Open AccessSupport Vector Machines in Smile detection: A comparison of auto-tuning standard processes in Gaussian kernel
Author(s) -
João José Costa Gondim,
Mateus Maia,
Ana Caroline Lopes Rocha,
Felipe Coelho Argôlo,
Alexander R.A. Anderson,
Alexandre Andrade Loch
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/wvc.2021.18900
Subject(s) - support vector machine , hyperparameter , computer science , kernel (algebra) , benchmark (surveying) , artificial intelligence , machine learning , gaussian process , relevance vector machine , set (abstract data type) , pattern recognition (psychology) , object detection , gaussian , image (mathematics) , contextual image classification , mathematics , physics , geodesy , combinatorics , quantum mechanics , programming language , geography
Support Vector Machines are a set of machine learning models that have great performance in several tasks as well as on image classification and object recognition. However, the proper choice of model's hyperparameters has a great influence on the outcomes and the general capacity performance. In this paper, we explore some different traditional auto-tuning processes to estimate σ hyper-parameter for SVMs Gaussian kernel. These processes are common and also implemented on standard software of data science languages. The paper considers some different situations on smile detection. The results are composed by simulation study, two benchmark image applications and a real video data application.