# IEEE Transactions on Pattern Analysis and Machine Intelligence

## Filter Results

Displaying Results 1 - 14 of 14
• ### Design of supervised classifiers using Boolean neural networks

Publication Year: 1995, Page(s):1239 - 1246
Cited by:  Papers (23)
| |PDF (752 KB)

In this paper we present two supervised pattern classifiers designed using Boolean neural networks. They are: 1) nearest-to-an-exemplar classifier; and 2) Boolean k-nearest neighbor classifier. The emphasis during the design of these classifiers was on simplicity, robustness, and the ease of hardware implementation. The classifiers use the idea of radius of attraction to achieve their goal. Mathem... View full abstract»

• ### A knowledge-based approach for script recognition without training

Publication Year: 1995, Page(s):1233 - 1239
Cited by:  Papers (3)
| |PDF (868 KB)

The approach described is based on an empirical parametric model for the handwriting recognition system. The parameters are so chosen and quantized as to retain only broad shape information, ignoring writer-dependent and other variability. Concatenation of character prototypes generates archetypal reference words for recognition, and training is unnecessary. The recognition scores exceed 90% View full abstract»

• ### Nonparametric segmentation of curves into various representations

Publication Year: 1995, Page(s):1140 - 1153
Cited by:  Papers (104)  |  Patents (14)
| |PDF (1508 KB)

This paper describes and demonstrates the operation and performance of an algorithm for segmenting connected points into a combination of representations such as lines, circular, elliptical and superelliptical arcs, and polynomials. The algorithm has a number of interesting properties including being scale invariant, nonparametric, general purpose, and efficient View full abstract»

• ### Optic flow field segmentation and motion estimation using a robust genetic partitioning algorithm

Publication Year: 1995, Page(s):1177 - 1190
Cited by:  Papers (38)
| |PDF (1612 KB)

Optic flow motion analysis represents an important family of visual information processing techniques in computer vision. Segmenting an optic flow field into coherent motion groups and estimating each underlying motion is a very challenging task when the optic flow field is projected from a scene of several independently moving objects. The problem is further complicated if the optic flow data are... View full abstract»

• ### Performance analysis of stereo, vergence, and focus as depth cues for active vision

Publication Year: 1995, Page(s):1213 - 1219
Cited by:  Papers (26)
| |PDF (1252 KB)

This paper compares the performances of the binocular cues of stereo and vergence, and the monocular cue of focus for range estimation using an active vision system. The performance of each cue is characterized in terms of sensitivity to errors in the imaging parameters. The effects of random, quantization errors are expressed in terms of the standard deviation of the resulting depth error. The ef... View full abstract»

• ### Extraction of 3D object features from CAD boundary representation using the super relation graph method

Publication Year: 1995, Page(s):1228 - 1233
Cited by:  Papers (12)  |  Patents (1)
| |PDF (700 KB)

This paper presents the super relation graph (SRG) method for extracting prismatic features from the CAD boundary representation of a machined part. Using the definition of super relations and the validity of a feature volume, this method recognizes features with all three types of interactions: face splitting, face merging, and edge truncation View full abstract»

• ### Symmetry as a continuous feature

Publication Year: 1995, Page(s):1154 - 1166
Cited by:  Papers (177)  |  Patents (3)
| |PDF (1484 KB)

Symmetry is treated as a continuous feature and a continuous measure of distance from symmetry in shapes is defined. The symmetry distance (SD) of a shape is defined to be the minimum mean squared distance required to move points of the original shape in order to obtain a symmetrical shape. This general definition of a symmetry measure enables a comparison of the “amount” of symmetry o... View full abstract»

• ### Goal-directed evaluation of binarization methods

Publication Year: 1995, Page(s):1191 - 1201
Cited by:  Papers (323)  |  Patents (31)
| |PDF (1392 KB)

This paper presents a methodology for evaluation of low-level image analysis methods, using binarization (two-level thresholding) as an example. Binarization of scanned gray scale images is the first step in most document image analysis systems. Selection of an appropriate binarization method for an input image domain is a difficult problem. Typically, a human expert evaluates the binarized images... View full abstract»

• ### On the estimation of rigid body rotation from noisy data

Publication Year: 1995, Page(s):1219 - 1220
Cited by:  Papers (24)
| |PDF (204 KB)

We derive an exact solution to the problem of estimating the rotation of a rigid body from noisy 3D image data. Our approach is based on total least squares (TLS), but unlike previous work involving TLS, we include the constraint that the transformation matrix should be orthonormal. It turns out that the solution to the estimation problem has the same form as if the data are not noisy, and thus th... View full abstract»

• ### Estimating motion and structure from correspondences of line segments between two perspective images

Publication Year: 1995, Page(s):1129 - 1139
Cited by:  Papers (47)  |  Patents (1)
| |PDF (1300 KB)

Presents an algorithm for determining 3D motion and structure from correspondences of line segments between two perspective images. To the author's knowledge, this paper is the first investigation of use of line segments in motion and structure from motion. Classical methods use their geometric abstraction, namely straight lines, but then three images are necessary for the motion and structure det... View full abstract»

• ### Extending the feature vector for automatic face recognition

Publication Year: 1995, Page(s):1167 - 1176
Cited by:  Papers (43)
| |PDF (1228 KB)

Many features can be used to describe a human face but few have been used in combination. Extending the feature vector using orthogonal sets of measurements can reduce the variance of a matching measure, to improve discrimination capability. This paper investigates how different features can be used for discrimination, alone or when integrated into an extended feature vector. This study concentrat... View full abstract»

• ### On the estimation of small' probabilities by leaving-one-out

Publication Year: 1995, Page(s):1202 - 1212
Cited by:  Papers (31)
| |PDF (1212 KB)

We apply the leaving-one-out concept to the estimation of small' probabilities, i.e., the case where the number of training samples is much smaller than the number of possible classes. After deriving the Turing-Good formula in this framework, we introduce several specific models in order to avoid the problems of the original Turing-Good formula. These models are the constrained model, the absolut... View full abstract»

• ### Uniqueness of 3D pose under weak perspective: a geometrical proof

Publication Year: 1995, Page(s):1220 - 1221
Cited by:  Papers (8)  |  Patents (6)
| |PDF (192 KB)

We present a purely geometrical proof that under the weak perspective model, the 3D pose of a 3-point configuration is determined uniquely up to a reflection by its 2D projection View full abstract»

• ### Motion and structure of four points from one motion of a stereo rig with unknown extrinsic parameters

Publication Year: 1995, Page(s):1222 - 1227
Cited by:  Papers (17)
| |PDF (648 KB)

We describe an analytical method for recovering 3D motion and structure of four or more points from one motion of a stereo rig. The extrinsic parameters are unknown. The motion of the stereo rig is also unknown. Because of the exploitation of information redundancy, the approach gains over the traditional “motion and structure from motion” approach in that less features and less motion... View full abstract»

## Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

## Meet Our Editors

Editor-in-Chief
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu