PROJECT TITLE:

An AdaBoost-Based Face Detection System Using Parallel Configurable Architecture With Optimized Computation - 2015

ABSTRACT:

With the event of image sensor technology, the AdaBoost-primarily based face detections are widely used in several monitoring sensor networks and mobile-camera-primarily based applications. Quick face detection with high detection accuracy and low power consumption in such kinds of applications is terribly necessary. Since the AdaBoost-based face detection exhibits characteristics of data computation in dual direction and knowledge diversity, we have a tendency to propose an AdaBoost-based mostly face detection system using parallel configurable architecture with optimized computation. The design consists of parallel configurable arrays and 2-level shared memory systems. It achieves twin-direction-primarily based integral image computation that improves parallel processing efficiency and enables the subwindow adaptive cascade classification for knowledge diversity, that any improves the detection potency in various face detection. Compared with the state-of-the-art works, this work achieves maximal performance of thirty frames/s at 1080p detection speed and extreme low power consumption.