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. © 2013 Springer-Verlag.
Information-based learning of deep architectures for feature extraction / Melacci, Stefano; Lippi, Marco; Gori, Marco; Maggini, Marco. - 8157:PART 2(2013), pp. 101-110. ((Intervento presentato al convegno 17th International Conference on Image Analysis and Processing, ICIAP 2013 tenutosi a Naples, ita nel 2013.
|Data di pubblicazione:||2013|
|Titolo:||Information-based learning of deep architectures for feature extraction|
|Autore/i:||Melacci, Stefano; Lippi, Marco; Gori, Marco; Maggini, Marco|
|Digital Object Identifier (DOI):||http://dx.doi.org/10.1007/978-3-642-41184-7_11|
|Nome del convegno:||17th International Conference on Image Analysis and Processing, ICIAP 2013|
|Luogo del convegno:||Naples, ita|
|Data del convegno:||2013|
|Citazione:||Information-based learning of deep architectures for feature extraction / Melacci, Stefano; Lippi, Marco; Gori, Marco; Maggini, Marco. - 8157:PART 2(2013), pp. 101-110. ((Intervento presentato al convegno 17th International Conference on Image Analysis and Processing, ICIAP 2013 tenutosi a Naples, ita nel 2013.|
|Tipologia||Relazione in Atti di Convegno|
I documenti presenti in Iris Unimore sono rilasciati con licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia, salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris