You are here


  1. Roberto Brunelli,
    A Classification Case Study: People Identity Verification Based on Finger Matching,
    This paper aims at comparing Support Vector Machines with Gaussian kernels to Hyper Basis Functions networks, a variant of Regularization Networks, with a small number of units. The comparison is performed on the task of personal identity verification using dorsal images of fingers, coupling geometrical and textural information,
  2. C. Corridoni; M. Zanin,
    High Curvature Two-Clothoid Road Model Estimation,
    Road recognition is of fundamental importance for many image understanding tasks involving cameras mounted on moving vehicles. In this paper we consider the well-known approach to road recognition based on a clothoid road model. In the case of high curvature roads this approach shows its limitations. We propose an extended road model that covers explicitly the possibility of having two different clothoid segments in the camera field of view. An algorithm estimating parameters of both clothoids and their transition point is presented and tested in a simulated environment,
  3. G. Cattoni; S. Messelodi; C. M. Modena,
    Vision-based bicycle/motorcycle classification with Support Vector Machines,
    Classification of vehicles plays an important role in a traffic monitoring system. In this paper we present a feature-based classifier, which can distinguish bicycles from motorcycles in real world traffic scenes.
    Basically, the algorithm extracts some visual features focusing on the region corresponding to the wheels of vehicle. It splits the problem into two sub-cases depending on the computed motion direction. The classification is performed by means of a non-linear Support Vector Machine. Tests lead to a successful classification rate of 93% on video sequences taken from different road junctions in an urban environment
  4. C. Andreatta,
    CBIR techniques for object recognition,
    Content Based Image Retrieval (CBIR) is a widely adopted method for retrieving images from unannotated databases which are similar to a given query image. Usually images are indexed on the basis of low level features that can be automatically computed from the image visual content. Object detection and classification is a mandatory requirement for systems aiming at deriving semantic descriptions typically used by hymans to understand images. In this paper a novel approach is presented for object classification wihich is based on the extension of COMPASS, a CBIR system developed at ITC-irst. The experimental results are illustrated along with a comparison with a SVM classification approach recently proposed,
  5. C. Andreatta; M. Lecca; S. Messelodi,
    Memory based object recognition in images,
    MEMORI is a system for the detection and recognition of objects, stored in a database, within digital images taken as an input. It aims to provide a content-based indexing scheme which exploits the semantic information contained in the images. Object detection is achieved by segmenting the input image using color and textural information, and grouping the obtained regions by analyzing their adjacency relationships and their visual similarity to the objects in the database. The database is the memory of the system and consists of objects depicted by a set of different views, each of them described by a feature vector encoding color, texture and shape information. The same description is computed for the region groups candidated to represent an object and is compared, by an object classifier, with the database objects. The final result is a number of image regions each associated to one or more object classes with a confidence score,
  6. Alessandro Santuari; Oswald Lanz; Roberto Brunelli,
    Synthetic Movies for Computer Vision Applications,
    Proceedings of the Third IASTED International Conference on Visualization, Imaging, and Image Processing,
    , pp. 139-
  7. Filippo Bertamini; Roberto Brunelli; Oswald Lanz; Alessandro Roat; F. Santuari; Q. Xu Tobia,
    Olympus: an Ambient Intelligence Architecture on the Verge of Reality,
    Proceedings of the 12th International Conference on Image Analysis and Processing [ICIAP 2003],
    , pp. 139-
  8. Michele Zanin; Stefano Messelodi; Carla Maria Modena,
    Mantova, Italy,
    17/09/2003 - 19/09/2003,
  9. Filippo Bertamini; Roberto Brunelli; Oswald Lanz; Alessandro Roat; Alessandro Santuari; Francesco Tobia; Qing Xu,
    Olympus: an ambient intelligence architecture on the verge of reality,
  10. Stefano Messelodi; Carla Maria Modena,
    Extraction of Polygonal Frames from Color Documents for Page Decomposition,
    Graphic accents are often used in the design of complex documents in order to emphasize particular information. Words or illustrations are surrounded by a border line or highlighted by means of a colored background. This paper presents a method for the automatic extraction of document layout items, called {\em frames}, having polygonal shape and/or a uniformly colored background. As frames break the normal text flow, frame detection is a fundamental step of the document layout analysis in a document understanding system. The presented method relies on a color region growing algorithm and on straight edges extractor. The shape analysis of the obtained regions permits to localize the frames with their attributes. In order to reduce computation time and to return only specific patterns, the method exploits information about a model of the frames to be detected such as shape, skew or size, possibly supplied by the user or depending on the specific document class. The presented algorithm is assessed on a page databases containing more than 675 framed items. The evaluation is based on a novel tree matching method that takes into account the frame hierarchy and their shape,