SASI: a generic texture descriptor for image retrieval

Abstract

In this paper, a generic texture descriptor, namely, Statistical Analysis of Structural Information (SASI) is introduced as a representation of texture. SASI is based on statistics of clique autocorrelation coefficients, calculated over structuring windows. SASI defines a set of clique windows to extract and measure various structural properties of texture by using a spatial multi-resolution method. Experimental results, performed on various image databases, indicate that SASI is more successful then the Gabor Filter descriptors in capturing small granularities and discontinuities such as sharp corners and abrupt changes. Due to the flexibility in designing the clique windows, SASI reaches higher average retrieval rates compared to Gabor Filter descriptors. However, the price of this performance is increased computational complexity.

Visual words dictionaries and fusion techniques for searching people through textual and visual attributes

“…These classifiers are learned using images from LFW database. We showed performance in line with recent attribute classifiers from the literature and important texture descriptors such as SASI (Çarkacıoglu and Yarman-Vural, 2003).…”

“…Finally, given a multiple-attribute query, we use some fusion methods to combine the outputs of the classifiers generating a reduced list of people complying with the describable attributes given by the user. With the visual dictionaries introduction, we achieve significant improvements on the results in comparison to the results obtained in the state of the art , our own prior work (Fabian et al, 2012), and also a top-performer texture descriptor in the literature (Çarkacıoglu and Yarman-Vural, 2003;Penatti et al, 2012).…”

“…In Table 2, we summarize the results obtained using Methods #2 and #3. In order to compare our methods with state of the art (Kumar et al, 2008), we also performed the Histograms of Oriented Gradient (HoG) description (which is the most common method used to represent visual attributes) as well as SASI (Çarkacıoglu and Yarman-Vural, 2003), one of the top-performers texture descriptors according to a recent survey (Penatti et al, 2012). Table 2 also brings such results.…”

Exposing Digital Image Forgeries from Near Duplicate Images

“…(SASI) [19] Algorithm for texture descriptor is used to extract texture information from IM. The main advantage of using SASI is its capability of capturing small granularities and discontinuities in texture pattern.…”

An Intelligent System for Aerial Image Retrieval and Classification

“…This is the retrieval of images on the basis of features automatically derived from the images themselves. The features most widely used are texture [1][2][3], color [4][5][6] and shape [7][8][9]. A plethora of texture features extraction algorithms exists, such as wavelets [10][11][12], mathematical morphology [13] and stochastic models [14], to mention few.…”