Search

Color is one of the most used features for image analysis. However, two uncertainty problems arise in this scope: first, color computer representation does not match with how humans understand the color concept; second, the color feature is imprecise by nature. For this reason, fuzzy colors and fuzzy color spaces were developed as a suitable way to model color categories. The most recent and best accurate approaches use crisp color prototypes to build fuzzy color spaces, considering standard and fixed set of colors prototypes (such as ISCC-NBS system) for this purpose. The use of these types of general purpose prototypes may not be flexible enough to collect particular colors of a given image (or a set of images); in addition, image colors may be context dependent in some cases (for example, red color in winery or medicine context). In order to solve these drawbacks, in this paper we propose to learn fuzzy color spaces by analyzing the relevant colors in a given set of representative images for a specific context and/or application; then, we will use them as prototypes in order to build adaptive fuzzy color spaces. Some real experiments are performed in order to illustrate the advantages of our proposal. [ABSTRACT FROM AUTHOR]

Abstract The modeling of the perceptual properties of texture plays a fundamental role in tasks where some interaction with subjects is needed. In order to face the imprecision related to these properties, fuzzy sets defined on the domain of computational measures of the corresponding property are usually employed. In this sense, the most interesting approaches show that the combination of different measures as reference sets improve the texture characterization. However, the main drawback of these proposals is that they do not take into account the subjectivity associated with human perception. For example, the perception of a texture property may change depending on the user, and in addition, the image context may influence the global perception of a given property. In this paper, we propose to solve these problems by combining the use of several computational measures in a reference set with adaptation to the subjectivity of human perception. To do this, we propose a generic methodology that automatically transforms any multidimensional fuzzy set modeling a texture property to the particular perception of a new user or to the image context. For this purpose, the information given by the user, or extracted from the textures present in the image, are employed. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of simulating the human perception of texture properties in images. In particular, we have focused our study on the properties of coarseness, contrast and directionality, that play a fundamental role in the human perception of texture. The objective is not to precisely identify, classify or discriminate between different textures as a whole, but to be able to assess the presence of each texture property in the image. For this purpose, fuzzy sets defined on the domain of different groups of measures are employed in order to model each property by using parametric membership functions. The corresponding parameters are obtained by learning a functional relationship between the computational values given by the measures and the human perception. The performance of each fuzzy set is analyzed and tested with the human assessments, and a ranking of subsets of measures is obtained according to their ability to represent the perception of the property, allowing us to identify the most suitable combination of measures. [ABSTRACT FROM AUTHOR]

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. In this paper, we propose a methodology to model texture properties by means of fuzzy sets defined on bidimensional spaces. In particular, we have focused our study on the fineness property that is considered as the most important feature for human visual interpretation. In our approach, pairwise combinations of fineness measures are used as a reference set, which allows to improve the ability to capture the presence of this property. To obtain the membership functions, we propose to learn the relationship between the computational values given by the measures and the human perception of fineness. The performance of each fuzzy set is analyzed and tested with the human assessments, allowing us to evaluate the goodness of each model and to identify the most suitable combination of measures for representing the fineness presence. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for the removal of semi-transparent defects from images of historical or artistic importance. It combines Lie group transformations with human perception rules in order to make restoration more flexible and adaptable to defects having different physical or mechanical causes. In particular, the restoration process consists of an iterative procedure that gradually reduces the visual perception of the defect. It takes advantage from Lie groups that allow to define a redundant set of transformations from which it is possible to automatically select the ones that better invert the physical formation of the defect. Experimental results on movies and photographs, affected by line-scratches and semi-transparent blotches, have shown the potential of the proposed approach in giving new guidelines and trends for human perception-based restoration. [ABSTRACT FROM AUTHOR]

CAPTCHA is an effective and widely used solution for preventing computer programs (i.e., bots) from performing automated but often malicious actions, such as registering thousands of free email accounts or posting advertisement on Web blogs. To make CAPTCHAs robust to automatic character recognition techniques, the text in the tests are often distorted, blurred, and obscure. At the same time, those robust tests may prevent genuine users from telling the text easily and thus distribute the cost of crime prevention among all the users. Thus, we are facing a dilemma, that is, a CAPTCHA should be robust enough so that it cannot be broken by programs, but also needs to be easy enough so that users need not to repeatedly take tests because of wrong guesses. In this article, we attempt to resolve the dilemma by proposing a human computation game for quantifying the usability of CAPTCHAs. In our game, DevilTyper, players try to defeat as many devils as possible by solving CAPTCHAs, and player behavior in completing a CAPTCHA is recorded at the same time. Therefore, we can evaluate CAPTCHAs' usability by analyzing collected player inputs. Since DevilTyper provides entertainment itself, we conduct a large-scale study for CAPTCHAs' usability without the resource overhead required by traditional survey-based studies. In addition, we propose a consistent and reliable metric for assessing usability. Our evaluation results show that DevilTyper provides a fun and efficient platform for CAPTCHA designers to assess their CAPTCHA usability and thus improve CAPTCHA design. [ABSTRACT FROM AUTHOR]

Abstract: This paper deals with an approach allowing to associate visual textures with given human perceptions. Hereby, based on a forward model associating human perceptions for given visual textures, the deduction of an reverse process is presented which is able to associate and characterize visual textures for given human perceptions. For doing so, we propose a constraint-based genetic algorithm approach, which is able to minimize a specific optimization problem containing constraints in form of band-widths for valid individuals (low level features extracted from textures) in a population. The constraints are determined by relationships between (low level) features characterizing textures in form of high-dimensional approximation models. Additionally, in each iteration step checking for valid individuals is carried out with a texture/non-texture classifier or by using a convex hull over a set of valid textures. The whole approach is evaluated based on a real-world texture set used as a start population in the genetic algorithm and by defining various kinds of human perceptions (for which textures are sought) represented by adjective vectors in the aesthetic space. The generated individuals (low level feature vectors) have a high level of fitness (they are quite close to the pre-defined adjective vectors) and a small distance to the initial population. The textures synthesized based on the generated individuals are visualized and compared with textures synthesized by a time-intensive direct texture mixing and re-combination method based on a real-world texture data base. [Copyright &y& Elsevier]