoVW and DSIFT }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 45 }, pages = { 44-49 }, doi = { 10.5120/ijca2024924096 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A G.G. Rajput %A Vanita Bhimappa Doddamani %T Pigeon pea Leaf Disease Classification Using BoVW and DSIFT%T %J International Journal of Computer Applications %V 186 %N 45 %P 44-49 %R 10.5120/ijca2024924096 %I Foundation of Computer Science (FCS), NY, USA
Plant diseases are continually emerging on leaves, posing a significant threat to agricultural productivity and food security in many parts of the world. Early detection and precise diagnosis of these plant diseases are essential to mitigate financial losses and environmental damage caused by misdiagnosis. In this paper, presented a feature-based approach for detecting pigeonpea leaf diseases from images. The pigeonpea (Cajanus cajan (L.) Millsp.), a member of the Fabaceae family, is a crucial legume shrub found in the semi-arid tropics and subtropics of Asia and Africa. Dense Scale-Invariant Feature Transforms (DSIFT) and Bag of Visual Words (BoVW) features are employed for feature extraction. Classification methods namely, SVM, KNN, RF, DT, XGBoost and Light GBM and CNN are used for disease classification with different combinations of DSIFT and BoVW features. Light GBM and CNN have yielded better accuracy compared to other classifiers.