Showing papers on "Feature (machine learning) published in 1976"
TL;DR: A very brief survey of recent developments in basic pattern recognition and image processing techniques is presented.
Abstract: Extensive research and development has taken place over the last 20 years in the areas of pattern recognition and image processing. Areas to which these disciplines have been applied include business (e. g., character recognition), medicine (diagnosis, abnormality detection), automation (robot vision), military intelligence, communications (data compression, speech recognition), and many others. This paper presents a very brief survey of recent developments in basic pattern recognition and image processing techniques.
153 citations
TL;DR: The topics covered are: printed Chinese Character Recognition, on-line recognition, and formal models of the structure of Chinese characters and their application in computerized systems.
106 citations
TL;DR: A set of 11 distinctive features for hand configurations (Dez) in the American Sign Language of the deaf is proposed, based on the results of applying clustering and scaling analyses to confusion matrices for Dez identifications in visual noise.
90 citations
TL;DR: For instance, the authors found that recognition memory for male faces was tested following nine different kinds of judgments made when the face was studied. But it made no difference for recognition whether the face had been positively or negatively categorized when it was studied, and memory was poorest following questions about a particular physical feature, e.g., size of nose or straightness of hair, than when other kinds of questions were asked.
Abstract: Recognition memory for male faces was tested following nine different kinds of judgments made when the face was studied. Memory was poorest following questions about a particular physical feature, e.g., size of nose or straightness of hair, than when other kinds of questions were asked. In general, it made no difference for recognition whether the face had been positively or negatively categorized when it was studied.
69 citations
TL;DR: A new preprocessing method that has found considerable use for chemical applications is presented and features are selected that are useful for class discrimination, orthogonal, and at least in part, retain identity to the original measurements.
52 citations
Patent•
12 Apr 1976TL;DR: In this paper, a pattern recognition system is described in which, when more than two reference patterns having a similarity to the input unknown pattern larger than a predetermined threshold level are detected by a first discriminating circuit, one or more suitable feature comparators are selected from a plurality of feature comparator by the control signals corresponding to the reference patterns or the category of the detected patterns.
Abstract: In order to recognize confusable characters exactly, a pattern recognition system is described wherein, when more than two reference patterns having a similarity to the input unknown pattern larger than a predetermined threshold level are detected by a first discriminating circuit, one or more suitable feature comparators are selected from a plurality of feature comparators by the control signals corresponding to the reference patterns or the category thereof detected by the first discriminating circuit and the selected one or more feature comparators determine the identity of the input unknown pattern by comparing selected features thereof to the corresponding portions of the plural reference patterns under consideration.
43 citations
34 citations
TL;DR: It is argued that machine algorithms based on feature detection promise the greatest chance for success in the recognition of isolated, unconstrained handprinted characters.
34 citations
Patent•
26 Nov 1976TL;DR: In this paper, the Coker vocal tract model was used to find the position and direction of movement of the speaker's tongue body in order to determine the formant frequencies in the applied speech signal.
Abstract: A speech recognition system is realized by applying a speech signal to a feature extractor wherein a sequence of predetermined features representing the speech signal are determined, and by comparing the determined features, in an acceptor, to predetermined sequences of features which represent selected words. One attribute of the feature extractor is the ability to represent certain classes of sounds in terms of the position and direction of motion of the movable structures of a human vocal tract model, such as the position and direction of movement of the speaker's tongue body. The tongue body position is derived by determining the formant frequencies in the applied speech signal and by employing the Coker vocal tract model to find the tongue body position which best matches the determined formants.
28 citations
TL;DR: A parameterized structural representation system for this class of events is discussed and a variety of alternative approaches are considered in light of the potential combinatorial explosions which might arise in applications of these procedures.
19 citations
01 Dec 1976
TL;DR: The measured data from an unclassified textural pattern and the estimated data from the models are used to determine similarity measures and variances which provide the key toTextural pattern recognition by computer.
Abstract: A two-dimensional statistical model is proposed for the characterization of textural pattern, and a technique is introduced for textural pattern recognition by computer. The model building involves two major steps. The first step is the determination of a preliminary model from textural data. In the second step, the model is refined via parameter optimization. The refined model is used to characterize a pattern class. The measured data from an unclassified textural pattern and the estimated data from the models are used to determine similarity measures and variances which provide the key to textural pattern recognition by computer.
Patent•
28 May 1976
TL;DR: In this paper, a method and device for recognizing characters is presented, in which in a learning phase, as well as in a subsequent working phase features of character patterns in a number of aspects thereof are classified in a many of groups.
Abstract: Method and device for recognizing characters, in which in a learning phase, as well as in a subsequent working phase features of character patterns in a number of aspects thereof are classified in a number of groups. During the learning phase the results of these classifications are recorded in a store as statistic frequencies. During the working phase the result of the feature classification of a freshly offered character is utilized in determining, for each class of characters, (a) the probabilities of the features found in this character, and (b) the weight of the features of a character pattern to be recognized. The weight attributed to each feature depends upon the shape of the pattern, and upon the basis of the values of these weights, the features are selected. The stored statistic frequencies of the selected features are multiplied by the values of the weights, and the largest value among the results is utilized for indicating the class of the feature. Thus from the selected classes of features, the character is determined.
12 Apr 1976
TL;DR: A new modular speaker recognition system consisting of a st of real?time speech analysis processors and a pattern recognition software package is described, results of which are being discussed.
Abstract: Summary form only given, as follows. This paper describes a new modular speaker recognition system consisting of a st of real?time speech analysis processors and a pattern recognition software package. Within a government sponsored research project, combinations of different speech analysis procedures and different pattern recognition algorithms are compared in order to find optimal subsystems, to be applied to security systems or law enforcement, for given boundary conditions. In order to find the influence of different techniques, distance measures, quantisation band distortions on the recognition rate of given data base (2,500 utterances), a study has been carried out, results of which are being discussed.
01 Jan 1976
TL;DR: The classification process involves much less computational effort than the foregoing subprocesses which locate the candidate nodule in the lung fields of the radiograph and find its boundary and it used a nearest neighbor classification procedure due to Cover and Hart (1967).
Abstract: The classification process involves much less computational effort than the foregoing subprocesses which locate the candidate nodule in the lung fields of the radiograph and find its boundary. One can readily specify features to distinguish the different candidate nodule categories as simple functions of the nodule boundary, and great care has been taken to optimize this boundary. For this reason no exotic classification process was required and we used a nearest neighbor classification procedure due to Cover and Hart (1967).
01 Apr 1976
TL;DR: The recognition system of spoken words using the restricted number of learning samples is described, where a half of the twenty words to be recognized is used as learning samples and the recognition rate is obtained in the case of the optimum learning sample.
Abstract: The recognition system of spoken words using the restricted number of learning samples is described. The learning samples are composed of a part of the whole words to be recognized and are used to derive the reference patterns of phonemic spectrums needed in the recognition system. Four kinds of algorithms for selecting the optimum set of words constituting the learning samples are proposed and tested. Recognition test of twenty words is done for 20 speakers. By the use of a half of the twenty words as learning samples, the recognition rate of 98.6 % is obtained in the case of the optimum learning sample.
01 Apr 1976
TL;DR: The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system.
Abstract: The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system. The results compare favourably with those produced by a cluster-based minimal Euclidean distance technique, run over the identical training and test samples. The predicates used are similar to auditory receptive fields.
01 Jan 1976
TL;DR: The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system.
Abstract: : The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system. The results compare favorably with those produced by a cluster-based minimal Euclidean distance technique, run over the identical training and test samples. The predicates used are similar to auditory receptive fields.
20 Jan 1976
TL;DR: A review along with criticism of some recent work on nonparametric and sequential rules in statistical pattern recognition and some new results and directions for future work are discussed.
Abstract: : A review along with criticism of some recent work on nonparametric and sequential rules in statistical pattern recognition is given in this paper. Some new results and directions for future work are also discussed. (Author)
01 Apr 1976
TL;DR: A new successive procedure for obtaining a sequence of phonemic categories from acoustic speech signal and the advantages are discussed from the viewpoints of reliability and flexibility of pattern recognition techniques.
Abstract: This paper aims to report a new successive procedure for obtaining a sequence of phonemic categories from acoustic speech signal. The procedure is composed of three levels, i.e., enhancement and inhibition of speech spectra (preprocessing), local peak extraction (feature extraction), and processing of dynamic properties of the feature series (categorization). Each level is composed of multistage processes whose one stage consists of two or three computational steps. The principal features of this procedure are: (1) Formulations of contrast effect, assimilation effect and uncertainty relation between time and space. (2) Potential function defined for phonemic categories. (3) Lattice-like configuration of functional devices. (4) No feed back loop process and no back tracking algorithm. The feasibility of the procedure is verified by applying it to continuous vowels and words. The advantages are discussed from the viewpoints of reliability and flexibility of pattern recognition techniques.
01 Apr 1976
TL;DR: This paper presents the preliminary study of a new approach to Automatic Speech Recognition using Acoustic-Phonetic analysis and Statistical Pattern Recognition techniques.
Abstract: This paper presents the preliminary study of a new approach to Automatic Speech Recognition using Acoustic-Phonetic analysis and Statistical Pattern Recognition techniques. Implementation of an On-Line, Adaptive, Speaker-Independent Word Recognition System is also described to illustrate the approach.
[...]
TL;DR: Applications of pattern recognition include character recognition, target detection, medical diagnosis, analysis of biomedical signals and images, remote sensing, identification of human faces and fingerprints, reliability, speech recognition and understanding, and machine parts recognition.
Abstract: During the past fifteen years, there has been a considerable growth of interest in problems of pattern recognition. This interest has created an increasing need for theoretical methods and experimental software and hardware for use in the design of pattern recognition systems. A number of books have been published on this subject,1-16and some special pattern recognition machines have been designed and built for practical use. Applications of pattern recognition include character recognition,12target detection, medical diagnosis, analysis of biomedical signals and images, remote sensing, identification of human faces and fingerprints, reliability,17socio-economics,18speech recognition and understanding,19and machine parts recognition.
DOI•
01 May 1976
TL;DR: As a rule, in the construction of measurement equipment in a recognition system, a situation exists in which the quality of the measurement information is substantially defined by thequality of the given measurement device, characterized by the values of its basic parameters and depending on the cost of development of the device.
Abstract: As a rule, in the construction of measurement equipment in a recognition system, based practicaIly on arbitrary physical causes, a situation exists in which the quality of the measurement information (in particular, the probabili ty of determining the measured parameter) is substantially defined by the quality of the given measurement device, characterized by the values of its basic parameters and depending in the general case on the cost of development of the device.
01 Jan 1976
TL;DR: In some pattern recognition problems, the recognition process includes not only the capability of assigning the pattern to a particular class (to classify it), but also the capacity to describe aspects of the pattern which make it ineligible for assignment to another class.
Abstract: The many different pattern recognition methods may be grouped into two general approaches; namely, the decision-theoretic (or discriminant) approach and the syntactic (or structural) approach. In the decision-theoretic approach, a set of characteristic measurements, called features, are extracted from the patterns; the recognition of each pattern (assignment to a pattern class) is usually made by partitioning the feature space. Most of the developments in pattern recognition research during the past decade deals with the decision-theoretic approach and its applications [1–11]. In some pattern recognition problems, the structural information which describes each pattern is important, and the recognition process includes not only the capability of assigning the pattern to a particular class (to classify it), but also the capacity to describe aspects of the pattern which make it ineligible for assignment to another class. A typical example of this class of recognition problem is picture recognition or more generally speaking, scene analysis. In this class of recognition problems, the patterns under consideration are usually quite complex and the number of features required is often very large which makes the idea of describing a complex pattern in terms of a (hierarchical) composition of simpler subpatterns very attractive. Also, when the patterns are complex and the number of possible descriptions is very large it is impractical to regard each description as defining a class (for example in fingerprint and face identification problems, recognition of continuous speech, Chinese characters, etc.). Consequently, the requirement of recognition can only be satisfied by a description for each pattern rather than the simple task of classification.