Perceptive visual texture classification and retrieval

Battiato, Sebastiano; Gallo, Giovanni; Nicotra, S.

doi:10.1109/iciap.2003.1234103

Cited by 23 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is quite costly to obtain, all in all difficult to use, but it does help the user in finding images with many buildings on them. Directionality vertical: This feature originally proposed in [10] seeks to characterize images by the main direction of lines in the image. Images with a strong vertical directionality contain many items such as flagposts and the like.…”

Section: Our Vfs Prototypementioning

confidence: 99%

Visualflamenco: Dependable, interactive image browsing based on visual properties

Müller

Zech

Henrich

et al. 2008

2008 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

Faceted search as a method for exploratory search is a search interface technique for Boolean retrieval that provides a good compromise between the wish to guide the user and the need to give freedom to the user. Both, guidance and freedom are needed in order to enable him (or her) to accomplish his search goal as quickly and efficiently as possible. The search goal can be both, to retrieve a target image (lookup search) or to get an overview of a collection as the basis for accomplishing complex search tasks (exploratory search).VisualFlamenco is about bringing content-based image retrieval and faceted search together. While there is some preexisting work towards faceted search based on automatically extracted metadata, the base innovation of our work is to visualize the meaning of facets and let the user pick visualized facets directly.The main point is this research is to give the user the right expectations about what the system can achieve. We see this as a step towards dependable multimedia search, search interfaces that do not promise more than they can achieve. A mismatch of expectations and possibilities has been denoted by some as one of the main problems in current research about multimedia search.Within this paper we present a visual faceted search tool that seeks to provide dependable image search. We describe its base idea, the features used, as well as user experiments done using the system.

show abstract

Section: Our Vfs Prototypementioning

confidence: 99%

Visualflamenco: Dependable, interactive image browsing based on visual properties

Müller

Zech

Henrich

et al. 2008

2008 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

show abstract

“…The latter in fact turn out to be redundant and not more discriminating than the former. The second one has been proposed by Battiato (Battiato et al, 2003) that gives a different definition of the same texture features of Tamura. The last one has been proposed by Haralick (Haralick, 1979) and we consider in particular three features among the fourteen defined: contrast, energy and entropy.…”

Section: Three Basic Statistical Descriptorsmentioning

confidence: 99%

“…From this it's possible to extract characteristics or features that allow the actual image texture characterization, by means of an adequate mathematical formulation. In this experimental analysis we compare three types of statistical descriptors that define, although in a different way, the same features: coarseness, contrast and directionality according to Battiato's (Battiato et al, 2003) and Tamura's (Tamura et al, 1978) definitions and contrast, energy and entropy making use the co-occurrence matrices as defined by Haralick (Haralick, 1979). The analysis is achieved in two different phases: in the first one there is the features extraction through the descriptors calculation and in the second one the calculated data are classified using five classifiers: the Naive Bayes, the RBF, the k-Nearest Neighbor, the Random-Forest and Random-Tree.…”

Section: Introductionmentioning

confidence: 99%

Statistical Features for Image Retrieval - A Quantitative Comparison

Ruberto

Fodde

2014

Proceedings of the 9th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

In this paper we present a comparison between various statistical descriptors and analyze their goodness in classifying textural images. The chosen statistical descriptors have been proposed by Tamura, Battiato and Haralick. In this work we also test a combination of the three descriptors for texture analysis. The database used in our study are the well-known Brodatz's album and DDSM (Heath et al., 1998). The computed features are classified using the Naive Bayes, the RBF, the KNN, the Random Forest and Random Tree models. The results obtained from this study show that we can achieve a high classification accuracy if the descriptors are used all together.

show abstract

“…For example, they can be applied in fields such as semantic description of images [7][8][9], obtaining texture descriptions that are directly interpretable by humans, or in content-based image retrieval systems [10,11,4], where linguistic queries related to the degree to which texture properties are present can be employed. 1 In addition, this perceptual characterization of texture can be also applied in expert systems, where the information provided by the expert is related to the presence of the texture properties.…”

Section: Introductionmentioning

confidence: 99%

An adaptive fuzzy approach for modeling visual texture properties

Chamorro-Martı́nez

Martínez-Jiménez

Soto-Hidalgo

et al. 2016

Fuzzy Sets and Systems

View full text Add to dashboard Cite

The analysis of the perceptual properties of texture plays a fundamental role in tasks like semantic description of images, content-based image retrieval using linguistic queries, or expert systems design based on low level visual features. The presence of these properties in images is very difficult to characterize due to their imprecision, and, moreover, because their perception may change depending on the user or the image context. In this paper, texture properties are modeled by means of an adaptive fuzzy approach that takes into account the subjectivity of the human perception. For this purpose, a methodology in two phases has been proposed. First, non-adaptive fuzzy models, that represent the average human perception about the presence of the texture properties, are obtained. For this modeling, we propose to learn a relationship between representative measures of the properties and the assessments given by human subjects. In a second phase, the obtained fuzzy sets are adapted in order to model the particular perception of the properties that a user may have, as well as the changes in perception influenced by the image context. For this purpose, the membership functions are automatically transformed on the basic of the information given by the user or extracted from the image context, respectively.

show abstract

Perceptive visual texture classification and retrieval

Cited by 23 publications

References 23 publications

Visualflamenco: Dependable, interactive image browsing based on visual properties

Visualflamenco: Dependable, interactive image browsing based on visual properties

Statistical Features for Image Retrieval - A Quantitative Comparison

An adaptive fuzzy approach for modeling visual texture properties

Contact Info

Product

Resources

About