Image Processing and Classification Method Appropriate for Extensible Mobile Applications

Abstract

The image processing technique described in this paper can be used for the classification of photographs that display an object of interest. Spots on the object having distinct color surrounded by a potential halo are segmented. The gray level, area and the number of the spots can determine the class of the object displayed in the photograph. The color histograms of the regions of interest are expected to have similar form in different photographs belonging to the same class. Instead of employing complicated pattern matching algorithms simple features are used including the position and the peaks of the lobes. Plant or skin disease diagnosis are indicative applications that can benefit from the proposed method. High speed classification is achieved with good accuracy in the cases where the proposed methods have been employed. However, their main advantage is the simplicity that allows extensibility since new classes can be supported after a draft statistical processing of a small number of photographs. © 2019 IEEE.