The quota system in Brazil made it possible to include blind studentsin higher education. Teachers’ lack of knowledge about the braillesystem can represent a barrier between them and students who useit for writing and reading. Computer-vision-based transcriptionsolutions represent mechanisms for reducing understanding restrictionson this system. However, such tools face nuisances inherentto image processing systems, e.g., illumination, noise, and scale,harming the result. This paper presents an automated approachto mitigate transcription errors in braille texts for the Portugueselanguage. We propose a selection function, combined with dictionaries,that provides the best correspondence of words based ontheir braille representation. We validated our proposal on a datasetof synthetic images by submitting them to different noise levelsand testing the proposal’s robustness. Experimental results confirmthe effectiveness of the solution compared to a standard approach.As a contribution of this paper, we expect to provide a method tosupport robust and adaptable solutions to real use conditions.

This work presents an analysis of the efficiency and effectiveness of a Video-Based Pain Monitoring System running on a Raspberry selected because it is a cheap device that can be easily carried around. The objective of the evaluated system is to allow the assessment of pain based on two characteristics: Heart Rate (HR) and facial expressions detected through the Facial Action Coding System (FACS). To measure HR an Eulerian Video Magnification (EVM) based method was implemented. EVM is one of the main current approaches to measure HR by Remote PhotoPlethysmoGraphy. FACS was used to detect pain intensity with the Prkachin and Solomon Pain Intensity (PSPI) equation which is one of the most used approaches to detect pain intensity based on facial features. To identify the PSPI value we trained a Regression Neural Network (RNN) with the UNBC-McMaster database. The experimental results demonstrate the strengths and limitations of the evaluated system.

No abstract

This work presents an approach to the automatic detection of Butterfly Malar Rash (BMR) in images. BMR is a Lupus symptom characterized by a reddish facial rash that appears symmetrically in the cheeks and the back of the nose. The proposed approach is based on Transfer Learning, a popular approach in Deep Learning that consists in the use of pre-trained models as the starting point for computer vision and natural language processing tasks. To perform the experiments, a database was created with images manually collected from the Instagram social network, searching for images with #butterflyrash. We evaluated the proposed approach with eight Convolutional Neural Networks (CNN) architecture. The experimental results are good results, with a precision of up to 0.957.

Esse trabalho apresenta um relato de experiência referente a um trabalho aplicado como Atividade Prática Supervisionada, em uma disciplina de Processo de Desenvolvimento de Software, ofertada em um curso de graduação em Engenharia de Software. Nessa atividade os alunos foram divididos em grupos, sendo que cada grupo, em diferentes momentos representou os papéis de adquirente e fornecedor de um software (tal como é definido na norma ISO/IEC 12207:2008), sendo obrigatória a interação entre diferentes grupos. Durante o desenvolvimento da atividade os grupos tiveram que seguir alguns dos requisitos do MPS.BR, reforçando assim conceitos de qualidade de processo de software aprendidos em aula. Destaca-se que de acordo com a opinião dos alunos (obtida por meio de um questionário), esse trabalho contribuiu para aquisição e fixação dos conhecimentos da disciplina, assim como para mantê-los motivados durante seu desenvolvimento.