AFIT neural network research

A brief summary of research done at the Air Force Institute of Technology (AFIT) in the area of neural networks is provided. It has been shown that backpropagation, used for feedforward artificial neural networks, is just a degenerate version of an extended Kalman filter, and that networks can do about as well as the optimum statistical classification technique. A method of finding the importance of features for use by a neural network classifier has been determined. Techniques for using neural networks for image segmentation have been developed. In optical pattern recognition, techniques that allow the processing of real FLIR (forward-looking infrared) images with existing binary spatial light modulators have been devised. An optical direction of arrival detector applicable to laser illumination direction determination has been designed and tested; the design is similar to a fly's eye. Coated mirrors for the optical confocal Fabry-Perot interferometer have been designed, specified, fabricated, and installed. Significant progress has been made in the use of neural networks for processing multiple-feature sets for speech recognition     

A wavelet multiresolution analysis for spatio-temporal signals

The wavelet filters of the conventional 3D multiresolution analysis possess homogeneous spatial and temporal frequency characteristics which limits one's ability to match filter frequency characteristics to signal frequency behavior. Also, the conventional 3D multiresolution analysis employs an oct-tree decomposition structure which restricts the analysis of signal details to identical resolutions in space and time. This paper presents a 3D wavelet multiresolution analysis constructed from nonhomogeneous spatial and temporal filters, and an orthogonal sub-band coding scheme that decouples the spatial and temporal decomposition processes     

Spatio-temporal pattern recognition using hidden Markov models

A spatio-temporal method for identifying objects contained in an image sequence is presented. The Hidden Markov Model (HMM) technique is used as the classification algorithm, making classification decisions based on a spatio-temporal sequence of observed object features. A five class problem is considered. Classification accuracies of 100% and 99.7%, are obtained for sequences of images generated over two separate regions of viewing positions. HMMs trained on image sequences of the objects moving in opposite directions showed a 98.1% successful classification rate by class and direction of movement. The HMM technique proved robust to image corruption with additive correlated noise and had a higher accuracy than a single-look nearest neighbor method. A real image sequence of one of the objects used was successfully recognized with the HMMs trained on synthetic data. This study shows the temporal changes that observed feature vectors undergo due to object motion hold information that can yield superior classification accuracy when compared with single-frame techniques