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

We present a simple yet highly efficient method to register range and color images. This method does not rely upon calibration parameters nor does it use visual features analysis. Our assumption is that if the transformation that registers the images is a mathematical function, we can approximate with little number of samples. To this end, thin-plate spline-based interpolations are used in this paper. Therefore, the registration of one point in our method takes only the solving of a nonlinear function. Drastically enhanced performances in the computational processing are attained under this condition. In fact, we show that ultimately our computational algorithm is independent of the complexity of the mathematical model underlying it. Finally, this paper reports on the results of experiments conducted with various range camera models that endorse the proposed method. Eventually, three key features can be derived from our method: practicality, accuracy, and wide applicability.

/pdf/efficient-registering-of-color-and-range-images-18pamdlslr.pdf

Efficient registering of color and range images

This project concerns the management of a multimedia database (text and image) of historical papers representing ancient watermarks The current database contains roughly 3’000 images of such watermarks; the system allows archival and retrieval by means of textual or morphological criteria During the archival phase, textual description are stored, as well as descriptive primitives extracted together with the watermark itself by image analysis methods For the retrieval phase, several types of queries are supported; they allow textual search on the basis of the accompanying descriptions, morphological search according to global characteristics, and shape-based search on the basis of the watermark shape

/pdf/archival-and-retrieval-for-large-image-databases-application-3377i0m8qg.pdf

Archival and Retrieval for Large Image Databases: Application to an Historical Watermarks Archive

The use of electromagnetic analogies for perceptual grouping of image primiti ves is presented. This approach assumes that grouping is a lo w-level, data-driven and global process, with all image tokens interacting in some way. Two computational models are introduced, which allo w determination of proximity and directionality of image primiti ves. With the second model, prominent image features are considered as being electrical charges. According to Poisson’s equation, they generate a scalar potential and an associated “electrical” v ector field. The potential and field, determined by the combined global influence of all image features, are well defined o ver the entire image. The scalar potential can be used for proximity grouping, while the local direction of the field allows grouping of primitives according to their common directional tendency. Implementation problems and solutions are presented. V arious results are sho wn and discussed.

Thierry Pun

Papers

Efficient registering of color and range images

Archival and Retrieval for Large Image Databases: Application to an Historical Watermarks Archive

Electromagnetic models for perceptual grouping

Perceptual grouping and directionality determination using an electromagnetic model

Stochastic Digital Image Watermarking