Measuring Icon Recognization Mapping with Automated Decision Making System

Abstract

Nowadays, mobile technology has been rapidly improved in both hardware and software aspects. Thus, many applications have been built and install in a smartphone. To find an application in the smartphone, a user has to search through various icons that design based on functions of the application. The purpose of this research is to build an automatic system that helps software designers to decide if the designed-icon is a proper icon that could be recognized by the user easily or not using entropy, Canny edge detection, and decision tree. Two experiments are reported in this research. 100 icons in both Android and iPhone operation system were used in both experiments. The sample included undergraduate students and workers in Thailand ($\mathbf{n}=90$) ages ranged from 18 to 57. The first experiment was made in order to find a relationship among edge, entropy and human visual processing and use it as a training and testing dataset for the proposed system. The second experiment shows that the proposed system can be used to judge for a proper icon property with 73.33% accuracy rate.