View article

The recent development of digital camera and growth of data storage has led to a huge amount of image databases. Only a few were proposed for specified databases such as satellite images, leaf sets, maps, faces, fingers and so on. There are a lot of content-based retrieval systems which are mostly applied to general image databases (CBIR) and there are very few for plant databases. The use of plants is plenty such as foodstuff, medicine and industry. This has led to the thought of identifying the different diseases of a leaves of a plant available around us which might be useful to the common man. Inspired in the active field of CBIR, we propose a new methodology for automatic identification of diseased leaves based on Wavelets and PCA. The data set considered in this paper is diseased Tomato leaves.