A. Othman

A. Othman

Pictograms (also called symbols) are widely used in daily life as a type of visual language, such as transportation venue signs (airport, rail station, etc.), road signs, care symbols on clothing, or direction symbols (Tijus et al., 2007). This shows how symbols can communicate information quickly and effectively. Fundamentally, symbols can be understood, regardless of the person's language or literacy skills. Therefore, people with communication difficulties may benefit from using symbols to comprehend what other people are saying, as well as to express themselves. There are many sets of pictograms available online or in the market as printed cards, some of them are free and some must be purchased. Pictogram sets can be considered in several ways including how pictorial, how guessable, how flexible, how consistent, and how visually complex. Each symbol set has strengths and weaknesses, and the choice of a symbol set should be based on the needs and abilities of the person using AAC.

A. Othman, H. R. Tizhoosh, F. Khalvati

Every segmentation algorithm has parameters that need to be adjusted in order to achieve good results. Evolving fuzzy systems for adjustment of segmentation parameters have been proposed recently (Evolving fuzzy image segmentation -- EFIS [1]. However, similar to any other algorithm, EFIS too suffers from a few limitations when used in practice. As a major drawback, EFIS depends on detection of the object of interest for feature calculation, a task that is highly application-dependent. In this paper, a new version of EFIS is proposed to overcome these limitations. The new EFIS, called self-configuring EFIS (SC-EFIS), uses available training data to auto-configure the parameters that are fixed in EFIS. As well, the proposed SC-EFIS relies on a feature selection process that does not require the detection of a region of interest (ROI).