Showing papers on "Three-dimensional face recognition published in 1998"

Characterising Virtual Eigensignatures for General Purpose Face Recognition

Abstract: We describe an eigenspace manifold for the representation and recognition of pose-varying faces. The distribution of faces in this manifold allows us to determine theoretical recognition characteristics which are then verified experimentally. Using this manifold a framework is proposed which can be used for both familiar and unfamiliar face recognition. A simple implementation demonstrates the pose dependent nature of the system over the transition from unfamiliar to familiar face recognition. Furthermore we show that multiple test images, whether real or virtual, can be used to augment the recognition process. The results compare favourably with reported human face recognition experiments. Finally, we describe how this framework can be used as a mechanism for characterising faces from video for general purpose recognition.

Face recognition using temporal image sequence

Abstract: We present a face recognition method using image sequence. As input we utilize plural face images rather than a "single-shot", so that the input reflects variation of facial expression and face direction. For the identification of the face, we essentially form a subspace with the image sequence and apply the Mutual Subspace Method in which the similarity is defined by the angle between the subspace of input and those of references. We demonstrate the effectiveness of the proposed method through several experimental results.

A novel method for automatic face segmentation, facial feature extraction and tracking

Abstract: The present paper describes a novel method for the segmentation of faces, extraction of facial features and tracking of the face contour and features over time. Robust segmentation of faces out of complex scenes is done based on color and shape information. Additionally, face candidates are verified by searching for facial features in the interior of the face. As interesting facial features we employ eyebrows, eyes, nostrils, mouth and chin. We consider incomplete feature constellations as well. If a face and its features are detected once reliably, we track the face contour and the features over time. Face contour tracking is done by using deformable models like snakes. Facial feature tracking is performed by block matching. The success of our approach was verified by evaluating 38 different color image sequences, containing features as beard, glasses and changing facial expressions.

Beyond eigenfaces: probabilistic matching for face recognition

Abstract: We propose a technique for direct visual matching for face recognition and database search, using a probabilistic measure of similarity which is based on a Bayesian analysis of image differences. Specifically we model lure mutually exclusive classes of variation between facial images: intra-personal (variations in appearance of the same individual, due to different expressions or lighting) and extra-personal (variations in appearance due to a difference in identity). The likelihoods for each respective class are learned from training data using eigenspace density estimation and used to compute similarity based on the a posteriori probability of membership in the intra-personal class, and ultimately used to rank matches in the database. The performance advantage of this probabilistic technique over nearest-neighbor eigenface matching is demonstrated using results front ARPA's 1996 "FERET" face recognition competition, in which this algorithm was found to be the top performer.

Multimodal human emotion/expression recognition

Abstract: Recognizing human facial expression and emotion by computer is an interesting and challenging problem. Many have investigated emotional contents in speech alone, or recognition of human facial expressions solely from images. However, relatively little has been done in combining these two modalities for recognizing human emotions. L.C. De Silva et al. (1997) studied human subjects' ability to recognize emotions from viewing video clips of facial expressions and listening to the corresponding emotional speech stimuli. They found that humans recognize some emotions better by audio information, and other emotions better by video. They also proposed an algorithm to integrate both kinds of inputs to mimic human's recognition process. While attempting to implement the algorithm, we encountered difficulties which led us to a different approach. We found these two modalities to be complimentary. By using both, we show it is possible to achieve higher recognition rates than either modality alone.

Facial feature extraction in frontal views using biometric analogies

Abstract: Face detection and facial feature extraction are considered to be key requirements in many applications, such as access control systems, model-based video coding, content-based video browsing and retrieval Thus, accurate face localization and facial feature extraction are most desirable A face detection and facial feature extraction in frontal views algorithm is described in this paper The algorithm is based on principles described in [1] but extends the work by considering: (a) the mirror-symmetry of the face in the vertical direction and (b) facial biometrie analogies depending on the size of the face estimated by the face localization method Further improvements have been added to the face localization method to enhance its performance The proposed algorithm has been applied to frontal views extracted from the European ACTS M2VTS database with very good results

Emotion recognition from audiovisual information

Abstract: We report preliminary results on emotion recognition by machine from joint audiovisual input of facial video and speech. The results show potential advantages in using both modalities over either modality alone. The recognition rate for audio alone is about 75% and video alone about 70%. Using audiovisual data we achieved 97% without increasing the number of features. The improvement in performance is accredited to the complementary property between the two modalities. A possible application is in natural human-computer interfaces.

Face recognition from unfamiliar views: subspace methods and pose dependency

Abstract: A framework for recognising human faces from unfamiliar views is described and a simple implementation of this framework evaluated. The interaction between training view and testing view is shown to compare with observations in human face recognition experiments. The ability of the system to learn from several training views, as available in video footage, is shown to improve the overall performance of the system as is the use of multiple testing images.

A robust approach to face and eyes detection from images with cluttered background

Abstract: Automatic face location in complex scenes is extremely challenging in human face recognition systems. Further more, the facial features detection also plays an important role. The paper presents a scheme for robust face and eyes detection from an image. The scheme uses the Gaussian steerable filter to search and detect the facial feature (preattentive feature) roughly in an image. The face model is investigated to locate the whole face and facial features, such as eyes, nose and mouth. Here, multiple evidences are used in the face location and eyes detection. One important feature is the structural information of the face, i.e. facial components of certain structure. The other is the symmetry property of the face, here only the front face with certain pose variation is considered. It will reduce the computation greatly. For facial components detection, some image features and PCA features are used for verification from the candidates detected before. Experiments show that the algorithm is robust and fast.

Fast Multi-Scale Face Detection

Abstract: Computerized human face processing (detection, recognition, synthesis) has known an intense research activity during the last few years. Applications involving human face recognition are very broad with an important commercial impacts. Human face processing is a difficult and challenging task: the space of different facial patterns is huge. The variability of human faces as well as their similarity and the influence of other features like beard, glasses, hair, illumination, background etc., make face recognition or face detection difficult to tackle. The main task during the internship was to study and implement a neural-network based face detection algorithm for general scenes, which has previously been developed within the IDIAP Computer Vision group. It also included the study and design of a multi-scale face detection method. A face database and a camera were available to make tests and perform some benchmarking. The main constaint was to have a real-time or almost real-time face detection system. This has beeen achieved. Evaluation of the face detection capability of the employed neural networks were demonstrated on a variety of still images. In addition, we introdudced an efficient preprocessing stage and a new post-processing strategy to eliminate false detections significantly. This allowed to deploy a single neural network for face detection running in a sequential manner on a standard workstation.

Partial face recognition using radial basis function networks

Abstract: The paper describes a face recognition system that uses partial face images (for example, eye, nose, and ear images) for input data. The recognition technique is based on using radial basis function (RBF) networks. As compared with using a standard backpropagation (BP) learning algorithm, the RBF networks are far superior for the face recognition task. From the experimental results of face recognition by partial face image data on a database of over 100 persons, we have achieved a recognition accuracy rate of 100% for the recognition of registered persons and a rejection rate of 100% for the rejection of unknown samples.

Real-time face recognition with the continuous n-tuple classifier

Abstract: The continuous n-tuple classifier was recently proposed by the author as a new type of n-tuple classifier that is ideally suited to problems where the input is continuous or multi-level rather than binary. Results on a widely used face database show the continuous n-tuple classifier to be as accurate as any method reported in the literature, while having the advantages of speed and simplicity over other methods. This paper summarises the previous work, provides fresh insight into how the system works and discusses its applicability to real-time face recognition. (7 pages)

Real-time face recognition using feature combination

Abstract: We present an experimental setup for real time face identification in a cluttered scene. Color images of people are recorded with a static camera. A rough face detection is performed, and the resulting images are stored in a database. At a future time, a person standing in front of the camera (although against a different background) is identified, if their image was present in the database. In our experiments, the main variation of the faces is wide pose variation (out-of-image plane rotation of the head); some scale variation was also present. For real time ability, we use simple image features and a voting procedure for performing face recognition.

Automatic pose estimation system for human faces based on bunch graph matching technology

Abstract: We present an automatic module that can determine the pose of a human face from a digitized portrait-style image. The module is integrated into a larger system called PersonSpotter, which is able to recognize people by their faces coming from a live video stream of data. The pose estimation module is based on bunch graph matching and can distinguish between five different degrees of rotation in depth. The system features close to real-time performance, considerable decrease in data size and increase in the accuracy of pose recognition compared to similar systems developed in the past. Pose estimation success rate of 98.5% has been reached for a set of 210 faces rotated in various degrees and directions.

Face Detection and Recognition

Abstract: Two of the most important aspects in the general research framework of face recognition by computer are addressed here: face and facial feature detection, and face recognition — or rather face comparison. The best reported results of the mug-shot face recognition problem are obtained with elastic matching using jets. In this approach, the overall face detection, facial feature localization, and face comparison is carried out in a single step. This paper describes our research progress towards a different approach for face recognition. On the one hand, we describe a visual learning technique and its application to face detection in complex background, and accurate facial feature detection/tracking. On the other hand, a fast algorithm for 2D-template matching is presented as well as its application to face recognition. Finally, we report an automatic, real-time face recognition system.

Detecting head pose from stereo image sequence for active face recognition

Abstract: An approach to detect human head pose by reconstructing 3D positions of facial points from stereo images is proposed for the implementation of an active face recognition system where fast, correct and automatic head pose detection is of critical importance. Four facial points (pupils and mouth corners) are extracted using a simple but efficient method and their three-dimensional coordinates are reconstructed from stereo images. The orientation of the face relative to the camera plane can be computed from the triangular points and thus eliminating the need to know the image vs. model correspondence or the head physical parameters. Errors of pose detection are analyzed and experimental results are shown. Using the head pose detection system, facial images with suitable pose can be selected automatically from the image sequence as input to the face recognition system.

A similarity-based method for the generalization of face recognition over pose and expression

Abstract: Human observers are capable of recognizing a face seen only once before when confronted with it subsequently under different viewing conditions. We constructed a working computational model of such generalization from a single view, and tested it on a homogeneous database of face images obtained under tightly controlled viewing conditions. The model effectively constructs a view space for novel faces by interpolating view spaces of familiar ones. Its performance /spl sim/30% error rate in one out of 18 recognition, and 8% in one out of three discrimination-is encouraging, given that it reflects generalization from a single view/expression to a range of /spl plusmn/34/spl deg/ rotation in depth and to two additional expressions. For comparison, human subjects in the one out of three task involving only viewpoint changes exhibit a 3% error rate.

Face recognition using binary image metrics

Abstract: We introduce a novel methodology applicable to face matching and fast screening of large facial databases. The proposed shape comparison method operates on edge maps and derives holistic similarity measures without the explicit need for point-to-point correspondence. While the use of edge images is important to introduce robustness to changes in illumination, the lack of point-to-point matching delivers speed and tolerance to local non-rigid distortions. In particular, we propose a face similarity measure derived as a variant of the Hausdorff distance by introducing the notion of a neighborhood function and associated penalties. Experimental results on a large set of face images demonstrate that our approach produces excellent recognition results even when less than 1% of the original grey scale face image information is stored in the face database (gallery). These results implicate that the process of face recognition may start at a much earlier stage of visual processing than it was earlier suggested.

Spatiotemporal analysis of face profiles: detection, segmentation, and registration

Abstract: We use a two-image approach to construct a 3D human facial model for multimedia applications The images used are those of faces at direct frontal and side views The selection of the side view from a sequence of facial images is automatically done by applying a spatiotemporal approach to face profile analysis The extracted side profile is then segmented based on knowledge of known local facial structures Temporal consistency in the structure of the face under small deviations from the profile image is exploited to improve robustness of the segmentation in the presence of noise and image artifacts Once the face profile is properly segmented, nine perceptually significant landmarks (fiducial points) on the face are registered based on a local maximum curvature computation The methods developed are invariant to geometric transformation and are more robust than earlier approaches which rely only on the spatial structure of the face

Learning to identify and track faces in image sequences

Abstract: We address the problem of robust face identification in the presence of pose, lighting, and expression variation. Previous approaches to the problem have assumed similar models of variation for each individual, estimated from pooled training data. We describe a method of updating a first order global estimate of identity by learning the class-specific correlation between the estimate and the residual variation during a sequence. This is integrated with an optimal tracking scheme, in which identity variation is decoupled from pose, lighting and expression variation. The method results in robust tracking and a more stable estimate of facial identity under changing conditions.

A robust face identification against lighting fluctuation for lock control

Abstract: Lock-control is one of the most important security. This paper presents a face identification system for the lock-control. This system is robust for the fluctuation of the size and incline of face and lighting condition. There are two main processes in the face identification: 1) extraction of a face from input image and normalization of the size and incline of the face image, 2) matching of facial features (eye, nose and mouth) which is robust for lighting fluctuation. In order to achieve high reliability, the normalization process searches inner corners of eyes and then applies affine transformation to the face image according to the positions of the detected inner corners. The matching is performed on facial features by new template matching which uses 'sectionally adaptive correlation' for robustness against lighting fluctuation. Thresholds of the matching are determined by statistical estimation. When the system identifies a registered person, if unlocks the door. We have implemented this system and tarried out same experiments. The results show good feasibility of the lock control system and its robustness against lighting fluctuation.

Face extraction from non-uniform background and recognition in compressed domain

Abstract: A complete face recognition system is proposed in this paper by introducing the concepts of foreground objects, which are currently used in the MPEG-4 standardization phase, to human identification. The system automatically detects and extracts the human face from the background, even if is not uniform, based on a combination of a retrainable neural network structure and the morphological size distribution technique. In order to combine face images of high quality and low computational complexity, the recognition stage is performed in the compressed domain. Thus, in contrast to existing recognition schemes, the face images are available in their original quality and not only in their transformed representation.

Improving OCR accuracy through combination: a survey

Abstract: Optical character recognition is perhaps the most studied application of pattern recognition. Recent work has increased accuracy in two ways. Combination of individual classifier outputs overcomes deficiencies of features and trainability of single classifiers. OCR systems take page images as input and output strings of recognized characters. Due to character segmentation errors, characters can be split or merged preventing output combination character-by-character. Merging of output strings is done using string alignment algorithms.

A fast approach for detecting human faces in a complex background

Abstract: Human face detection is an important capability with a wide range of applications, such as human face recognition, surveillance systems, human-computer interfacing, video-conferencing, etc. In most such applications, the existence of human faces and their corresponding locations must be found. In other words, a reliable and fast method for detecting and locating face regions is of practical importance. In this paper, possible face region candidates in an image with a complex background are identified by means of the valley features on the eyes. These valley features are considered to belong to the eyes of a human face if they satisfy the local properties of the eyes. A pair of these features is matched if their Gabor features are similar; a face region is then formed. Each of the face region candidates is then further verified by matching it to a human face template, and by measuring its symmetry. Experiments show that this approach is fast and reliable.

Vowel recognition according to lip shapes by using neural network

Abstract: Although speech recognition techniques have been successfully developed, the noise of the circumstances causes serious errors in recognition. In such cases, we expect that lip shapes are useful data as supporting data to improve the performance of recognition. We propose a method to extract lip shapes from input face images by using an active contour model. After transformation and normalization the extracted data are input to a neural network to recognize vowels. Experimental results of vowel recognition are shown to confirm effectiveness of the proposed method.

Segmentation of Japanese handwritten characters using peripheral feature analysis

Abstract: A method of character segmentation of Japanese handwritten characters has been developed. It is effective especially in character recognition with the over-segmentation process. The method is based on the credibility measurement of each presegmented pattern for being a true character by analyzing peripheral features such as gaps between patterns and widths and heights of patterns. A heuristic statistical method is applied to the analysis. Experimental results show that the developed method increases the accuracy of character segmentation. It is effective especially when no linguistic feedback to segmentation is available and/or the character classifier ability is not high enough. In such cases, the recognition accuracy is increased from 30% to 70% by the new segmentation method.