Abstract: Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult.
Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches.

Abstract: In this paper, we propose a novel technique to detect the shadows cast by urban infrastructure, such as buildings, billboards, and traffic signs, using a sequence of images taken from a fixed camera. In our approach, we compute two different background models in parallel: one for the edges and one for the reflected light intensity. An algorithm is proposed to train the system to distinguish between moving edges in general and edges that belong to static objects, creating an edge background model. Then, during operation, a background intensity model allow us to separate between moving and static objects. Those edges included in the moving objects and those that belong to the edge background model are subtracted from the current image edges. The remaining edges are the ones cast by urban infrastructure. Our method is tested on a typical crossroad scene and the results show that the approach is sound and promising.

Abstract: This article describes a novel approach to the modeling of human actions in 3D. The method we propose is based on a “bag of poses” model that represents human actions as histograms of key-pose occurrences over the course of a video sequence. Actions are first represented as 3D poses using a sequence of 36 direction cosines corresponding to the angles 12 joints form with the world coordinate frame in an articulated human body model. These pose representations are then projected to three-dimensional, action-specific principal eigenspaces which we refer to as aSpaces. We introduce a method for key-pose selection based on a local-motion energy optimization criterion and we show that this method is more stable and more resistant to noisy data than other key-poses selection criteria for action recognition.

Abstract: One of the first usual steps in pattern recognition schemas is image segmentation, in order to reduce the dimensionality of the problem and manage smaller quantity of data. In our case as we are pursuing real-time colon cancer polyp detection, this step is crucial. In this paper we present a non-informative region estimation algorithm that will let us discard some parts of the image where we will not expect to find colon cancer polyps. The performance of our approach will be measured in terms of both non-informative areas elimination and polyps’ areas preserving. The results obtained show the importance of having correct non- informative region estimation in order to fasten the whole recognition process.

Abstract: Sequential learning is that discipline of machine learning that deals with dependent data. In this paper, we use the Multi-scale Stacked Sequential Learning approach (MSSL) to solve the task of pixel-wise classification based on contextual information. The main contribution of this work is a shifting technique applied during the testing phase that makes possible, thanks to template images, to classify objects at different sizes. The results show that the proposed method robustly classifies such objects capturing their spatial relationships.

Abstract: State of the art methods for image matching, content-based retrieval and recognition use local features. Most of these still exploit only the luminance information for detection. The color saliency boosting algorithm has provided an efficient method to exploit the saliency of color edges based on information theory. However, during the design of this algorithm, some issues were not addressed in depth: (1) The method has ignored the underlying distribution of derivatives in natural images. (2) The dependence of information content in color-boosted edges on its spatial derivatives has not been quantitatively established. (3) To evaluate luminance and color contributions to saliency of edges, a parameter gradually balancing both contributions is required.
We introduce a novel algorithm, based on the principles of independent component analysis, which models the first order derivatives of color natural images by a generalized Gaussian distribution. Furthermore, using this probability model we show that for images with a Laplacian distribution, which is a particular case of generalized Gaussian distribution, the magnitudes of color-boosted edges reflect their corresponding information content. In order to evaluate the impact of color edge saliency in real world applications, we introduce an extension of the Laplacian-of-Gaussian detector to color, and the performance for image matching is evaluated. Our experiments show that our approach provides more discriminative regions in comparison with the original detector.

Abstract: The characterization of trichromatic cameras is usually done in terms of a device-independent color space, such as the CIE 1931 XYZ space. This is indeed convenient since it allows the testing of results against colorimetric measures. We have characterized our camera to represent human cone activation by mapping the camera sensor's (RGB) responses to human (LMS) through a polynomial transformation, which can be “customized” according to the types of scenes we want to represent. Here we present a method to test the accuracy of the camera measures and a study on how the choice of training reflectances for the polynomial may alter the results.