Thesis (Ph.D.) - Cairo University - Institute of Statistical Studies and Research - Department of Computer and Information Science

During the recent past, plant diseases have become serious threats to national income for many countries. These diseases can result in plant decline, plant death, yield loss and loss of marketability. Likewise, the farmers are concerned about huge costs from pro{uFB01}t loss, crops loss, and chemicals used in an attempt to control the disease. An automated detection system may help in plant diseases prevention and, thus reduce the serious loss to the agricultural based industry. This thesis addresses the problem of automatic detection and identi{uFB01}cation of diseases in digital images of tomato leaves. New approaches for automatic detection and identi{uFB01}cation of tomato plant diseases were introduced in this thesis. This approach consists of these major sub-systems, namely, image acquisition, image processing and pattern recogni- tion. The image acquisition system consists of digital camera and lighting system. The image processing sub-system combines the advantages of intelligent techniques such as k-means algorithm as a clustering technique, gray-level Co-occurrence matrix (GLCM) and wavelet transformation as features extraction techniques, as long as moth {uFB02}am optimization as a new technique for features selection. Pattern recognition sub-system was used to classify samples among several different types of diseases. Ef{uFB01}cient result obtained from the proposed approach can lead to tighter connection between agriculture specialists and computer system, yielding more effective and reliable results

Issued also as CD