Showing papers on "Three-dimensional face recognition published in 1993"

Face recognition: features versus templates

Abstract: Two new algorithms for computer recognition of human faces, one based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second based on almost-gray-level template matching, are presented. The results obtained for the testing sets show about 90% correct recognition using geometrical features and perfect recognition using template matching. >

Eyes detection for face recognition

Abstract: A correlation-based approach to automatic face recognition requires adequate normalization techniques. If the positioning of the face in the image is accurate, the need for shifting to obtain the best matching between the unknown subject and a template is drastically reduced, with considerable advantages in computing costs. In this paper, a novel technique is presented based on a very efficient eyes localization algorithm. The technique has been implemented as part of the “electronic librarian” of MAIA, the experimental platform of the integrated Al project under development at IRST. Preliminary experimental results on a set of 220 facial images of 55 people disclose excellent recognition rates and processing speed.

Integration of acoustic and visual speech for speaker recognition.

Abstract: • an improvement in recognition performance resulting from data fusion for normal input data and for a range of degraded input data conditions. • discriminative models will show better performance than predictive models. This will result from the more stringent data alignment (lip sync) requirements and the lack of classifier input information redundancy in the predictive scheme. Also, predictive modelling is expected to show less robustness to input data variability. • fuzzy ARTMAP models are expected to outperform MLP predictive models with regard to accuracy. This is because the fuzzy ARTMAP map field realises a minimax learning rule that conjointly allows the minimisation of predictive error and the maximisation of predictive generalisation [9]. Standard back–propagation learning does not provide such a mechanism. In addition, tremendous savings in training times are expected with the fuzzy ARTMAP approach. 4 CONCLUSIONS Humans often rely on multiple senses – particularly hearing and vision – for many recognition tasks. We have proposed the joint use of acoustic and visual information for reliable automatic speaker recognition. The initial step towards this goal has combined static facial image information with voice, and the results have shown that performance improvements can be achieved even with a relatively simple integration scheme. We believe that visual speech does convey personal identity information, and that its use in conjunction with acoustic speech results in improved automatic speaker recognition performance in terms of accuracy, robustness, and protection against impersonation. ACKNOWLEDGEMENT Sincere thanks are expressed to the Beit Trust for the financial support in form of a Beit Trust Fellowship awarded to the first author. 3 CLASSIFICATION Each known person is allocated an artificial neural network model. Multi–layer perceptrons (MLPs) trained as predictive or discriminative networks (Figure 1) are considered. speech speech Prediction Prediction Visual Acoustic speech Visual Identity error (a) Predictive modelling Visual speech Identity Acoustic speech Categorisation (b) Discriminative modelling Figure 1: Predictive and discriminative classifier modes For speedier and incremental training, fuzzy ARTMAP models are preferred. Each fuzzy ARTMAP model is trained to make a many–to–one mapping from acoustic speech to visual speech for its allotted person (Figure 2). The predictive error across an utterance acts as recognition measure. A fuzzy ARTMAP neural network architecture is composed of a pair of fuzzy Adaptive Resonance Theory modules (modules A and B in Figure 2) [9]. Each module creates recognition categories corresponding to its input data. The two modules are interconnected by …

Biologically Motivated Approach to Face Recognition

Abstract: A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition. The approach is based on the use of two-dimensional Gabor functions that fit the receptive fields of simple cells in the primary visual cortex of mammals. A descriptor set that is robust against translations is extracted by a global reduction operation and used for a search in an image database. The method was applied on a database of 205 face images of 30 persons and a recognition rate of 94% was achieved.

Attentional selection in object recognition

Abstract: A key problem in object recognition is selection, namely, the problem of identifying regions in an image within which to start the recognition process, ideally by isolating regions that are likely to come from a single object. Such a selection mechanism has been found to be crucial in reducing the combinatorial search involved in the matching stage of object recognition. Even though selection is of help in recognition, it has largely remained unsolved because of the difficulty in isolating regions belonging to objects under complex imaging conditions involving occlusions, changing illumination, and object appearances. This thesis presents a novel approach to the selection problem by proposing a computational model of visual attentional selection as a paradigm for selection in recognition. In particular, it proposes two modes of attentional selection, namely, attracted and pay attention modes as being appropriate for data and model-driven selection in recognition. An implementation of this model has led to new ways of extracting color, texture and line group information in images, and their subsequent use in isolating areas of the scene likely to contain the model object. Among the specific results in this thesis are: a method of specifying color by perceptual color categories for fast color region segmentation and color-based localization of objects, and a result showing that the recognition of texture patterns on model objects is possible under changes in orientation and occlusions without detailed segmentation. The thesis also presents an evaluation of the proposed model by integrating with a 3D from 2D object recognition system and recording the improvement in performance. These results indicate that attentional selection can significantly overcome the computational bottleneck in object recognition, both due to a reduction in the number of features, and due to a reduction in the number of matches during recognition using the information derived during selection. Finally, these studies have revealed a surprising use of selection, namely, in the partial solution of the pose of a 3D object. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

Testing Face Recognition Systems.

Abstract: This paper discusses some of the difficulties which arise when reporting computer face recognition testing results. Examples are given, from the authors' own work, of factors that are not usually discussed which can have a significant bearing on the reported recognition rate. It is shown that a popular and apparently rigorous approach to testing, where the choice is between a fixed number of faces, each of which appears in each of a fixed number of different conditions, can produce unrepresentative results. The paper raises more general questions, and makes recommendations about the type of information that should be included in order to provide greater confidence in reported recognition rates.

Knowledge-based face recognition using neural networks

Abstract: In this paper, we propose a method for facial feature extraction and recognition algorithm based on neural networks. First we separate the face part from the captured image based on the fact that the face image is located in the center of an input image and the background is relatively uniform. Then we obtain 4 normalized features from the extracted face image. For face recognition, we use the backpropagation technique of the neural networks. The proposed knowledge-based technique recognizes 14 persons correctly.

Recognition of partially occluded object

Abstract: Recognition of partially occluded objects has long been a difficult task in the area of pattern recognition and computer vision. The presence of occlusions complicates the problem of image registration and hence the subsequent tasks of object recognition. Traditionally, separate modules are used to detect occlusions prior to image registration. These are too intensive in terms of computation. In this paper, we propose a new image registration algorithm based on concurrent cross-correlation of two-dimensional multi-scale images to aid in the recognition of partially occluded objects. This algorithm is capable of detecting the presence of occlusions and localizing their positions concurrently during the image registration process. Experimental results show that the proposed algorithm is very effective in dealing with partial occlusion. >

Novel approach to human face recognition

Abstract: This paper presents a new method of human face recognition based on a novel algebraic feature extraction method. An input human face image is First transformed into a standard image; Then, the projective feature vectors of the standard image are extracted by projecting it onto the optimal discriminant projection vectors; Finally, face image recognition is completed by classifying these projective feature vectors. Experimental results showed that the present method is effective.

Face Recognition on the Connection Machine CM-5

Abstract: A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition The approach is based on the use of two dimensional Gabor functions that t the receptive elds of simple cells in the primary visual cortex of mammals A descriptor set that is robust against translations is extracted and used for a search in an image database The method was applied on a database of face images of persons and a recognition rate of was achieved The nal version of the paper will report on the results obtained by applying a set of Gabor functions on a database of face images of persons and on the implementation on a Connection Machine CM parallel supercomputer to be installed at our university until the end of