HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRA-TD500, show that the proposed method achieves state-ofthe-art in scene text detection.

PurposeTo examine community integration and contributing factors in people with aphasia (PWA) following stroke and to investigate the relationship between community integration and quality of life (QOL).Materials and MethodsThirty PWA and 42 age-and education-matched control subjects were involved. Main variables were as follows: socioeconomic status, mobility, and activity of daily living (ADL) (Modified Barthel Index), language function [Frenchay Aphasia Screening Test (FAST)], depression [Geriatric Depression Scale (GDS)], Community Integration Questionnaire (CIQ) and Stroke and Aphasia Quality of Life Scale-39 (SAQOL-39). Differences between aphasia and control groups and factors affecting community integration and QOL were analyzed.ResultsHome and social integration and productive activity were significantly decreased in the aphasia group compared to the control group; 8.5 and 18.3 points in total CIQ score, respectively. Amount of time spent outside the home and frequency of social contact were also significantly reduced in the aphasia group. Total mean score on the SAQOL-39 was 2.75±0.80 points and was significantly correlated with economic status, gait performance, ADL, depressive mood, and social domain score on the CIQ. Depression score measured by GDS was the single most important factor for the prediction of QOL, but the FAST score was significantly correlated only with the communication domain of the SAQOL-39.ConclusionCommunity activities of PWA were very limited, and depression was highly associated with decreased community integration and QOL. Enhancing social participation and reducing emotional distress should be emphasized for rehabilitation of PWA.

No abstract

No abstract