Papers by Claudia Diamantini
Lecture Notes in Computer Science, 1995
ABSTRACT Treatment of natural images requires, due to their complexity, to exploit high level kno... more ABSTRACT Treatment of natural images requires, due to their complexity, to exploit high level knowledge, such as domain knowledge and heuristics, which are typically well formalized by rule based systems. However, the intrinsic variability and irregularity of objects in the image makes their characterization in terms of rules often unfeasible. Such variability and irregularity are, on the other hand, the ultimate reason for the existence of statistical methods. For these reasons, a hybrid system, exploiting characteristics of both approaches, may show better performances than purely syntactical or statistical systems in the interpretation of natural images. In this paper we present a hybrid system for image interpretation that integrates a rule based system with a Labeled Learning Vector Quantizer. The rule based system controls the interpretation process, by dynamically determining the interpretation strategy, and the Labeled Learning Vector Quantizer is exploited as classification kernel. The system has been tested on images of liver biopsies. Results on nuclei classification are here discussed.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2006
Bookmarks Related papers MentionsView impact
IEEE Transactions on Neural Networks, 1998
In pattern classification, a decision rule is a labeled partition of the observation space, where... more In pattern classification, a decision rule is a labeled partition of the observation space, where labels represent classes. A way to establish a decision rule is to attach a label to each code vector of a vector quantizer (VQ). When a labeled VQ is adopted as a classifier, we have to design it in such a way that high classification performance is obtained by a given number of code vectors. In this paper we propose a learning algorithm which optimizes the position of labeled code vectors in the observation space under the minimum average misclassification risk criterion.
Bookmarks Related papers MentionsView impact
IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2000
LVQ1 is a supervised fine tuning of the Self-Organizing Map, introduced by Kohonen for the classi... more LVQ1 is a supervised fine tuning of the Self-Organizing Map, introduced by Kohonen for the classification task. In this paper we present a study about LVQ1. We show that it implements the search of certain saddles on a scalar cost function. The above criterion does not guarantee convergence to a stable solution, as enlightened by a simple example. We also
Bookmarks Related papers MentionsView impact
Electronics Letters, 1995
Bookmarks Related papers MentionsView impact
Electronics Letters, 1995
ABSTRACT In pattern classification one has to test which class an observation vector belongs to, ... more ABSTRACT In pattern classification one has to test which class an observation vector belongs to, paying the minimum error probability. According to the nonparametric formulation, the statistical information is given by a labelled training set. The authors show how to design a classification rule by optimising the position of code vectors of a labelled vector quantiser under the minimum error probability criterion
Bookmarks Related papers MentionsView impact
... lsb. Citations (CiTO). No CiTO tags defined. X There are no reviews yet. There are no reviews... more ... lsb. Citations (CiTO). No CiTO tags defined. X There are no reviews yet. There are no reviews of this article. ... Group Tags. All tags in the group handwriting-recognition. Filter: [Display as Cloud] [Display as List] [Hide Cito Tags] [Show Cito Tags]. lsb, 3359. handwriting-recognition, 66 ...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Sistemi Evoluti per Basi di Dati, 2006
Bookmarks Related papers MentionsView impact
Sistemi Evoluti per Basi di Dati, 2004
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2015
Bookmarks Related papers MentionsView impact
Studies in Computational Intelligence, 2014
Bookmarks Related papers MentionsView impact
Research Advancements, 2012
Bookmarks Related papers MentionsView impact
Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, 2007
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Knowledge Discovery in Databases (KDD) is a complex dis- covery process where a lot of data manip... more Knowledge Discovery in Databases (KDD) is a complex dis- covery process where a lot of data manipulation tools with dierent char- acteristics can, and in fact have to, be used together to reach the goal of previously unknown, potentially useful information extraction. In order to guide the user in the correct and eective use of tools, a KDD sup- port
Bookmarks Related papers MentionsView impact
Uploads
Papers by Claudia Diamantini