The increasing accessibility and high security of electroencephalography (EEG) signals have led to growing attention in the field of biometrics. Compared to existing biometric methods, the performance of EEG-based is not satisfactory due to the complexity and instability of EEG signals. For these methods, on the one hand, directly using raw EEG time series makes it difficult to obtain deep features to reflect individual differences; On the other hand, there is a lack of effective feature extraction methods to explore the correlation between EEG spatiotemporal dimensions. To this end, this paper proposes a novel stochastic adaptive Fourier decomposition (SAFD) enhanced multi-level collaborative network, abbreviated as SAFD-MLCNet, for EEG Biometric Authentication. Firstly, SAFD can simultaneously represent the intrinsic characteristics of multiple signals, rendering it exceptionally suitable for processing multichannel EEG signals. As such, SAFD is used to derive EEG signals with enhanced correlated information for subsequent network inputs. Following this, the MLCNet combines a temporal-spatial convolution (TS-Conv) block and a temporal-spatial joint attention (TSJ-Attn) block is employed to extract multi-scale spatiotemporal features, with the TSJ-Attn focusing on the mutual interaction between local temporal and spatial features. Experimental studies have been performed on two benchmark databases for various tasks of internal attack scenarios, external attack scenarios, cross-session capabilities. The experimental results prove that the proposed method achieves a state-of-the-art performance on the EEG Biometric Authentication, especially on the EEG Motor Movement/Imagery Dataset containing 109 individuals, achieving a classification accuracy of 99. 39% and an equal error rate (EER) of 0. 29%.

Convolutional neural networks (CNNs) have shown impressive performance in hyperspectral image (HSI) classification. However, these deep learning methods still face two major challenges. One is that they require a large number of training samples to train parameters, and the other is that high-dimensional nonlinear feature extraction and multi-source information fusion. This paper proposes a deep stochastic adaptive Fourier decomposition (SAFD) network integrated with back-propagation (BP) and multi-scale feature fusion to significantly improve classification accuracy. The main contributions are threefold: 1) A deep SAFD network with BP is designed, which introduces BP into the deep SAFD network for the first time, and achieves automatic dynamic optimization of network parameters through the back-propagation algorithm. 2) A Kalman filter-based multi-scale pyramid construction method is proposed, which extracts hierarchical spatial features through state recursion equations and enhances texture representation by fusing local binary patterns (LBP). 3) An efficient classification algorithm based on a deep stochastic adaptive Fourier decomposition network with a BP algorithm is developed to integrate deep SAFD features, multi-scale pyramid features, and LBP texture features, achieving higher classification accuracy. Experimental results show that the proposed method outperforms other selected HSI classification methods with similar principles. Moreover, compared with other state-of-the-art deep learning methods, the proposed method can achieve better classification performance.

Shaft-rate electromagnetic (EM) field is a critical feature in the detection of ships and underwater vehicles. However, the signal-to-noise ratio of the shaft-rate EM field is greatly reduced due to the presence of the static EM field, whose main energy is concentrated in the low-frequency section. In order to realize the effective detection of the weak shaft-rate EM field signals under a low signal-to-noise ratio, we propose a signal extraction method based on the Adaptive Fourier Decomposition (AFD) algorithm. At the decomposition stage, we utilize the Nevanlinna factorization and the maximal selection principle in each step, and then iteratively obtain various single components from low-frequency to high-frequency. At the extraction stage, the low-frequency information of the signal is effectively reconstructed by summing the first few components, leading to the retrieval of the shaft-rate EM field signal through residual operations. The experiment results on both synthesized and measured data show that the proposed algorithm converges faster with higher fidelity compared to the existing state-of-the-art method.

Deep learning-based hyperspectral image (HSI) classification methods have recently shown excellent performance. However, the success of these deep learning methods mainly relies on the deep network architecture with a huge amount of parameters trained by a large number of training samples. In this article, a deep high-order tensor sparse representation (SR) network (DHTSRNet) is proposed, which can obtain better classification results in the case of small training samples. Specifically, we propose a high-order tensor SR (HTSR) model that can handle arbitrary-order tensor-type data, and extend it to a deep HTSR model that can be used to train deep high-order tensor filters and features. Then, a deep feature extraction network (DHTSRNet) based on the deep HTSR model is constructed, which is used for feature extraction of HSI. Finally, an HSI classification method is constructed by combining DHTSRNet and the classifier based on graph-based learning (GSL), which can obtain better classification results in the case of small training samples. Experimental results show that the DHTSRNet can obtain better classification performance compared with other state-of-the-art HSI classification methods.

Very limited training samples pose significant challenges for hyperspectral image (HSI) classification. To address this issue, small-sample learning methods based on classical machine learning or deep learning offer promising solutions. In this article, a novel two-stage learning-based small-sample classification framework is proposed for HSIs, termed edge-preserving features-based smooth ordering (EPFSO). In the proposed EPFSO, a self-training approach and two screening mechanisms are designed to iteratively learn newly labeled samples from a vast pool of unlabeled samples, thereby enhancing classification accuracies by incorporating these additional samples into the training set. The preprocessing step involves using edge-preserving filters to extract key features and generate low-dimensional feature images. Subsequently, all samples are ordered based on spectral similarity and spatial proximity, resulting in a smooth 1-D signal. In the case of limited labeled samples, a specialized self-training approach based on linear interpolation is utilized to iteratively learn newly labeled samples from unlabeled samples. This process continues until no further labeled samples are introduced, enabling gradual improvement in classification performance. In addition, two screening mechanisms are designed into the self-training process to strike a balance between the reliability and quantity of newly labeled samples. Finally, once a sufficient number of training samples are available, a majority voting mechanism is employed to efficiently classify the remaining samples. Experimental results on three open HSI datasets demonstrate that the proposed EPFSO framework outperforms several state-of-the-art methods, including six deep learning approaches. This validates the attractiveness of using EPFSO to address the challenges associated with limited labeled samples.

Deep learning-based hyperspectral image (HSI) classification methods have recently shown excellent performance, however, there are two shortcomings that need to be addressed. One is that deep network training requires a large number of labeled images, and the other is that deep network needs to learn a large number of parameters. They are also general problems of deep networks, especially in applications that require professional techniques to acquire and label images, such as HSI and medical images. In this paper, we propose a deep network architecture (SAFDNet) based on the stochastic adaptive Fourier decomposition (SAFD) theory. SAFD has powerful unsupervised feature extraction capabilities, so the entire deep network only requires a small number of annotated images to train the classifier. In addition, we use fewer convolution kernels in the entire deep network, which greatly reduces the number of deep network parameters. SAFD is a newly developed signal processing tool with solid mathematical foundation, which is used to construct the unsupervised deep feature extraction mechanism of SAFDNet. Experimental results on three popular HSI classification datasets show that our proposed SAFDNet outperforms other compared state-of-the-art deep learning methods in HSI classification.

Real-time detection of driver drowsiness is critical to reduce the risk of road accidents and fatalities. Current facial landmark-based methods usually use a two-stage paradigm, where faces and facial landmarks are localized separately. Additionally, most methods can be hindered by challenging conditions, such as night driving or eyes closed. To address these challenges, we present a refined YOLO network named YOLOFaceMark that can simultaneously detect faces and their facial landmarks. Furthermore, we introduce a drowsiness detection model based on facial landmarks. This model utilizes extracted eye and mouth information to identify drowsy states. We optimize the original YOLO components through structural re-parameterization, channel shuffling, and the design of a dual-branch detection head with an implicit module. These enhancements are designed to improve the accuracy while maintaining computational efficiency. We validate the real-time performance and accuracy of YOLOFaceMark on public datasets, including 300W and COFW. Additionally, we conduct further validation to demonstrate our ability to achieve effective and robust drowsiness detection solely based on the facial landmarks detected by YOLOFaceMark.

Recently, hyperspectral image (HSI) classification methods based on deep learning have demonstrated excellent performance. However, these deep learning methods still face two major challenges. One is that they require a large number of labeled samples, and the other is that training parameters takes a lot of time. In this paper, we propose a dual-branch deep stochastic adaptive Fourier decomposition (SAFD) network (DSAFDNet) to alleviate the aforementioned two issues in HSI classification applications. SAFD is a newly developed signal processing tool with solid mathematical foundation. It can be used to find common filters (i.e. convolution kernels) of a set of random signals or multi-signals. Since the convolution kernels obtained by SAFD decomposition are complex numbers, few deep learning methods directly deal with such complex convolution kernels. To this end, we propose a dual-branch network to extract deep features from hyperspectral images using both real and imaginary parts of convolutional kernels. After deep feature extraction using DSAFDNet, we further investigate the classification performance of different classifiers on the extracted features. Experimental results show that the proposed method outperforms some HSI classification methods with similar principles. Moreover, compared with other state-of-the-art deep learning methods, the proposed method can achieve better classification performance.

In recent years, Correlation Filter (CF) based tracking methods using Convolutional Neural Network (CNN) features have achieved the state-of-the-art performance for object tracking. However, how to design an efficient deep CF based tracking method has not been well studied in the literature. To address this issue, we first develop a generic framework, which breaks a deep CF based tracking method into five components, including motion model, CNN feature extractor, CF model, CF updater, and location model. According to this framework, we design each component step by step. Then we propose a novel deep CF based tracking method by combining five effective components together. The proposed method outperforms several state-of-the-art tracking methods on two tracking benchmarks. Then the ablative experiments are conducted to study the influence of each component. The results show that the CF model and the CNN feature extractor play the most important roles in a deep CF based tracking method. Moreover, the CF updater, the location model, and the motion model can also improve the performance substantially.

This paper proposes a novel video compression method – stochastic adaptive Fourier decomposition (SAFD) based joint spatiotemporal model (JSTM). SAFD is a recently developed sparse representation theory that combines the traditional signal decomposition method with machine learning to adaptively decompose multi-signals into common atoms of predefined interpretable Szeg$\ddot{\text{o}}$kernel dictionary. Based on SAFD, this paper firstly proposes a learning-based 3D video to 2D data embedding method. The method learns common atoms based on the frames themselves that require to be compressed, without the need for pre-training on large-scale data like deep learning. Then the embedding-based JSTM and a feasible video compression architecture are developed. The contribution is twofold: introducing SAFD into video compression first time in the literature and developing a new video compression model JSTM. The experimental results are promising.

This paper is concerned with distributed consensus control of unknown multiagent systems. As the system’s dynamics is unknown, an adaptive Fourier decomposition (AFD) based iterative learning control (ILC) dynamics adaptive matching method in frequency domain is put forward to deal with it. First, large amounts of input and output measurement data are used to estimate the frequency domain characteristics of the system by Takenaka-Malmquist functions. Second, convert the traditional time domain ILC to the frequency domain to establish a matching relationship with the estimated frequency domain features. Then, an adaptive iterative learning rate is constructed to achieve the optimal convergence at each sampling point. The feasibility of the proposed algorithm is guaranteed by the convergence of AFD in Hardy space$H^{2}(\mathbb {D})$under the maximum selection principle. Compared with the reinforcement learning data-driven control scheme, the method proposed in this paper has obvious advantages in the control accuracy and convergence efficiency. In addition, this paper takes two kinds of denoising algorithms based on unwinding AFD to deal with the multi-agent systems with channel noise. Finally, the feasibility and effectiveness of the developed method are verified by a series of simulations.

In this paper, a Takenaka-Malmquist (TM) basis function based equivalent data-model is established by an adaptive rational decomposition for the finite-time interval trajectory tracking control and real-time control of a class of nonlinear systems in the frequency domain. This data model can adaptively learn and match the control process of nonlinear systems. As a result, the proposed trajectory tracking as well as real-time control method can reflect the feature of adaptive learning in order-by-order decomposition, and the feasibility of the proposed method is guaranteed by the convergence of adaptive decomposition by TM basis function under the maximum selection principle (MSP) in Hardy space$H^{2}(\mathbb {D})$. Compared with the traditional model-free control method, this data learning model which matches the control process has obvious advantages in the system model expression and control accuracy. Simulation results at the end of this paper show the effectiveness of the proposed method.

Most hyperspectral image (HSI) data exist in the form of tensor; the tensor representation preserves the potential spatial–spectral structure information compared with the vector representation, which can help improve the classification performance of HSI. In this article, a deep high-order tensor convolutional sparse coding (CSC) model is proposed, which can be used to train deep high-order filters. Based on the deep high-order tensor CSC model, a deep feature extraction network (DHTCSCNet) is constructed, which is used for feature extraction of HSIs. By combining the spectral–spatial feature and the features extracted by the proposed DHTCSCNet at each layer, a combined feature that incorporates shallow, deep, spectral, and spatial features can be obtained. Then, the graph-based learning (GSL) methods are used to classify the combined feature. Experimental results show that the DHTCSCNet can obtain better classification performance compared with other HSI classification methods.

Deconvolutional networks have attracted extensive attention and have been successfully applied in the field of computer vision. In this paper we propose a novel two-branch deconvolutional network (TBDN) that can improve the performance of conventional deconvolutional networks and reduce the computational complexity. A feasible iterative algorithm is designed to solve the optimization problem for the TBDN model, and a theoretical analysis of the convergence and computational complexity for the algorithm is also provided. The application of the TBDN in stereo matching is presented by constructing a disparity estimation network. Extensive experimental results on four commonly used datasets demonstrate the efficiency and effectiveness of the proposed TBDN.

Adaptive Fourier decomposition (AFD) is a newly developed signal processing tool that can adaptively decompose any single signal using a Szegö kernel dictionary. To process multiple signals, a novel stochastic-AFD (SAFD) theory was recently proposed. The innovation of this study is twofold. First, a SAFD-based general multi-signal sparse representation learning algorithm is designed and implemented for the first time in the literature, which can be used in many signal and image processing areas. Second, a novel SAFD based image compression framework is proposed. The algorithm design and implementation of the SAFD theory and image compression methods are presented in detail. The proposed compression methods are compared with 13 other state-of-the-art compression methods, including JPEG, JPEG2000, BPG, and other popular deep learning-based methods. The experimental results show that our methods achieve the best balanced performance. The proposed methods are based on single image adaptive sparse representation learning, and they require no pre-training. In addition, the decompression quality or compression efficiency can be easily adjusted by a single parameter, that is, the decomposition level. Our method is supported by a solid mathematical foundation, which has the potential to become a new core technology in image compression.

Disparity estimation is a popular topic in computer vision and has drawn increasing attention in recent years. In this article, we propose a new multi-stage network for the purpose of two to three-dimensional video conversion that contains two training stages: an initial disparity estimation as the first training stage and depth-image-based rendering (DIBR) as an extra component to form the second training stage. In the first training stage, we propose a revised end-to-end feature pyramid stereo network, in which the original non-pyramid structure is replaced by a bottom-up convolutional neural network pyramid for disparity regression. It utilizes the spatial information by concatenating different scale features to boost the performance on boundary consistency. Mirror connections between feature extraction and disparity regression on the corresponding layers are also added to improve the quality of the results. In the second stage, we propose an improved disocclusion filling technique in the DIBR branch and connect the non-neural-network method to the disparity estimation network. This two-stage training strategy can work effectively to generate the improved disparity estimation for two to three-dimensional video conversion. Extensive experiments are conducted and some selected state-of-the-art algorithms are compared with our proposed approach on the popular KITTI2015 and Scene Flow datasets. The results demonstrate that our estimated disparity map can generate high quality 3D images.

A functional feature extraction method based on rational function approximation for hyperspectral image (HSI) classification is proposed. In digital imagery, the spectral information of a pixel can be regarded as a 1-D signal. An HSI is composed of these 1-D signals arranged in a certain spatial structure. According to the functional characteristic of hyperspectral data, 1-D signals can be approximated by a linear combination of basis functions. Thus, a joint rational basis function system (JRBFS) based on class adaptivity is here first built for an HSI by adaptive Fourier decomposition (AFD). Second, the functional representations (FRs) and corresponding reconstructed spectral curves are obtained by decomposing the original spectral information in a JRBFS. Furthermore, the functional spectral-spatial features are extracted on the basis of FRs by an edge-preserving filtering method, FR-EPFs. Finally, the functional spectral-spatial features are used for HSI classification by SVM. Experimental results for five commonly used HSI data sets demonstrate the effectiveness and advantages of the proposed method FR-EPFs.

Object tracking is a challenging task in computer vision based intelligent transportation systems. Recently, Siamese based object tracking methods have attracted significant attention due to their highly efficient performance. These tracking methods usually train a Siamese network to match the initial target patch of the first frame with candidates in a new frame. In these methods, the offline training of the deep neural network and the online instance searching are effectively combined. However, these methods usually do not include template update or object re-identification, which easily results in the drift problem. In this paper, we propose a novel real-time object tracking method to overcome the above problems by effectively combining a multi-stream Siamese network and a region-based convolutional neural network. Specifically, a novel multi-stream Siamese network is proposed to search the target and update the instance template in a new frame. In addition, a faster region-based convolutional neural network detector is used to perform object re-identification in order to improve the tracking performance by making full use of the object category information. These two networks are tightly coupled to ensure that the proposed tracking method has high efficiency and strong discriminative capability. Experimental results on several object tracking benchmarks show that our tracking method can effectively track vehicles and pedestrians in video sequences by exploiting the object category information. The proposed tracking method achieves real-time operations and outperforms several other state-of-the-art methods.

This paper aims at proposing a novel 2D non-linear phase decomposition of images, which performs the image processing tasks better than the traditional Fourier transformation (linear phase decomposition), but further, it has additional mathematical properties allowing more effective image analysis, including adaptive decomposition components and positive instantaneous phase derivatives. 1D unwinding Blaschke decomposition has recently been proposed and studied. Through factorization it expresses arbitrary 1D signal into an infinite linear combination of Blaschke products. It offers fast converging positive frequency decomposition in the form of rational approximation. However, in the multi-dimensional cases, the usual factorization mechanism does not work. As a consequence, there is no genuine unwinding decomposition for multi-dimensions. In this paper, a 2D partial unwinding decomposition based on algebraic transforms reducing multi-dimensions to the 1D case is proposed and analyzed. The result shows that the fast convergence offers efficient image reconstruction. The tensor type decomposing terms are mutually orthogonal, giving rise to 2D positive frequency decomposition. The comparison results show that the proposed method outperforms the standard greedy algorithm and the most commonly used methods in the Fourier category. An application in watermarking is presented to demonstrate its potential in applications.

Matrix completion has been widely used in image processing, in which the popular approach is to formulate this issue as a general low-rank matrix approximation problem. This paper proposes a novel regularization method referred to as truncated Frobenius norm (TFN), and presents a hybrid truncated norm (HTN) model combining the truncated nuclear norm and truncated Frobenius norm for solving matrix completion problems. To address this model, a simple and effective two-step iteration algorithm is designed. Further, an adaptive way to change the penalty parameter is introduced to reduce the computational cost. Also, the convergence of the proposed method is discussed and proved mathematically. The proposed approach could not only effectively improve the recovery performance but also greatly promote the stability of the model. Meanwhile, the use of this new method could eliminate large variations that exist when estimating complex models, and achieve competitive successes in matrix completion. Experimental results on the synthetic data, real-world images as well as recommendation systems, particularly the use of the statistical analysis strategy, verify the effectiveness and superiority of the proposed method, i.e. the proposed method is more stable and effective than other state-of-the-art approaches.

This paper presents a novel signal compression algorithm based on the Blaschke unwinding adaptive Fourier decomposition (AFD). The Blaschke unwinding AFD is a newly developed signal decomposition theory. It utilizes the Nevanlinna factorization and the maximal selection principle in each decomposition step, and achieves a faster convergence rate with higher fidelity. The proposed compression algorithm is applied to the electrocardiogram signal. To assess the performance of the proposed compression algorithm, in addition to the generic assessment criteria, we consider the less discussed criteria related to the clinical needs-for the heart rate variability analysis purpose, how accurate the R-peak information is preserved is evaluated. The experiments are conducted on the MIT-BIH arrhythmia benchmark database. The results show that the proposed algorithm performs better than other state-of-the-art approaches. Meanwhile, it also well preserves the R-peak information.

Recently, the correlation filter based trackers have achieved very good tracking performance. However, due to the boundary effects of the circulant matrix and the usage of cosine window, the lack of effective negative samples becomes a challenging problem for the correlation filter based trackers. This problem may cause overfitting so that these trackers become very sensitive to deformation and occlusion. In this paper, we propose a novel object tracker (i.e., STAPLE_HNM), which can effectively select hard negative samples and assign adaptive weights to these samples to train the correlation filter. Experimental results demonstrate that the proposed STAPLE_HNM tracker effectively improves the performance of the baseline STAPLE_CA tracker on the OTB-50 and OTB-100 datasets. Moreover, the proposed STAPLE_HNM tracker also achieves superior performance among several state-of-the-art trackers.

In this paper, we deal with geometric model fitting problems on graphs, where each vertex represents a model hypothesis, and each edge represents the similarity between two model hypotheses. Conventional median-shift methods are very efficient and they can automatically estimate the number of clusters. However, they assign the same weighting scores to all vertices of a graph, which can not show the discriminability on different vertices. Therefore, we propose a novel weighted median-shift on graphs method (WMSG) to fit and segment multiple-structure data. Specifically, we assign a weighting score to each vertex according to the distribution of the corresponding inliers. After that, we shift vertices towards the weighted median vertices iteratively to detect modes. The proposed method can adaptively estimate the number of model instances and deal with data contaminated with a large number of outliers. Experimental results on both synthetic data and real images show the advantages of the proposed method over several state-of-the-art model fitting methods.

The depth image based rendering (DIBR) plays a key role in 3D video synthesis, by which other virtual views can be generated from a 2D video and its depth map. However, in the synthesis process, the background occluded by the foreground objects might be exposed in the new view, resulting in some holes in the synthetized video. In this paper, a hole filling approach based on background reconstruction is proposed, in which the temporal correlation information in both the 2D video and its corresponding depth map are exploited to construct a background video. To construct a clean background video, the foreground objects are detected and removed. Also motion compensation is applied to make the background reconstruction model suitable for moving camera scenario. Each frame is projected to the current plane where a modified Gaussian mixture model is performed. The constructed background video is used to eliminate the holes in the synthetized video. Our experimental results have indicated that the proposed approach has better quality of the synthetized 3D video compared with the other methods.

A challenge task of data mining is to process massive data in the big data era. MapReduce is an attractive model to overcome this challenge. This paper presents a new method to accelerate the process of learning Markov blanket Bayesian network(MBBN). Markov blanket is a better model type of Bayesian network in some complex datasets. The time and space cost of learning Markov blanket is large, and grows fast as the variables increase. Large amounts of data are needed for its independence test which makes the problem harder. The statistical phase and independence test are parallelized to make it find an appropriate relation among variables in the MapReduce framework. Computational results are reported by testing four datasets and show that the speed-up can be obtained by means of MapReduce. In particular, the Markov blanket in MapReduce has higher accuracy rate than naïve Bayesian and tree-augmented naïve Bayesian.

Smartphone camera is a very powerful sensor for many intelligent applications. But it is difficult to obtain a stable video quality in an unstable motion environment. In this case, robust and fast video stabilization algorithm is necessary for some intelligent applications on smartphone. A novel rapid and efficient video stabilization algorithm is proposed in this paper. The proposed algorithm not only obtains good visual effect, but can also be implemented in real-time on mobile platforms with limited computational resource. Our algorithm can process about 2.9ms per frame with QVGA video format on the mobile platform. The experimental results show the proposed method has similar video stabilization effect with the Optical Image Stabilization (OIS) hardware. The proposed algorithm can support many camera applications for smartphone.

3D video provides an immersive experience to viewers and is getting more and more popular. The solution to create 3D video from 2D video is low-cost compared with that captures 3D video directly, and the generation of depth map from 2D video is a key in the 2D-3D video conversion systems. Therefore, protection of depth map is vital for 3D video. In this paper, a digital blind watermarking scheme based on Quantization Index Modulation (QIM) algorithm is proposed in which the copyright information is embedded in the DCT coefficients of depth map imperceptibly. The experimental results show that the proposed scheme has good robustness against video attacks such as salt noise, median filtering, wiener filtering, and scaling. In the meanwhile, the stereo video embedded watermarking can accomplish zero distortion in comparison with the original one.

The paper introduces two different types of frequencies of which one is the Arccosine Instantaneous Frequency (ArccosineIF) for the so called axial simple waves (ASWs); and the other is the α-Counting Instantaneous Frequency (α-CIF) for a more general class of signals called simple waves (SWs). The classes ASW and SW contain a wide range of signals for which the concept instantaneous frequency has a perfect physical sense. Then under wavelet decomposition the two types of frequencies are used to analyze the time-frequency distributions of the biomedical EEG signals with comparison. A set of experiments on publicly available database clearly indicate that the proposed approaches are very promising.

Human facial feature detection is a significant but difficult task. An algorithm of knowledge based eye detection is presented. The algorithm consists of two main stages: the face and eye region locating stage and the eye detection stage. In the first stage, an effective approach to fast location of the face and eye region is developed. In the second stage, eye edge contour searching directed by knowledge is introduced in detail. Regional image processing techniques are also described in the second stage. The main purpose of the first stage is to locate the eye region roughly. The algorithm employed in the second stage is restricted to application in just this region. It reduces the complexity of the first stage and improves the reliability in the second stage. The Yale Face Database is used to evaluate the capability of the proposed methods and the results are promising.