INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Classification of diseases in Banana Leaves using Diagonal Path Value Pattern
Authors Name:
Dr.Gladrene Sheena Basil
, Dr.N. Ani Brown Mary , Dr. P. Persis Glory
Unique Id:
IJSDR2210012
Published In:
Volume 7 Issue 10, October-2022
Abstract:
The classification of diseases in Banana leaves is emerging as the latest research area using machine learning and deep learning techniques in agricultural image processing. A lot of banana plants are wiped out, due to diseases such as Banana Bunchy Top Virus (BBTV), Banana Bacterial Wilt (BBW) and Banana Black Sigatoka (BBS). But there is not much research work done in identifying these diseases. In the proposed method, texture features are extracted using the proposed Diagonal Path Value Pattern (DPVP). The proposed texture feature descriptors provide codes taking into account of elements in diagonal directions.Then, Pulse Coupled Convolution Neural Network (PCCNN) is utilized for classifying banana leaf diseases. The experimental results with standard datasets prove that the proposed method performs better than the existing techniques. Classification results are validated by agriculture biologists.
Keywords:
Banana, classification, Pulse Coupled Convolution, Diagonal Path Value Pattern
Cite Article:
"Classification of diseases in Banana Leaves using Diagonal Path Value Pattern", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.7, Issue 10, page no.67 - 71, October-2022, Available :http://www.ijsdr.org/papers/IJSDR2210012.pdf
Downloads:
000337073
Publication Details:
Published Paper ID: IJSDR2210012
Registration ID:201971
Published In: Volume 7 Issue 10, October-2022
DOI (Digital Object Identifier):
Page No: 67 - 71
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn