Issue No. 09 - September (1994 vol. 16)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.310684
<p>Recent work in feature-based classification has focused on nonparametric techniques that can classify instances even when the underlying feature distributions are unknown. The inference algorithms for training these techniques, however, are designed to maximize the accuracy of the classifier, with all errors weighted equally. In many applications, certain errors are far more costly than others, and the need arises for nonparametric classification techniques that can be trained to optimize task-specific cost functions. This correspondence reviews the linear machine decision tree (LMDT) algorithm for inducing multivariate decision trees, and shows how LMDT can be altered to induce decision trees that minimize arbitrary misclassification cost functions (MCF's). Demonstrations of pixel classification in outdoor scenes show how MCF's can optimize the performance of embedded classifiers within the context of larger image understanding systems.</p>
pattern recognition; inference mechanisms; decision theory; trees (mathematics); learning systems; computer vision; goal-directed classification; linear machine decision trees; feature-based classification; inference algorithms; nonparametric classification; linear machine decision tree; multivariate decision tree induction; misclassification cost functions; pixel classification; image understanding systems
P. Utgoff, B. Draper and C. Brodley, "Goal-Directed Classification Using Linear Machine Decision Trees," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 16, no. , pp. 888-893, 1994.