Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult [43]. We present a hybrid neural network solution which compares favorably with other methods. The system combines local image sampling, a self-organizing map neural network, and a convolutional neural network. The self-organizing map provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the self-organizing map, and a multi-layer perceptron in place of the convolutional netwo...

Elastic graph matching has been proposed as a practical implementation of dynamic link matching, which is a neural network with dynamically evolving links between a reference model and an input image. Each node of the graph contains features that characterize the neighborhood of its location in the image. The elastic graph matching usually consists of two consecutive steps, namely a matching with a rigid grid, followed by a deformation of the grid, which is actually the elastic part. The deformation step is introduced in order to allow for some deformation, rotation, and scaling of the object to be matched. This method is applied here to the authentication of human faces where candidates claim an identity that is to be checked. The matching error as originally suggested is not powerful enough to provide satisfying results in this case. We introduce an automatic weighting of the nodes according to their significance. We also explore the significance of the elastic deformation for an application of face-based person authentication. We compare performance results obtained with and without the second matching step. Results show that the deformation step slightly increases the performance, but has lower influence than the weighting of the nodes. The best results are obtained with the combination of both aspects. The results provided by the proposed method compare favorably with two methods that require a prior geometric face normalization, namely the synergetic and eigenface approaches.

Face recognition is a rapidly growing research area due to increasing demands for security in commercial and law enforcement applications. This paper provides an up-to-date review of research efforts in face recognition techniques based on two-dimensional (2D) images in the visual and infrared (IR) spectra. Face recognition systems based on visual images have reached a significant level of maturity with some practical success. However, the performance of visual face recognition may degrade under poor illumination conditions or for subjects of various skin colors. IR imagery represents a viable alternative to visible imaging in the search for a robust and practical identification system. While visual face recognition systems perform relatively reliably under controlled illumination conditions, thermal IR face recognition systems are advantageous when there is no control over illumination or for detecting disguised faces. Face recognition using 3D images is another active area of face recognition, which provides robust face recognition with changes in pose. Recent research has also demonstrated that the fusion of different imaging modalities and spectral components can improve the overall performance of face recognition.

Gesture recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost importance in designing an intelligent and efficient human–computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation to virtual reality. In this paper, we provide a survey on gesture recognition with particular emphasis on hand gestures and facial expressions. Applications involving hidden Markov models, particle filtering and condensation, finite-state machines, optical flow, skin color, and connectionist models are discussed in detail. Existing challenges and future research possibilities are also highlighted.

Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult (Turk and Pentland, 1991). We present a hybrid neural network solution which compares favorably with other methods. The system combines local image sampling, a self-organizing map neural network, and a convolutional neural network. The self-organizing map provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loève transform in place of the self-organizing map, and a multilayer perceptron in place of the convolutional network. The Karhunen-Loève transform performs almost as well (5.3 % error versus 3.8%). The multilayer perceptron performs very poorly (40 % error versus 3.8%). The method is capable of rapid classification, requires only fast, approximate normalization and preprocessing, and consistently exhibits better classification performance than the eigenfaces approach (Turk and Pentland, 1991) on the database

Search has arguably become the dominant paradigm for finding information on the World Wide Web. In order to build a successful search engine, there are a number of challenges that arise where techniques from artificial intelligence can be used to have a significant impact. In this paper, we explore a number of problems related to finding information on the web and discuss approaches that have been employed in various research programs, including some of those at Google. Specifically, we examine issues of such as web graph analysis, statistical methods for inferring meaning in text, and the retrieval and analysis of newsgroup postings, images, and sounds. We show that leveraging the vast amounts of data on web, it is possible to successfully address problems in innovative ways that vastly improve on standard, but often data impoverished, methods. We also present a number of open research problems to help spur further research in these areas.

This paper describes information theoretic methods for the determination of the optimal subset of pixels for the problem of face detection in complex backgrounds. A view-based method is described, which has limitations due to misalignments. This motivates the modular feature based method which minimizes the misalignment problem. Empirical comparisons between the viewbased, modular, and sum of squared difference methods are made using four databases from three universities. 1. Introduction The face detection problem may be described as follows: Given a test image (any scanned in photograph or frame from a video camera), find the locations and size of every human face within the image. The problem of face detection differs from the problem of face recognition in that face detection has exactly two classifications: face or nonface, whereas face recognition usually has a number of classifications equal to the number of individuals. Face detection is important to a wide variety of areas wh...

Snakes are now a very popular technique for shape extraction by minimising a suitably formulated energy functional. A dual snake configuration using dynamic programming has been developed to locate a global energy minimum. This complements recent approaches to global energy minimisation via simulated annealing and genetic algorithms. These differ from a conventional evolutionary snake approach, where an energy function is minimised according to a local optimisation strategy and may not converge to extract the target shape, in contrast with the guaranteed convergence of a global approach. The new technique employing dynamic programming is deployed to extract the inner face boundary, along with a conventional normaldriven technique to extract the outer face boundary. Application to a database of 75 subjects showed that the outer contour was extracted successfully for 96 % of the subjects and the inner contour was successful for 82%. The results demonstrated the benefits that could accrue from inclusion of face features, giving an appropriate avenue for future research.

This report describe a new algorithm to measure local symmetry in a graylevels image. The introduced DST shows intresting properties of size and ro18 tation invariance; moreover it can be espressed as a local operator, given by the product of two filters. This allows to implement fast serial and parallel algorithms.

. Recent advances in human face detection algorithms have seen varying degrees of success using numerous approaches. We identify that a feature-based approach is able to detect faces efficiently over large viewpoint and illumination variations. In this paper, we will enhance the approach by proposing the use of active contour models to detect the face boundary, and subsequently use it to verify face candidates. We present a method to initialize the active contour model, and show how the resulting information can be used to verify true face candidates. Further verification of the face hypothesis is achieved by checking for consistency with motion. We present results of testing the system under a wide range of imaging conditions, demonstrating its capability and robustness. 1 Introduction Human face detection is an active research area with important applications in automatic face recognition, visual surveillance, and man-machine interface. Successful detection on fronto-parallel faces ...