An approach to novelty detection applied to the classification of image regions

The proposed framework for novelty detection evaluates neural networks as adaptive classifiers that are capable of novelty detection and retraining on the basis of newly discovered information and applies this model to the application area of object recognition in video.

Abstract

We present a new framework for novelty detection. The framework evaluates neural networks as adaptive classifiers that are capable of novelty detection and retraining on the basis of newly discovered information. We apply our newly developed model to the application area of object recognition in video. We detail the tools and methods needed for novelty detection such that data from unknown classes can be reliably rejected without any a priori knowledge of its characteristics. The rejected data is postprocessed to determine which samples can be manually labeled of a new type and used for retraining. We compare the proposed framework with other novelty detection methods and discuss the results of adaptive retraining of neural network to recognize further unseen data containing the newly added objects.