Visual terrain classification for mobile robot using bag of words / 医疗卫生装备

Objective To design a visual terrain classification algorithm to facilitate the robot to make appropriate movement strategy by perceiving the surrounding environment.Methods Bag of words (BOW) and support vector machine (SVM) were used to develop a simple and effective terrain classification algorithm.The BOW model involved in feature extraction,codebook generation and feature coding.The mid-level feature developed by BOW model was then fed into SVM classifier to obtain the terrain classification result.Results The quadruped robot platform was applied to performing visual terrain classification experiment in the natural environment.The test environment included floor,asphalt,sand and grass.Good experimental results were achieved,and the classification accuracy was above 90％ (the beat was 97.54％ for grass).Conclusion The algorithm can effectively and accurately distinguish all kinds of terrains,with high accuracy and good stability.The key frame selection method needs researching in the future.

Selección de color dentario: comparación de los métodos visual y espectrofotométrico / Selection of tooth colour: comparison of visual and spectrophotometric methods

Introducción En odontología la selección de color se realiza mediante métodos visuales o instrumentales: el primero, ampliamente utilizado, es subjetivo e influenciado por diversos factores, en tanto el instrumental con espectrofotómetro es objetivo y simple, pero poco utilizado. Objetivo Comparar los resultados en la selección del color utilizando los métodos visual y el espectrofotómetro Easyshade Compact, para verificar si existen diferencias. Material y método Cincuenta odontólogos, 25 hombres y 25 mujeres, seleccionaron el color de una pieza dentaria anterior sana con el muestrario Vitapan 3D Master, y se compararon los resultados con los obtenidos al utilizar el espectrofotómetro. Los datos se analizaron mediante Chi-cuadrado. Resultados El 18% de los odontólogos (el 24% de las mujeres y el 12% de los hombres) coincidió en la selección visual del color con lo obtenido con espectrofotómetro. Un 76% de las mujeres y un 88% de los hombres no concordaron en la selección visual con respecto a los resultados obtenidos con el espectrofotómetro. Conclusiones Existen diferencias estadísticamente significativas entre la selección del color dentario con el método visual y el espectrofotómetro (p < 0,0005). El género no parecería ser un factor determinante en la selección del color (p < 0,232).

Introduction In cosmetic dentistry the selection of colour can be performed by visual or instrumental methods. The former is subjective, influenced by multiple factors and widely used by dentists, whilst the latter, using a spectrophotometer, is objective and simple but little used. Objective To compare the results in the selection of colour by a visual method and using the Easyshade Compact spectrophotometer, to verify whether there are differences between them. Material and method A total of 50 dentists, 25 men and 25 women, were asked to select the colour of a healthy anterior tooth using the 3D Master Vitapan, and the results were compared with those obtained when using the Easyshade Compact spectrophotometer. The data obtained were analysed using the Chi-squared statistical test. Results The colour obtained by the visual colour selection matched that obtained with spectrophotometer by 18% of dentists. The colour selection by the visual method was different to that obtained with the spectrophotometer for 76% of women and 88% of men. Conclusions There are statistically significant differences between the selection of colour with the visual method and with spectrophotometer (P < .0005). Gender does not seem to be a determining factor in the selection of colour (P < .232).

Evaluation of perception of dental color by students and professors of dentistry

AIM: To evaluate visual perception of dental color carried out by students and professors of Dentistry area. MATERIAL AND METHODS: For this study, 64 people were selected to respond a personal questionnaire and a color selection questionnaire. The respondents also perform, using the color scale VITAPAN classical, the choice of healthy human tooth color, maintained humid and in an acrylic resin cylinder developed especially for this research. RESULTS: Only 6.25% of respondents answered correctly the natural tooth color. CONCLUSION: According to the color verification through a spectrophotometer, only 6.25% of respondents have carried out correctly the color selection. In this way, for the good aesthetical result, the criteria need to be standardized and pre-stablished in order to perform the color selection correctly, observing the variables which can interfere on its choice.