Institutions | About Us | Help | Gaeilge
rian logo

Go Back
Learning midlevel image features for natural scene and texture classification
Le Borgne, Hervé; Guérin-Dugué, Anne; O'Connor, Noel E.
This paper deals with coding of natural scenes in order to extract semantic information. We present a new scheme to project natural scenes onto a basis in which each dimension encodes statistically independent information. Basis extraction is performed by independent component analysis (ICA) applied to image patches culled from natural scenes. The study of the resulting coding units (coding filters) extracted from well-chosen categories of images shows that they adapt and respond selectively to discriminant features in natural scenes. Given this basis, we define global and local image signatures relying on the maximal activity of filters on the input image. Locally, the construction of the signature takes into account the spatial distribution of the maximal responses within the image. We propose a criterion to reduce the size of the space of representation for faster computation. The proposed approach is tested in the context of texture classification (111 classes), as well as natural scenes classification (11 categories, 2037 images). Using a common protocol, the other commonly used descriptors have at most 47.7% accuracy on average while our method obtains performances of up to 63.8%. We show that this advantage does not depend on the size of the signature and demonstrate the efficiency of the proposed criterion to select ICA filters and reduce the dimension
Keyword(s): Information retrieval; Image processing; feature extraction; filtering theory; image classification; image coding; image texture; independent component analysis; natural scenes
Publication Date:
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Le Borgne, Hervé ORCID: 0000-0003-0520-8436 <>, Guérin-Dugué, Anne and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 <> (2007) Learning midlevel image features for natural scene and texture classification. IEEE Transactions on Circuits and Systems for Video Technology, 17 (3). pp. 286-297. ISSN 1051-8215
Publisher(s): Institute of Electrical and Electronics Engineers
File Format(s): application/pdf
Related Link(s):,
First Indexed: 2009-11-05 02:00:27 Last Updated: 2019-02-09 07:04:45