A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.

/pdf/a-model-of-saliency-based-visual-attention-for-rapid-scene-wv0n3yqxix.pdf

A model of saliency-based visual attention for rapid scene analysis

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralbas "gist" and Lowes SIFT descriptors.

/pdf/beyond-bags-of-features-spatial-pyramid-matching-for-4aa5cbe2fz.pdf

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

This paper reports the application of techniques inspired by text retrieval research to content-based image retrieval. In particular, we show how the use of an inverted file data structure permits the use of an extremely high-dimensional feature-space, by restricting search to the subspace spanned by the features present in the query. A suitably sparse set of colour and texture features is proposed. A weighting scheme based on feature frequencies is used to combine disparate features in a compatible manner, and naturally extends to incorporate relevance feedback queries. The use of relevance feedback is shown consistently to improve system performance.

Content-based query of image databases: inspirations from text retrieval

Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. The paper describes a method for the secure and robust copyright protection of digital images. We present an approach for embedding a digital watermark into an image using the fast Fourier transform. To this watermark is added a template in the Fourier transform domain, to render the method robust against rotations and scaling, or aspect ratio changes. We detail an algorithm based on the log-polar or log-log maps for the accurate and efficient recovery of the template in a rotated and scaled image. We also present results which demonstrate the robustness of the method against some common image processing operations such as compression, rotation, scaling and aspect ratio changes.

/pdf/template-based-recovery-of-fourier-based-watermarks-using-42ue8akmgs.pdf

Template based recovery of Fourier-based watermarks using log-polar and log-log maps

This paper proposes an approach based on emotion recognition to maintain engagement of players in a game by modulating the game difficulty. Physiological and questionnaire data were gathered from 20 players during and after playing a Tetris game at different difficulty levels. Both physiological and self-report analyses lead to the conclusion that playing at different levels gave rise to different emotional states and that playing at the same level of difficulty several times elicits boredom. Emotion assessment from physiological signals was performed using a SVM (Support Vector Machine). An accuracy of 53.33% was obtained on the discrimination of three emotional classes, namely boredom, anxiety, engagement.

/pdf/boredom-engagement-and-anxiety-as-indicators-for-adaptation-2yyaadg5sg.pdf

Boredom, engagement and anxiety as indicators for adaptation to difficulty in games

Digital image watermarking techniques for copyright protection have become increasingly robust. The best algorithms perform well against the now standard benchmark tests included in the Stirmark package. However the stirmark tests are limited since in general they do not properly model the watermarking process and consequently are limited in their potential to removing the best watermarks. Here we propose a second generation benchmark for image watermarking which includes attacks which take into account powerful prior information about the watermark and the watermarking algorithms. We follow the model of the Stirmark benchmark and propose several new categories of tests including: denoising (ML and MAP), wavelet compression, watermark copy attack, active desynchronization, denoising, geometrical attacks, and denoising followed by perceptual remodulation. In addition, we take the important step of presenting results as a function of application. This is an important contribution since it is unlikely that one technology will be suitable for all applications.

/pdf/second-generation-benchmarking-and-application-oriented-1zj3k9jv0r.pdf

Second Generation Benchmarking and Application Oriented Evaluation

To demonstrate the performance of content-based image retrieval systems (CBIRSs), there is not yet any standard data set that is widely used. The only dataset used by a large number of research groups are the Corel Photo CDs. There are more than 800 of those CDs, each containing 100 pictures roughly similar in theme. Unfortunately, basically every evaluation is done on a different subset of the image sets thus making comparison impossible.In this article, we compare different ways of evaluating the performance using a subset of the Corel images with the same CBIRSan d the same set of evaluation measures. The aim is to show how easy it is to get differing results, even when using the same image collection, the same CBIRS and the same performance measures. This pinpoints the fact that we need a standard database of images with a query set and corresponding relevance judgments (RJs) to really compare systems.The techniques used in this article to "enhance" the apparent performance of a CBIRSa re commonly used, sometimes described, sometimes not. They all have a justification and seem to change the performance of a CBIRS but they do actually not. With a larger subset of images it is of course much easier to generate even bigger differences in performance. The goal of this article is not to be a guide of how to make the "apparent" performance of systems look good, but rather to make readers aware of CBIRS evaluations and the importance of standardized image databases, queries and RJ.

Thierry Pun

Papers

Content-based query of image databases: inspirations from text retrieval

Template based recovery of Fourier-based watermarks using log-polar and log-log maps

Boredom, engagement and anxiety as indicators for adaptation to difficulty in games

Second Generation Benchmarking and Application Oriented Evaluation

The Truth about Corel - Evaluation in Image Retrieval