Selective Refinement Network for High Performance Face Detection

High Performance Method for Skin Roughness Detection Using Raman Spectroscopy

Motion Vector Refinement for High-Performance Transcoding

In transcoding, simply reusing the motion vectors extracted from an incoming video bit stream may not result in the best quality. In this paper, we show that the incoming motion vectors become nonoptimal due to the reconstruction errors. To achieve the best video quality possible, a new motion estimation should be performed in the transcoder. We propose a fast-search adaptive motion vector refi...

High-performance Network Intrusion Detection through Parallelism

Schuff, Derek L. M.S.E.C.E, Purdue University, May, 2007. High-Performance Network Intrusion Detection through Parallelism. Major Professor: Vijay S. Pai. Network intrusion detection has become increasingly popular in recent years due to the proliferation of Internet-based security attacks. Network intrusion detection systems (NIDS) inspect the content of incoming packets on a network for known...

Selective screening of 650 high risk Iranian patients for detection of inborn error of metabolism

Objective: Although metabolic diseases individually are rare ,but overall have an incidence of 1/2000 and can cause devastating and irreversible effect if not diagnosed early and treated promptly. selective screening is an acceptable method for detection of these multi presentation diseases.Method: using panel neonatal screening for detection of metabolic diseases in 650 high risk Iranian patie...

A high-performance face detection system using OpenMP

We present the development of a novel high-performance face detection system using a neural network-based classification algorithm and an efficient parallelization with OpenMP. We discuss the design of the system in detail along with experimental assessment. Our parallelization strategy starts with one level of threads and moves to the exploitation of nested parallel regions in order to further...