A Novel Densely Search based Fire-Fly (DSFF) Optimization Algorithm for Image Classification Application

Data processing and analytics are wide spread study with profound applications. Data analytics deals with deriving or applying an algorithm to an application that work with dataset. The proposed work analyses the image data with optimization algorithm by using novel method of Fire-Fly (FF) algorithm, which is named as Densely Search Fire-Fly (DSFF) optimization algorithm. The Neural Network (NN) is applied to classify the optimized data. In this process, the optimized data refers to selective attributes from the raw data of image features. To test the performance of proposed optimization, the Gabor feature extraction method is used to fetch the features from raw image data. The Gabor method retrieves the pattern in various angle of projections. This produces 5 × 8 number of patterns to represent the image feature. From this feature attributes of whole image dataset, the optimization search for the best attributes by the reference of weight value is calculated from the particles of Fire-Fly. According to the best selection of attributes from the objective function, the neurons in a network that can segregate the different classes in the training dataset. The performance of the proposed FF algorithm are compared with the traditional optimization methods in the image classification application.