ABSTRACT This paper addresses some key issues related to the automation of fermentation process analysis in the context of industrial-scale ethanol production from sugarcane substrates. As the current methods for the determination of cell density and viability are time consuming and laborious, high resolution in situ microscopy (0.5µm) is proposed as a promising alternative. Laboratory-scale experiments presented here show that this imaging technique allows automatic, on-line, and real-time monitoring of yeast cells suspended in sugarcane molasses used in the ethanol industry. In particular, the feasibility of cell concentration measurements of Saccharomyces cerevisiae SA-1 in industrial sugarcane molasses is demonstrated. Automated concentration measurements exhibit a linear correlation with manual reference values using a Neubauer chamber from 3×106 cells/mL up to a saturation level at approximately 2×108 cells/mL. Furthermore, it was demonstrated that the microscopic resolution of this technique, combined with its large statistics, allows a morphological assessment of the size, shape and some internal structures of the yeast cells. On average, the accuracy of the algorithm´s yeast cells classification was 0.80. The results obtained suggest that the ISM is a suitable tool to perform in-line sugarcane fermentation monitoring.

Este artigo propõe um método automático com base em visão computacional, implementado em uma plataforma móvel, para inspecionar fissuras em alvenaria e concreto. O algoritmo desenvolvido para processamento de imagem realiza esta tarefa a partir de imagens da evolução de fissuras. A contribuição deste trabalho é o desenvolvimento de uma ferramenta móvel, com resposta rápida visando auxiliar os técnicos em visitas periódicas no monitorameto da abertura de fissuras em alvenaria e concreto. Os resultados obtidos mostram, com sucesso, as alterações dimensionais de fissuras detectadas pelo telefone celular de uma maneira mais rápida e precisa em comparação com a técnica de medição convencional. Independente da forma irregular das fissuras, o método proposto tem a vantagem de produzir resultados estatisticamente significativos na repetição de medição, diminuindo a subjetividade inerente à técnica de medição manual.

This paper proposes an automatic method based on the computing vision, implemented in a mobile platform, to inspect cracks in masonry and concrete. The developed algorithm for image processing performs this task from images of the cracks evolution. The contribution of this paper is the development of a mobile tool with quick response aiming to assist technicians in periodic visits when monitoring the crack opening in masonry and concrete. The obtained results show, successfully, the dimensional alterations of cracks detected by mobile phone in a faster and accurate way compared with the conventional measurement technique. Regardless the irregular shape of the cracks, the proposed method has the advantage of producing results statistically significant in measurement repetition by decreasing the subjectivity inherent to manual measurement technique.