One of the main challenges of computer vision is efficiently detecting and classifying objects in an image or video sequence. Several machine learning approaches have been applied to this problem, demonstrating significant improvements in detection accuracy and speed. However, most approaches have limited object detection to a single class of objects, such as faces or pedestrians. A common benchmark for computer vision researchers is face detection. Given a set of images, a face detection

more »

... thm determines which images have sub-windows containing faces. This task is trivial for humans, but is computationally expensive for machines. Most face detection systems simplify the face detection problem by constraining the problem to frontal views of non-rotated faces. Approaches have been demonstrated capable of relaxing these constraints, at the cost of additional computation. They utilize AdaBoost to select a set of features and train a classifier. The detector uses a cascade structure to reduce the number of features considered for each subwindow. This approach is significantly faster than previous techniques and is applicable for real-time systems. There is a need for hardware architectures capable of detecting several objects in large image frames, and which can be used under several object detection scenarios. In this work, we present a generic, flexible parallel architecture, which is suitable for all ranges of object detection applications and image sizes. The architecture implements the AdaBoost-based detection algorithm, which is considered one of the most efficient object detection algorithms.