Feature extraction is a crucial phase in complex computer vision systems. Mainly two different approaches have been proposed so far. A quite common solution is the design of appropriate filters and features based on image processing techniques, such as the SIFT descriptors. On the other hand, machine learning techniques can be applied, relying on their capabilities to automatically develop optimal processing schemes from a significant set of training examples. Recently, deep neural networks and convolutional neural networks have been shown to yield promising results in many computer vision tasks, such as object detection and recognition. This paper introduces a new computer vision deep architecture model for the hierarchical extraction of pixel-based features, that naturally embed scale and rotation invariances. Hence, the proposed feature extraction process combines the two mentioned approaches, by merging design criteria derived from image processing tools with a learning algorithm able to extract structured feature representations from data. In particular, the learning algorithm is based on information-theoretic principles and it is able to develop invariant features from unsupervised examples. Preliminary experimental results on image classification support this new challenging research direction, when compared with other deep architectures models.

Melacci, S., Lippi, M., Gori, M., Maggini, M. (2013). Information-Based Learning of Deep Architectures for Feature Extraction. In Image Analysis and Processing - ICIAP 2013 (pp.101-110). SPRINGER-VERLAG [10.1007/978-3-642-41184-7_11].

Information-Based Learning of Deep Architectures for Feature Extraction

MELACCI, STEFANO;LIPPI, MARCO;GORI, MARCO;MAGGINI, MARCO
2013-01-01

Abstract

Feature extraction is a crucial phase in complex computer vision systems. Mainly two different approaches have been proposed so far. A quite common solution is the design of appropriate filters and features based on image processing techniques, such as the SIFT descriptors. On the other hand, machine learning techniques can be applied, relying on their capabilities to automatically develop optimal processing schemes from a significant set of training examples. Recently, deep neural networks and convolutional neural networks have been shown to yield promising results in many computer vision tasks, such as object detection and recognition. This paper introduces a new computer vision deep architecture model for the hierarchical extraction of pixel-based features, that naturally embed scale and rotation invariances. Hence, the proposed feature extraction process combines the two mentioned approaches, by merging design criteria derived from image processing tools with a learning algorithm able to extract structured feature representations from data. In particular, the learning algorithm is based on information-theoretic principles and it is able to develop invariant features from unsupervised examples. Preliminary experimental results on image classification support this new challenging research direction, when compared with other deep architectures models.
978-3-642-41184-7
978-3-642-41183-0
Melacci, S., Lippi, M., Gori, M., Maggini, M. (2013). Information-Based Learning of Deep Architectures for Feature Extraction. In Image Analysis and Processing - ICIAP 2013 (pp.101-110). SPRINGER-VERLAG [10.1007/978-3-642-41184-7_11].
File in questo prodotto:
File Dimensione Formato  
ICIAP2013.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.6 MB
Formato Adobe PDF
1.6 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/47106
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo