Participatory design for selection of icons to represent daily activities of living for a vision-based rehabilitation-cum-assistance system for locked-in patients.

Purpose: The majority of rehabilitation systems for locked-in patients are used for therapeutic purposes. However, round-the-clock assistance and support are essential after discharge from hospitals or nursing homes. This inspired us to develop a round-the-clock rehabilitation-cum-assistance system operated by eye gazes of locked-in patients. To do this, we aimed to identify the essential daily activities of living for locked-in patients and represent these activities using the most universally acceptable icons/images on the interface for the rehabilitation-cum-assistance system.Method: Activities were selected from available conventions and literature with advice from a local physiotherapy centre. Simple arithmetic averages and weighted averages of recognition rates for different icons representing different daily activities were calculated as per ISO 3864. Universal acceptability of the icons was compared based on responses from 72 locked-in patients across five different age groups. The final icons or images were then selected.Results: Three icons were categorized as identifiable with overall average recognition rates above 66.7%. Icons with average recognition rates 30-60% were considered to have "medium" recognisability and 21 icons were in this category. The average recognition rates of six icons were below 30% and were not acceptable. An overall recognition efficiency of 91% was achieved for participants from all age groups.Conclusions: The most preferred and unambiguous icons or images representing the essential daily activities of living were identified for use on the interface of our rehabilitation-cum-assistance system for round-the-clock operation.Implications for rehabilitationPerforming some of the daily activities by locked-in patients himself/herself is essential for self-independence as well as measures the level of regular improvement.Assistive technologies have huge potential for application for the purpose, especially the vision-based systems.Present technology is useful for development of a vision-based rehabilitation-cum-assistance system for 24 × 7 assistance for the locked-in patients.A new approach for real-time, user-based field evaluation of icons representing daily activities of living using statistical method of averaging of the recognition rates.

Guiding attention of faces through graph based visual saliency (GBVS).

In a general scenario, while attending a scene containing multiple faces or looking towards a group photograph, our attention does not go equal towards all the faces. It means, we are naturally biased towards some faces. This biasness happens due to availability of dominant perceptual features in those faces. In visual saliency terminology it can be called as 'salient face'. Human's focus their gaze towards a face which carries the 'dominating look' in the crowd. This happens due to comparative saliency of the faces. Saliency of a face is determined by its feature dissimilarity with the surrounding faces. In this context there is a big role of human psychology and its cognitive science too. Therefore, enormous researches have been carried out towards modeling the computer vision system like human's vision. This paper proposed a graphical based bottom up approach to point up the salient face in the crowd or in an image having multiple faces. In this novel method, visual saliencies of faces have been calculated based on the intensity values, facial areas and their relative spatial distances. Experiment has been conducted on gray scale images. In order to verify this experiment, three level of validation has been done. In the first level, our results have been verified with the prepared ground truth. In the second level, intensity scores of proposed saliency maps have been cross verified with the saliency score. In the third level, saliency map is validated with some standard parameters. The results are found to be interesting and in some aspects saliency predictions are like human vision system. The evaluation made with the proposed approach shows moderately boost up results and hence, this idea can be useful in the future modeling of intelligent vision (robot vision) system.