In this paper we present a framework for implementing computer vision algorithms on embedded processors using the analog devices Blackfin BF561 processor. This framework is designed to consist of a set of simple functions that allow complex tasks to be performed, such as object tracking or object recognition. Special consideration is given to the methods of optimization that are needed to achieve real-time performance. Given the low cost and low power consumption of embedded devices, the applications for this framework are very widespread and have the potential to be seen in many everyday devices. The completed framework is capable of processing algorithms at 15 frames per second with 24 bit colour, 360 times 240 pixel images which supports this approach as a useful direction for low cost, low power computer vision platforms.

Embedded computer vision framework on a multimedia processor

Este articulo sintetiza las principales investigaciones que se estan llevando a cabo en el area de los sistemas de reconocimiento a traves de la imagen facial. Se realiza la descripcion de las principales lineas de trabajo en los sistema de identificacion de personas por medio de la imagen del rostro. Ademas, se realiza una sintesis de las ultimas tecnicas matematicas para realizar la extraccion de caracteristicas dentro de estos sistemas de identificacion.

https://www.revistas.unal.edu.co/index.php/avances/article/download/19127/29978

Sistemas de reconocimiento basados en la imagen facial

This article summarizes the most important research projects developed in thearea of recognitions y stemsusing facial images. It presents the description of the principal lines of study about people identification systems using face recognition. Furthermore, it contains a synthesis of recent mathematical techniques for pattern sextraction in these systems.

Sistemas de reconocimiento basados en la imagen facial Recognition systems based on the facial

This work deals with face detection with using of directly connected camera to signal processor Blackfin (produced by Analog Devices). This work consists of description of interconnection between monochromatic camera KAC-9618 and DSP processor Blackfin BF-537. An algorithm of face detection and algorithm for communication between camera and DSP are also included. First of them is based on using of backpropagation neural network. Camera is controlled by setting values of its registers via I2C serial bus. In addition, there is an overview of used neural network.

B. Polikarpov

Papers

Face Detection by DSP Using Directly Connected Camera