Gerald M. Flachs

Hand recognition by wavelet transforms and neural networks

A new approach to human hand recognition is presented. It combines concepts from image segmentation, contour representation, wavelet transforms, and neural networks. With this approach, people are distinguished by their hands. After obtaining a persons hand contour, each finger of the hand is located and separated based on its points of sharp curvature. A two dimensional (2-D) finger contour is then mapped to a one dimensional (1-D) functional representation of the boundary called a finger signature. The wavelet transform then decomposes the finger signature signal into lower resolutions retaining the most significant features. The energy at each stage of the decomposition is calculated to extract the features of each finger. A three layer artificial neural network with back propagation training is employed to measure the performance of the wavelet transform. A database consisting of five hand images obtained from twenty-eight different people is used in the experiment. Three of the images are used for training the neural network. The other two are used for testing the algorithm. Results presented illustrate high accuracy human recognition using this scheme.

Sensor fusion using K-nearest neighbor concepts

Sensor fusion using K—nearest neighbor conceptsDavid R. ScottNorthern Arizona University, Department of Electrical EngineeringBox 15600, Flagstaff, Arizona 86011Gerald N. Flachs and Patrick T. GaughanNew Mexico State University, Department of Electrical and Computer EngineeringBox 3—0, Las Cruces, New Mexico 88003ABSTRACTA new K—nearest neighbor (KNN) statistic is introduced to fuse information frommultiple sensors/features into a single dimensional decision space for electronicvision systems. Theorems establish the relationship of the KNN statistic to otherprobability density function distance measures such as the Kolmogorov—Smirnov Distanceand the Tie Statistic. A new KNN search algorithm is presented along with factors forselecting K. Applications include cueing and texture recognition.

Task Specific Complexity Metrics For Electronic Vision

This paper presents a mathematical basis for establishing achievable performance levels for multisensor electronic vision systems. A random process model of the multisensor scene environment is developed. The concept of feature space and its importance in the context of this model is presented. A set of complexity metrics used to measure the difficulty of an electronic vision task in a given scene environment is developed and presented. These metrics are based on the feature space used for the electronic vision task and the a priori knowledge of scene truth. Several applications of complexity metrics to the analysis of electronic vision systems are proposed.

Information Fusion Methodology

An approach is presented for designing multisensor electronic vision systems using information fusion concepts. A random process model of the multisensor scene environment provides a mathematical foundation for fusing information. A complexity metric is introduced to measure the level of difficulty associated with various vision tasks. This complexity metric provides a mathematical basis for fusing information and selecting features to minimize the complexity metric. A major result presented in the paper is a method for utilizing a priori knowledge to fuse an n-dimensional feature vector X = (X1, X2, ..., Xn) into a single feature Y while retaining the same complexity. A fusing theorem is presented that defines the class of fusing functions that retains the minimum complexity.

Multisensor image analysis system demonstration

A multisensor image analysis system that locates and recognizes realistic models of military objects placed on a terrain board has been demonstrated. Images are acquired using two overhead video sensors--a wide field, low resolution camera for cueing and a narrow field, high resolution camera for object segmentation and recognition. The red, green, and blue sensor information is fused and used in the digital image analysis. Small regions of interest located within the wide field-of-view scene by a high-speed digital cuer are automatically acquired and imaged by the high resolution camera. A high-speed statistical segmenter produces a binary image of any military object found within a given region and sends it to a computer-controlled binary phase-only optical correlator for recognition. Rotation, scale and aspect invariant recognition is accomplished using a binary tree search of composite binary phase-only filters. The system can reliably recognize any one of ten different objects placed at any location and orientation on the terrain board within ten seconds.

Wavelet transform application in human face recognition

A wavelet transformation is introduced as a new method to extract sideview face features in human face recognition. Utilizing the wavelet transformation, a sideview profile is decomposed as high frequency and low frequency components. Signal reconstruction, autocorrelation and energy distribution are used to decide a optimal decomposition level in the wavelet transformation without losing sideview features. To evaluate the feasibility of the wavelet transformation features in human sideview face recognition, the tie statistic is used to compute the complexity of the wavelet transform features. Using wavelet transformation, the sideview data size is reduced. The reduced features have almost the same ability as the original sideview face profile data in terms of distinguishing different people. The computational expense is greatly decreased. The results of the experiments are also shown in this paper.

Feature Selection and Decision Space Mapping for Sensor Fusion

An information fusion approach is presented for mapping a multiple dimensional feature space into a lower dimensional decision space with simplified decision boundaries. A new statistic, called the tie statistic, is used to perform the mapping by measuring differences in probability density functions of features. These features are then evaluated based on the separation of the decision classes using a parametric beta representation for the tie statistic. The feature evaluation and fusion methods are applied to perform texture recognition.

Statistical Segmentation Of Digital Images

Statistically based models of digital images are used to locate and segment objects of interest from background scenes. Three models are presented and evaluated. These models are based on a Bayesian cost function, a Neyman-Pearson constant false alarm rate function, and a maximum entropy function. Detailed algorithms are presented for separating object regions from background clutter using each of these statistical methods.

Fusion of multiple, coarse features from the face, hand and voice for reliable human identity determination

Currently, a number of systems for determining or verifying the identity of an individual have been developed that rely on a single, intricate identifying feature such as a fingerprint or the retina of an eye. The large amount of detail required for such systems generally complicates sensing and necessitates a certain amount of direct interaction with human users. Although current systems work reasonably well, it is advantageous to explore new techniques that reduce the amount of interaction required and minimize the possibility of deception. The development of a standoff (i.e., no physical contact) biometric identification system capable of quickly determining or verifying the identity of an individual with a low probability of error is described. The low probability of error is obtained by fusing coarse features remotely acquired from the face, hand and voice. Individually, these features provide inadequate error performance, however, complementary information obtained by fusing or combining the features in a higher dimensional feature space enables reliable identity determination. The use of coarse features simplifies the remote sensing requirements, reduces the computing power required for feature extraction and minimizes human interaction with the system. The simultaneous use of multiple features from multiple sensors lessens the possibility of deception. A description of the system is presented together with preliminary performance results.

Fuzzy approach to object recognition

Certain effective object recognition schemes involve the location of various distinguishing object components, extraction of component features, and the recognition based on these features. For certain classes of object recognition problems, a critical part is the automatic location of the object components. A common method for locating the object components involves the correlation of point to point or area to area. This correlation procedure can be relatively computationally expensive. This paper develops a fast, stable fuzzy approach for locating object components. The effectiveness of the approach is illustrated by an application to the human face recognition problem.