Proposed FPGA Hardware Architecture for High Frame Rate (≫100 fps) Face Detection Using Feature Cascade Classifiers
ABSTRACT Face detection is the first and most crucial step in any face recognition systems with applications to face tracking, recognition and automatic surveillance. AdaBoost based face detection training methods have been proposed for producing a rapidly fast detection implementation compared to other methods using the integral image for evaluating a series of weak classifiers very fast. Current software version implementations can achieve about 15-25 frames per second (fps) with a tunable compromise between detection accuracy and speed. In this paper, a novel hardware architecture design on FPGA based on AdaBoost face training and detection algorithm for detecting faces in high resolution images at high frame rates (>100 fps) is proposed. The proposed architecture can evaluate each sub-window in a single clock cycle, which is the fastest possible speed land is limited by the H/W clock running speed. Thus in this proposed approach, detection speed is independent from the number of weak classifiers implemented. The proposed architecture is verified on Xilinx Virtex-II Pro FPGA platform where experimental results show that the speed and memory outperform previous approaches in literature, achieving 143 fps for image size of 640 by 480 pixels using a single scan window. Parallelizing the scan window can lead to double/triple this speed and is dependent on the gate capacity of the FPGA.
- SourceAvailable from: psu.edu[show abstract] [hide abstract]
ABSTRACT: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.02/2004;
- [show abstract] [hide abstract]
ABSTRACT: We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based “face” and “nonface” model clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at the current image location. We show empirically that the distance metric we adopt for computing difference feature vectors, and the “nonface” clusters we include in our distribution-based model, are both critical for the success of our systemIEEE Transactions on Pattern Analysis and Machine Intelligence 02/1998; · 4.80 Impact Factor
Article: Detecting faces in images: a survey[show abstract] [hide abstract]
ABSTRACT: Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future researchIEEE Transactions on Pattern Analysis and Machine Intelligence 02/2002; · 4.80 Impact Factor