Kernel Regression based Sparse Metric Learning for Extensive Classification of Visual Art Images

In recent decades, the collection of visual art paintings is in a large number which are digitized and available for public uses that are rapidly growing. The development of multi-media systems is very much needed due to the huge amount of digitized artwork collections for retrieving and archiving this large-scale data. This multimedia system is getting benefit from high-level tasks and has an essential step for measuringsimilarity of visual between the artistic items. For modeling the similarities between the artworks or paintings, it is essential to extract useful features of visual paintings and propose a best approach for learning this similarity metrics. In this paper, the detailed visual features are listed and similarity measurement between the paintings is optimized by the Sparse Metric Learning based Kernel Regression (KR-SML) and classification model is developed using hybrid SVM-ANN for semantic-level understanding for prediction of painting's genre, artist, and style. Furthermore, the Human-Computer Interaction (HCI) based formulation model is built to analyse the proposed technique. The simulations results are showing that the proposed model proves to be better in terms of performance when compared with other existing techniques.