Azriel Rosenfeld

Face recognition: A literature survey

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.

A Comparative Study of Texture Measures for Terrain Classification

Three standard approaches to automatic texture classification make use of features based on the Fourier power spectrum, on second-order gray level statistics, and on first-order statistics of gray level differences, respectively. Feature sets of these types, all designed analogously, were used to classify two sets of terrain samples. It was found that the Fourier features generally performed more poorly, while the other feature sets all performned comparably.

Scene Labeling by Relaxation Operations

Given a set of objects in a scene whose identifications are ambiguous, it is often possible to use relationships among the objects to reduce or eliminate the ambiguity. A striking example of this approach was given by Waltz [13]. This paper formulates the ambiguity-reduction process in terms of iterated parallel operations (i.e., relaxation operations) performed on an array of (object, identification) data. Several different models of the process are developed, convergence properties of these models are established, and simple examples are given.

Digital topology: introduction and survey

Abstract Digital topology deals with the topological properties of digital images: or, more generally, of discrete arrays in two or more dimensions. It provides the theoretical foundations for important image processing operations such as connected component labeling and counting, border following, contour filling, and thinning—and their generalizations to three- (or higher-) dimensional “images.” This paper reviews the fundamental concepts of digital topology and surveys the major theoretical results in the field. A bibliography of almost 140 references is included.

Distance functions on digital pictures

Abstract This paper describes algorithms for computing various functions on a digital picture which depend on the distance to a given subset of the picture. The algorithms involve local operations which are performed repeatedly, “in parallel”, on every picture element and its immediate neighbors. Applications to the detection of “clusters” and “regularities” in a picture, and to the dissection of a region into “pieces”, are also described.

Tracking Groups of People

A computer vision system for tracking multiple people in relatively unconstrained environments is described. Tracking is performed at three levels of abstraction: regions, people, and groups. A novel, adaptive background subtraction method that combines color and gradient information is used to cope with shadows and unreliable color cues. People are tracked through mutual occlusions as they form groups and separate from one another. Strong use is made of color information to disambiguate occlusion and to provide qualitative estimates of depth ordering and position during occlusion. Simple interactions with objects can also be detected. The system is tested using both indoor and outdoor sequences. It is robust and should provide a useful mechanism for bootstrapping and reinitialization of tracking using more specific but less robust human models.

Robust regression methods for computer vision: a review

Regression analysis (fitting a model to noisy data) is a basic technique in computer vision, Robust regression methods that remain reliable in the presence of various types of noise are therefore of considerable importance. We review several robust estimation techniques and describe in detail the least-median-of-squares (LMedS) method. The method yields the correct result even when half of the data is severely corrupted. Its efficiency in the presence of Gaussian noise can be improved by complementing it with a weighted least-squares-based procedure. The high time-complexity of the LMedS algorithm can be reduced by a Monte Carlo type speed-up technique. We discuss the relationship of LMedS with the RANSAC paradigm and its limitations in the presence of noise corrupting all the data, and we compare its performance with the class of robust M-estimators. References to published applications of robust techniques in computer vision are also given.

Angle Detection on Digital Curves

A simple parallel procedure for selecting significant curvature maxima and minima on a digital curve is described.

Graph-Grammars and Their Application to Computer Science

Tutorial introduction to the algebraic approach of graph grammars.- May we introduce to you: Hyperedge replacement.- An introduction to parallel map generating systems.- Set theoretic approaches to graph grammars.- An introduction to the NLC way of rewriting graphs.- Array grammars.- Graph grammar based specification of interconnection structures for massively parallel computation.- Towards distributed graph grammars.- On partially ordered graph grammars.- A representation of graphs by algebraic expressions and its use for graph rewriting systems.- On context-free sets of graphs and their monadic second-order theory.- Restricting the complexity of regular DNLC languages.- Apex graph grammars.- Graph grammar engineering: A software specification method.- A linguistic formalism for engineering solid modeling.- Graph grammars and diagram editing.- Graphics and their grammars.- On network algebras and recursive equations.- Ada-concurrency specified by graph grammars.- Basic notions of actor grammars.- Embedding rule independent theory of graph grammars.- Supporting the software development process with attributed NLC graph grammars.- Practical applications of precedence graph grammars.- Is parallelism already concurrency? Part 1: Derivations in graph grammars.- Is parallelism already concurrency? Part 2: Non-sequential processes in graph grammars.- Map OL-systems with edge label control: Comparison of marker and cyclic systems.- From 0L and 1L map systems to indeterminate and determinate growth in plant morphogenesis.- Fundamentals of edge-label controlled graph grammars.- Parallelism analysis in rule-based systems using graph grammars.- An efficient algorithm for the solution of hierarchical networks of constraints.- A software development environment based on graph technology.- Map 0L systems with markers.- Graph rewriting with unification and composition.- Complexity of pattern generation via planar parallel binary fission/fusion grammars.- Applications of L-systems to computer imagery.- Advances in array languages.- Rosenfelds cycle grammars and kolam.- Application of graph grammars in music composing systems.- Boundary NLC and partition controlled graph grammars.

Segmentation and Estimation of Image Region Properties through Cooperative Hierarchial Computation

The task of segmenting an image and that of estimating properties of image regions may be highly interdependent. The goal of segmentation is to partition the image into regions with more or less homogeneous properties; but the processes which estimate these properties should be confined within individual regions. A cooperative, iterative approach to segmentation and property estimation is defined; the results of each process at a given iteration are used to adjust the other process at the next iteration. A linked pyramid structure provides a framework for this process iteration. This hierarchical structure ensures rapid convergence even with strictly local communication between pyramid nodes.