One of the major issues in novelty detection for video and image analysis application is how to recognize objects that are not in full view. As the camera pans, tilts and zooms, image objects within a scene are never in full view and enter and exit image frames with time. These objects with partial view do not contain enough number of pixels that can generate robust color, texture and statistical features, and therefore result in classification samples that are often not representative of that class, e.g. outliers. From a data analysis point of view, it is impossible to known which samples are truly outliers because of partial view as opposed to outliers because of mistakes in object labeling. This can cause serious problems in novelty detection tasks using neural networks. In this paper we propose a novel methodology for automatically detecting image objects with partial view and discuss how to use this knowledge to improve novelty detection results.

This paper proposes a new model of "novelty detection" for image sequence analysis using neural networks. This model uses the concept of artificially generated negative data to form closed decision boundaries using a multilayer perceptron. The neural network output is novelty filtered by thresholding the output of multiple networks (one per known class) to which the sample is input and clustered for determining which clusters represent novel classes. After labeling these novel clusters, new networks are trained on this data. We perform experiments with video-based image sequence data containing a number of novel classes. The performance of the novelty filter is evaluated using two performance metrics and we compare our proposed model on the basis of these with five baseline novelty detectors. We also discuss the results of retraining each model after novelty detection. On the basis of Chi-square performance metric, we prove at 5 percent significance level that our optimized novelty detector performs at the same level as an ideal novelty detector that does not make any mistakes.

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.

In this paper we compare four classification techniques for classifying texture data of various natural objects found in forward-looking infrared (FLIR) images. The techniques compared include linear discriminant analysis, mean classifier and two different models of k-nearest neighbour methods. Hermite functions are used for texture feature extraction from segmented regions of interest in natural scenes taken as a video sequence. A total of 2680 samples for a total of twelve different classes are used for object recognition. The results on correctly identifying twelve natural objects in scenes are compared across the four classifiers on both unnormalised and normalised data. On unnormalised data, the average best recognition rate obtained using a ten fold cross-validation is 96.5%, and on unnormalised data it is 86.1% with a single nearest neighbour technique.

In this paper we apply artificial neural networks for classifying texture data of various natural objects found in FLIR images. Hermite functions are used for texture feature extraction from segmented regions of interest in natural scenes taken as a video sequence. A total of 2680 samples for a total of twelve different classes are used for object recognition. The results on correctly identifying twelve natural objects in scenes are compared across ten folds of the cross-validation study. Neural networks are found to be extremely effective in robust classification of our data giving an average recognition rate of 91.8%.