Deep learning fusion algorithm for arts categorization
Mohamed Masoud, Saeid O. Belkasim, Iman Chahine · 2017
The intent of the image classification process is to objectively categorize an image visual contents into semantic meanings. The classification process is a challenging task due to the difficulty associated with extracting and identifying relevant shape information. In this paper, we introduce a new fusion algorithm that combines the strengths of deep learning and mid-level image descriptors. Our approach is evaluated using a newly constructed dataset of artifacts' images organized into seven categories of 100 images each. The algorithm shows an improvement in the classification accuracy over other state of the art methods.