Human-computer interaction (HCI) is used to create software products which are interactive, easy like child's play and enjoyable to use for the end users. HCI is multidisciplinary, integrates value systems of users from various backgrounds and experiences. Hence HCI is challenging for designers to create applications which are user friendly and at affordable price. This becomes more challenging in situations where communication in a local language or dialect through cell-phone or tablet is

more »

... pted and this situation is very much vogue in a country like India where variety of ways communication is done. With texts and images added, this lands itself to dealing with unstructured and heterogeneous HCI. In such a situation a need arises to deliver content irrespective of language or text of communication and this is more essential in the context of safety. A methodology is proposed to initiate action based on content estimation of any form of communication, text or language and the approach is based on operating generic pixel-maps as stored for any data, so that issues of language, text-script and format do not pose problems. With the pixel-maps, as bases, different methods are used to convert into a numerical form for suitable neural modeling and content is extracted with ease so that approach is universal. Statistical features of the pixel-maps are extracted from the pixel map matrix of the image and through effective classification content is assessed to initiate action.