5 resultados para computer vision


Relevância:

60.00% 60.00%

Publicador:

Resumo:

[ES]Hoy en día, la linea de investigación sobre la detección de rostros se ha incrementado, debido al uso y la influencia del mismo en diferentes aplicaciones. Por ejemplo, la mayoría de las cámaras digitales actuales, para mejorar la claridad de la imagen y la focalización, tienen incorporado un sistema de detección del rostro. La detección del rostro también es el primer paso para otras aplicaciones y lineas de investigación, como pueden ser el seguimiento de los ojos, y la vigilancia de la seguridad de varias aplicaciones, entre otros. Por esta razón, es necesario realizar una correcta detección facial. En esta tesis de máster, se realizará un análisis y estudio del estado del arte de la detección del rostro, para posteriormente realizar una aplicación práctica, así como su validación y análisis. El detector desarrollado es la conjunción del uso de diferentes cascadas de clasificadores basados en el método de Viola y Jones y las características de Lienhart, y un detector de piel.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Computer vision algorithms that use color information require color constant images to operate correctly. Color constancy of the images is usually achieved in two steps: first the illuminant is detected and then image is transformed with the chromatic adaptation transform ( CAT). Existing CAT methods use a single transformation matrix for all the colors of the input image. The method proposed in this paper requires multiple corresponding color pairs between source and target illuminants given by patches of the Macbeth color checker. It uses Delaunay triangulation to divide the color gamut of the input image into small triangles. Each color of the input image is associated with the triangle containing the color point and transformed with a full linear model associated with the triangle. Full linear model is used because diagonal models are known to be inaccurate if channel color matching functions do not have narrow peaks. Objective evaluation showed that the proposed method outperforms existing CAT methods by more than 21%; that is, it performs statistically significantly better than other existing methods.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

215 p.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Deep neural networks have recently gained popularity for improv- ing state-of-the-art machine learning algorithms in diverse areas such as speech recognition, computer vision and bioinformatics. Convolutional networks especially have shown prowess in visual recognition tasks such as object recognition and detection in which this work is focused on. Mod- ern award-winning architectures have systematically surpassed previous attempts at tackling computer vision problems and keep winning most current competitions. After a brief study of deep learning architectures and readily available frameworks and libraries, the LeNet handwriting digit recognition network study case is developed, and lastly a deep learn- ing network for playing simple videogames is reviewed.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Computer vision algorithms that use color information require color constant images to operate correctly. Color constancy of the images is usually achieved in two steps: first the illuminant is detected and then image is transformed with the chromatic adaptation transform ( CAT). Existing CAT methods use a single transformation matrix for all the colors of the input image. The method proposed in this paper requires multiple corresponding color pairs between source and target illuminants given by patches of the Macbeth color checker. It uses Delaunay triangulation to divide the color gamut of the input image into small triangles. Each color of the input image is associated with the triangle containing the color point and transformed with a full linear model associated with the triangle. Full linear model is used because diagonal models are known to be inaccurate if channel color matching functions do not have narrow peaks. Objective evaluation showed that the proposed method outperforms existing CAT methods by more than 21%; that is, it performs statistically significantly better than other existing methods.