We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Reduced Scattering Representation for Malayalam Character Recognition.
- Authors
Manjusha, K.; Anand Kumar, M.; Soman, K. P.
- Abstract
Scattering convolution network generates stable feature representation by applying a sequence wavelet decomposition operation on input signals. The feature representation in higher layers of the network builds a large-dimensional feature vector, which is often undesirable in most of the applications. Dimension reduction techniques can be applied on these higher-dimensional feature descriptors to produce an informative representation. In this paper, singular value decomposition is applied to the higher-layer scattering representation to generate informative feature descriptors. The effectiveness of the reduced scattering representation is evaluated on Malayalam printed and handwritten character recognition using support vector machine classifier. The reduced scattering representation improves the recognition performance when combining with lower-layer scattering network features.
- Subjects
PATTERN recognition systems; WAVELET transforms; SUPPORT vector machines
- Publication
Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ), 2018, Vol 43, Issue 8, p4315
- ISSN
2193-567X
- Publication type
Article
- DOI
10.1007/s13369-017-2945-9