Showing papers in "Pattern Recognition in 1977"

TL;DR: Two error measures, the percentage area misclassified and a new pixel distance error, were defined and evaluated in terms of their correlation with human observation for comparison of multiple segmentations of the same scene and multiple scenes segmented by the same technique.

TL;DR: Algorithms are described for extracting critical points of shape description in the presence of noise and an illustration is given showing how the critical points may be used in the development of a shape description system.

TL;DR: A method is presented for the machine recognition of constrained, hand printed Devanagari characters, where each stage of decision making narrows down the choice regarding the class membership of the input token.

TL;DR: A system of computer algorithms that finds the rib cage in chest radiographs by linking the dorsal and ventral portions of the rib contours such that each rib is identified and can be displayed individually.

TL;DR: Two modifications of the Duda-Hart procedure which compensate for noise are presented, applicable when the distribution of the noise is known and the other can be used when it is not.

TL;DR: A 4-dimensional histogram is computed to reduce the large LANDSAT pixel data to the much smaller number of distinct vectors and their frequency of occurrence in the scene, using the histogram count as a probability density estimate.

TL;DR: Pigeons learn no more of the visual projections of a three dimensional object than of an abstract object, and they lack the capacity to integrate the transformations of perspective.

TL;DR: The curvature chain is used to detect indentations in the boundary and it can be freed of noise (smoothed) by convolving it with a rectangular filter, once (the Freeman operation), twice (the Gallus operation) or more times.

TL;DR: An algorithm is developed for the design of an efficient decision tree with application to the pattern recognition problems involving discrete variables by defining a criterion to estimate the minimum expected cost of a tree in terms of the weights of its terminal nodes and costs of the measurements.

TL;DR: A method for recognizing both the three-dimensional pattern and the size of objects by grasping them with multijointed fingers equipped with tactile sensors, which shows that the most useful discriminant function is a linear one.

TL;DR: A pattern recognition system for the analysis of human sleep stages using the EEG data is presented and it is implemented in hardware for real-time applications.

TL;DR: An efficient method to determine the required camera offset parameters and a relatively fast calibration procedure are given.

TL;DR: In an attempt to provide a nonparametric estimator which not only uses the data efficiently but is also essentially an unbiased estimator of the probability of misclassification, Toussaint evaluated empirically an estimator formed by weighting the resubstitution and rotation estimators.

TL;DR: This new method is based on the prediction in parallel of the output residual and of discriminant functions, thus yielding a predictive state classification into overall degradation classes, and has been implemented in the engine maintenance department of an airline.

TL;DR: A procedure based on a multichannel system of epoch filters for recognizing the pulses of glottal chord vibrations by an analysis of the speech waveform by a stochastic finite state automaton.

TL;DR: A critical review of two measurement methods used so far for the evaluation of print quality parameters is given and the development of an automatic measurement device which is described in detail is described.

TL;DR: The lower bound on the probability of correct classification is a monotonically increasing function of the Mahalanobis distance for all monotonic ellipsoidally symmetric forms.

TL;DR: This paper derives a form of Parzen estimator which uses a data dependent smoothing matrix and a Gaussian weighting function and it is established that the estimator is asymptotically consistent.

TL;DR: By re-assembling the extracted components, a cleaned-up low-entropy frequency-time picture of the signal is produced which shows more structure and which is much more amenable to automatic analysis than the original spectrogram.

TL;DR: In this article, the authors proposed a multiple regression analysis (MRA) method for regression analysis, which is based on multiple regression with multiple regressions (MR) and multiple regression models (MRMs).

TL;DR: An attempt for a world model driven recognition process of two dimensional visual patterns is presented, in a form of a lattice-like structure, to recognize objects by partial information, because of the lattice property.

TL;DR: It is shown that the sensitivity of the pattern recognition functions to pattern perturbation can be a priori controlled and two new solutions are given.

TL;DR: A theorem is presented to obtain the changes in the eigenvalues and eigenvectors of matrices of the form S 2 −1 S 1 when there are changes of first order of smallness in the real symmetric matrices S i, i = 1, 2.

TL;DR: A supervised discriminant mixed integer programming algorithm (DISMIP) is described which achieves either linear or non-linear separation, without assuming any specific probability distribution, which offers greater flexibility in dealing with problems of multi-spectral classification.

TL;DR: Computer simulation is used to compare selected pattern recognition functions with two new recognition functions introduced in a recent predecessor article, focusing on the classical minimum distance recognition functions.

TL;DR: It turns out that the human visual system is superior in recognizing handprinted characters and inferior in the case of single font characters with additive noise.

TL;DR: It is shown that, if the number of invariants within the power spectrum of a one-dimensional transformation is an affine function of the transformation order, the numberof invariants is a quadratic function of that order in the case of two-dimensional transformations.