On the creation of visual models for keywords through crowdsourcing

Abstract

Crowdsourcing annotation is a recent development since a complete and elaborate annotation of the content of an image is an extremely labour-intensive and time consuming task. In this paper we examine the possibility to build accurate visual models for keywords created through crowdsourcing. Specifically, 8 different keywords related to athletics domain have been modelled using MPEG-7 and Histogram of Oriented Gradients (HOG) low level features and the Sequential Minimal Optimization (SMO) classifier. The experimental results have been examined using accuracy metrics and are very promising showing the ability of the visual models to classify the images into the 8 classes with the highest average accuracy rate of 73.13% in the purpose of the HOG features.