DIMENSIONALITY REDUCTION and FEATURE SELECTION IN HYPERSPECTRAL IMAGE CLASSIFICATION

Add to your list(s) Download to your calendar using vCal

• Joel Trussell, North Carolina State University
• Thursday 09 August 2007, 13:00-14:30
• LR6, Engineering, Department of.

If you have a question about this talk, please contact Taylan Cemgil.

Hyperspectral images provide a vast amount of information about a scene. However, much of that information is redundant as the bands are highly correlated. For computational and data compression reasons, it is desired to reduce the dimensionality of the data set while maintaining good performance in image analysis tasks. We present a method of dimensionality reduction based on neural networks that uses a novel penalty function to successfully reduce the number of active neurons, which corresponds to the dimensionality of the data for the task of interest. This method can be extended to select the best features from an arbitrary feature set, where “best” is defined in terms of reduction of the number of features while maintaining a desired level of classification performance.

This talk is part of the Signal Processing and Communications Lab Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• LR6, Engineering, Department of
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.