Análise de Características para Detecção de Nudez em Imagens

Thesis for: Master, Advisor: Eduardo Souto, Eulanda Santos, João Cavalcanti, Angela Dias

ABSTRACT The popularization of Internet access has lead institutions and parents to face serious problems on preventing employees, as well as children, to have access to inappropriate content, such as pornographic pages. This kind of content is available in different forms, including videos, sounds, text, and especially images, on the Web. Since most of this inappropriate content is provided as images, it is necessary to employ strategies which allow the analysis of image content in order to control access to inappropriate content. In this context, nudity detection in images plays an important role. Several approaches apply skin detection as a key step toward nudity detection. Skin detection is a difficult task due to the fact that it is necessary to use skin filters robust to shade variations caused by light. In addition, these methods employ a combination of features based on color, texture and shape, which may increase the complexity and time processing of detection algorithms. In despite of this drawback, feature analysis, or selection, is not carried out in most of the work available in the literature, The objective of this work is to investigate the features most frequently used in the literature for the description of nude images, as well as to select the most relevant subset of features taking into account classification accuracy. The feature analysis is carried out through three series of experiments focusing on investigating different scenarios of comparison. In the first series, we compare features extracted without applying skin filter, called global evidence in this work. In the second series, features extracted after skin filter are also compared. These features are called local evidence. Finally, in the third series of experiments, a zoning algorithm is used in order to allow us to analyze the impact of both local and global features in each area of the image. In all series of experiments, each feature is analyzed individually and all subsets of features are tested so as to determinate the best tradeoff between feature set and classification accuracy. In addition, an architecture called ANDImage (Architecture for Nude Detection in Image) is proposed. ANDImage allows that different modules may be used in order to provide the possibility of dealing with different scenarios of features comparison.

  • [Show abstract] [Hide abstract]
    ABSTRACT: The book gives an extensive introduction to statistical pattern recognition. The content is centered around statistical models of decision making and estimation theory regarded as fundamental to the study of statistical pattern recognition. In comparison to the first, 1972 - edition the book contains a significant portion of new material, especially pertaining to feature extraction and clustering techniques. The book is self-contained. Chapters 2 and 3 provide all necessary material on multidimensional random variables (random vectors) along with their linear transformations. Hypothesis testing including determination of error probabilities in hypothesis testing and upper bounds on the Bayes error are included in Chapter 3. Parametric classifiers (such as the Bayes linear classifier, linear and quadratic ones) are covered in Chapter 4 (Parametric classifiers). Subsequently, essential problems of parametric and nonparametric estimation are studied in Chapters 5 and 6, respectively. They constitute a rational prerequisite for studies in nonparametric classification. A thorough discussion on nonparametric classification (K Nearest Neighbor) and error estimation is included in Chapter 7. Successive parameter estimation (such as e.g., stochastic approximation and Bayes estimation) is studied in Chapter 8. The presentation of feature extraction and linear mapping for signal representation and classification (Chapter 9 and 10) is focussed on useful techniques such as Karhunen-Loève expansion and discriminant analysis, involving several generalized criteria. Unsupervised learning (clustering) discussed in Chapter 11 addresses parametric as well as nonparametric approaches. The book contains a vast number of computer experiments. Each chapter contains computer projects, problems and references. The material is well organized, its exposition is lucid. A major emphasis is put on concepts and algorithms. Formal proofs are not provided; in most of the cases the reader is usually referred to carefully selected references. Due to its contents and organization the book can serve as an introductory text to statistical pattern recognition in courses on pattern recognition. It can be useful as a reference source for practitioners working in this field.Reviewer: W.Pedrycz
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: With the explosive growth of the World Wide Web, the public is gaining access to massive amounts of information. However, locating needed and relevant information remains a difficult task, whether the information is textual or visual. Text search engines have existed for some years now and have achieved a certain degree of success. However, despite the large number of images available on the Web, image search engines are still rare. In this article, we show that in order to allow people to profit from all this visual information, there is a need to develop tools that help them to locate the needed images with good precision in a reasonable time, and that such tools are useful for many applications and purposes. The article surveys the main characteristics of the existing systems most often cited in the literature, such as ImageRover, WebSeek, Diogenes, and Atlas WISE. It then examines the various issues related to the design and implementation of a Web image search engine, such as data gathering and digestion, indexing, query specification, retrieval and similarity, Web coverage, and performance evaluation. A general discussion is given for each of these issues, with examples of the ways they are addressed by existing engines, and 130 related references are given. Some concluding remarks and directions for future research are also presented.
    ACM Comput. Surv. 01/2004; 36.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Object recognition is a central problem in computer vision research. Most object recognition systems have taken one of two approaches, using either global or local features exclusively. This may be in part due to the difficulty of combining a single global feature vector with a set of local features in a suitable manner. In this paper, we show that combining local and global features is beneficial in an application where rough segmentations of objects are available. We present a method for classification with local features using non-parametric density estimation. Subsequently, we present two methods for combining local and global features. The first uses a "stacking" ensemble technique, and the second uses a hierarchical classification system. Results show the superior performance of these combined methods over the component classifiers, with a reduction of over 20% in the error rate on a challenging marine science application.
    Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 06/2005;


Available from
May 20, 2014