This paper describes the development of a system for automatic number plate recognition of Colombian vehicles. This system is based on an embedded system with mixed processing capability, specifically using the ZedBoard, which includes a Zynq 7000 Xilinx device. The results presented in this document correspond to the first part of a research project, which involves the license plate number recognition using only software components. The methodology for segmentation and detection of the plate was made by identifying the yellow color on the plane HSV (saturation and brightness matrix) in the color image. A neuronal network was implemented using a backpropagation algorithm, which allows the identification of every alphanumeric character in the plate.