On Functional Relation between Recognition Error and Class-Selective Reject
نویسنده
چکیده
This report reviews various optimum decision rules for pattern recognition, namely, Bayes rule, Chow's rule (optimum error-reject tradeo ), and a recently proposed class-selective rejection rule. The latter provides an optimum tradeo between the error rate and the average number of (selected) classes. A new general relation between the error rate and the average number of classes is presented. The error rate can directly be computed from the class-selective reject function, which in turn can be estimated from unlabelled patterns, by simply counting the rejects. Theoretical as well as practical implications are discussed and some future research directions are proposed. CR
منابع مشابه
An Experimental Study of the Optimal Class-Selective Rejection Rule
This report reviews various class-selective rejection rules for pattern recognition. A rejection rule is called class-selective if it does not reject an ambiguous pattern from all classes but only from those classes that are most unlikely to issue the pattern. Both optimal and suboptimal rules, e.g. top-n ranking, are considered. Experimental comparisons performed on the recognition of isolated...
متن کاملThe interaction between classification and reject performance for distance-based reject-option classifiers
Consider the class of problems in which a target class is well defined, and an outlier class is ill-defined. In these cases new outlier classes can appear, or the classconditional distribution of the outlier class itself may be poorly sampled. A strategy to deal with this problem involves a two-stage classifier, in which one stage is designed to perform discrimination between known classes, and...
متن کاملA unified view of class-selection with probabilistic classifiers
The possibility of selecting a subset of classes instead of one unique class for assignation is of great interest in many decision making systems. Selecting a subset of classes instead of singleton allows to reduce the error rate and to propose a reduced set to another classifier or an expert. This second step provides additional information, and therefore increases the quality of the result. I...
متن کاملMultiple Reject Thresholds for Improving Classification Reliability
In pattern recognition systems, Chow’s rule is commonly used to reach a trade-off between error and reject probabilities. In this paper, we investigate the effects of estimate errors affecting the a posteriori probabilities on the optimality of Chow’s rule. We show that the optimal error-reject tradeoff is not provided by Chow’s rule if the a posteriori probabilities are affected by errors. The...
متن کاملVoice-based Age and Gender Recognition using Training Generative Sparse Model
Abstract: Gender recognition and age detection are important problems in telephone speech processing to investigate the identity of an individual using voice characteristics. In this paper a new gender and age recognition system is introduced based on generative incoherent models learned using sparse non-negative matrix factorization and atom correction post-processing method. Similar to genera...
متن کامل