Gabor transforms and neural networks for automatic target recognition
Conference
·
OSTI ID:5829377
We are interested in training neural networks to recognize objects in images. An important part of this task is to make the overall system robust with respect to image variations, including rotation, scale, and translation. This paper addresses two major issues associated with feature extraction for this problem; Selection of meaningful features, and data compression. Selection of meaningful features: Even though neural networks are very effective and robust pattern classifiers, they have an important limitation; for any given application, we cannot always explain why they succeeded or why they failed. The black box'' nature of the neural networks makes it difficult to analyze their internal states. Also, their performance is highly dependent on the training data. Our approach, therefore, is to create feature vectors that contain information that is as meaningful as possible. This paper describes the use of Gabor representations to generate feature vectors that are robust to variations in rotation, scaling, and translation. We are also studying ways to make the system robust to variations in perspective, occlusion, contrast, noise, and background. Gabor filters when used as the receptive field in a hierarchical scheme for feature extraction, offer properties that make them promising for providing the desired robustness to image variations. Unlike other filters, Gabor filters are optimally localized in both the space domain and the frequency domain, so that their space-bandwidth product is minimum. It has been shown that their properties of spatial localization, orientation selectivity, and spatial frequency selectivity make Gabor filters a good model for biological vision. This paper describes experiments in which we demonstrate the ability of the overall recognition system to classify objects in simulated scenes, even though they have undergone variations in orientation scale, and position.
- Research Organization:
- Lawrence Livermore National Lab., CA (USA)
- Sponsoring Organization:
- DOE; USDOE, Washington, DC (USA)
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 5829377
- Report Number(s):
- UCRL-JC-105362; CONF-910217--1; ON: DE91011919
- Country of Publication:
- United States
- Language:
- English
Similar Records
Texture segmentation by clustering of Gabor feature vectors
Intelligent robots and computer vision XII: Algorithms and techniques; Proceedings of the Meeting, Boston, MA, Sept. 7-9, 1993
Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers
Conference
·
Mon Dec 31 23:00:00 EST 1990
·
OSTI ID:5903298
Intelligent robots and computer vision XII: Algorithms and techniques; Proceedings of the Meeting, Boston, MA, Sept. 7-9, 1993
Conference
·
Thu Dec 31 23:00:00 EST 1992
·
OSTI ID:5598994
Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers
Technical Report
·
Fri Oct 01 00:00:00 EDT 2021
·
OSTI ID:1823733