Resumen
The article reports that vision and speech are co-expressive and complementary channels in human-human interaction. Just as automatic speech recognition seeks to build machines that perceive the verbal aspects of human communication, computer vision technology can be used to build machines that look at people and automatically perceive relevant visual information. Computer vision is the computing discipline that attempts to make computers see by processing images and video. By understanding the geometry and radiometry of image formation, properties of the sensor, and properties of the physical world, it is possible to infer useful information about the world from imagery such as the color of a swatch of fabric, the width of a printed circuit trace, the size of an obstacle in front of a mobile robot on Mars, the identity of a person's face in a surveillance system, the vegetation type of the ground below, or the location of a tumor in an MRI scan.