Improving the Estimation of Font Face Attributes According to User Preferences

Every day in our life we can discover a lot of optimization problems. By exploring them more deeply we can reveal their fundamentals and think about their solution. The problem of the most attractive font face for the writer is such a problem. The optimization function of this problem is unknown. Beside other methods also interactive evolutionary computation could be used to solve such type of optimization problems. If we utilize interactive evolutionary computation to find solution we encounter the user fatigue problem. To eliminate this disadvantage we need to accelerate the convergence of the evolutionary computation part. In this article we propose an algorithm that tries to find a candidate solution to the most attractive font face based on input data. We assume that user likes his handwriting properties which is a subject of research for graphology. These handwriting properties will project into properties or attributes of the font face. The algorithm tries to connect Schwartz’s culture model with observations and theoretical knowledge from graphology. It maps the computer font attributes to Schwartz’s culture model using the revealed knowledge from graphology about handwriting. We modified our existing algorithm proposal and we included a learning phase of fuzzy membership function to match a case when user preferences are different from the theory found in graphology. The algorithm is a theoretical proposal to the user fatigue problem in interactive evolutionary computation.