CSolutions for a Face Detection and （人脸检测和CSolutions）.pdf

ˇ FACTA UNIVERSITATIS (NI S) SER .: ELEC . ENERG . vol. 20, no. 1, April 2007, 93-105 C# Solutions for a Face Detection and Recognition System ˘ ˘ ˘ Catalin-Daniel Caleanu and Corina Botoca Abstract: Key issues on using a new programming language - C# - in implementation of a face detection and recognition (FDR) system are presented. Mainly the following aspects are detailed: how to acquire an image, broadcast a video stream, manipulate a database, and finally, the detection/recognition phase, all in relation with theirs pos- sible C#/.NET solutions. Emphasis was placed on artificial neural network (ANN) methods for face detection/recognition along with C# object oriented implementation proposal. Keywords: C#/.NET, face detection and recognition. 1 Introduction In June 2000, Microsoft announced both the .NET platform and a new program- ming language called C# [1–3]. .NET is a framework that covers all the layers of software development from the operating system up. It actually wraps the operat- ing system, insulating software developed with .NET from most operating system specifics such as file handling and memory allocation. It provides a new appli- cation programming interface (API) to the services and APIs of classic Windows operating systems while bringing together a number of disparate technologies that emerged from Microsoft during the late 1990s. It provides the richest level of integration among presentation technologies, component technologies, and data technologies ever seen on a Microsoft platform. This includes COM+ component services, a commitment to XML and object-oriented design, support for new web services protocols such as SOAP, WSDL, and UDDI, etc. .NET framework com- ponents are depicted in Figure 1. Manuscript