An image-processing diagnostic program for identifying common rice diseases in the Philippines

Date of Publication

2012

Document Type

Master's Thesis

Degree Name

Master of Science in Manufacturing Engineering

College

Gokongwei College of Engineering

Department/Unit

Manufacturing Engineering and Management

Thesis Adviser

Edwin J. Calilung

Defense Panel Chair

Nilo T. Bugtai

Defense Panel Member

Lord Kenneth Pinpin
Arthur Pius Santiago

Abstract/Summary

In the past decades various epidemics have crippled the supply of rice in the Philippines. Various methods have been created to detect crop diseases early to aid in its prevention by use of software. This study deals with the detection of four common rice diseases in the Philippines. Images of diseased rice plants are obtained from the IRRI. The .jpg files are modified by various techniques in image processing using various image software but mostly MATLAB, following this basic procedure: pre-processing, quantization, pixel classifying, and classification via decision table and matrices. The Naive-Bayes classifier is used to train and test the images according to their Lab pixel values and classify them by disease. The testing and training images are organized into datasets containing images of diseased leaves from different sources to note the effects of difference of sources in the overall analysis.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTG005292

Shelf Location

Archives, The Learning Commons, 12F Henry Sy Sr. Hall

Physical Description

1 computer optical disc ; 4 3/4 in.

Upload Full Text

wf_no

This document is currently not available here.

Share

COinS