DIMENSIONALITY REDUCTION and FEATURE SELECTION IN HYPERSPECTRAL IMAGE CLASSIFICATION
- π€ Speaker: Joel Trussell, North Carolina State University
- π Date & Time: Thursday 09 August 2007, 13:00 - 14:30
- π Venue: LR6, Engineering, Department of
Abstract
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.
Series This talk is part of the Probabilistic Systems, Information, and Inference Group Seminars series.
Included in Lists
- All Talks (aka the CURE list)
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge talks
- Cambridge University Engineering Department 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
- ndk22's list
- ob366-ai4er
- Probabilistic Systems, Information, and Inference Group Seminars
- rp587
- School of Technology
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)


Thursday 09 August 2007, 13:00-14:30