The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents a multi-expert system for dynamic signature verification. The system combines three experts whose complementar behaviour is achieved by using both different features and verification strategies. The first expert uses shape-based features and performs signature verification by a wholistic analysis. The second and third expert uses speed-based features and performs signature verification...
This paper addresses the problem of dynamic configuration of multiclassifier systems. For this purpose, the performance of combination methods for abstract-level classifiers is predicted, under different working conditions, and sets of rules are discovered and used for dynamic configuration of multiclassifier systems. The experimental tests have been carried out in the field of hand-written numeral...
Personal stability in signing in one of the key factors for high-accuracy signature verification. In this paper the local stability of a dynamic signature is measured. The acccuracy of an on-line signature verification system is improved by selecting, among a set of specimens available, the subset of reference signatures which is near-optimal for different signature representation domains in terms...
This paper presents a system for handwritten word recognition based on an analytical approach. Through a fast segmentation procedure, basic strokes are detected and used to recognize the word by a bottom-up approach. The system has been tested on the worded amounts on bankchecks. The experimental results show the effectiveness of the approach.
Complementarity among classifiers is a crucial aspect in classifier combination. A combined classifier is significantly superior to the individual classifiers only if they strongly complement each other. In this paper a complementarity-based analysis of sets of classifier is proposed for investigating the behaviour of multi-classifier systems, as new classifiers are added to the set. The experimental...
In this paper a new technique for handwritten word description is presented. It is based on the development of a description graph which results little sensitive to handwriting variability. The experimental results show the effectiveness of the description graph in retaining the basic information for the recognition of the word image.
This paper presents the State of the Art on handwriting recognition and points out some major future trends of scientific research in this field. Some of the most relevant results presented in the series of Workshops on Frontiers in Handwriting Recognition and Conferences on Document Analysis and Recognition are also discussed and an extensive bibliography of selected papers is reported.
In this paper a new method to make faster the Winograd-Fourier algorithm is presented. In fact it is shown as for some prime factors the Cooley FFT algorithm together with the Rader algorithm allow a very fast computation of the DFT.
This paper presents a new approach for zoning design. The approach is based on a techinque which detects the most discriminant image regions by the analysis of feature distributions, and obtains the zoning by an iterative zone-growing process. An application to handwritten numeral recognition is also reported showing the effectiveness of the proposed approach.
In this paper we propose a digital image quality metric based on human visual system. This metric considers the coefficients of discrete cosine transform related to each 8×8 block of an image. To perform image evaluation PQMET detects a distortion applied to the image and then selects the corresponding matrix of minimum visibility thresholds capable to produce a visible signal. Therefore it uses the...
The introduction and rapid growth of social computing into educational practices has encouraged the development of the networked learning through a careful evaluation of the “social nature” of digital applications that implement interaction and collaboration among network users. This evolution is reflected in the Virtual Learning Environments (VLE) systems and supports the progress to online shared...
This paper presents a framework for the analysis of similarity among abstract-level classifiers and proposes a methodology for the evaluation of combination methods. In this paper, each abstract-level classifier is considered as a random variable, and sets of classifiers with different degrees of similarity are systematically simulated, combined, and studied. It is shown to what extent the performance...
The `diagonal function' is a new tool for performing non-modular operations in the Residue Number System (RNS). It is defined from the RNS to the integers and exploits the geometrical disposal in multi-dimensional discrete spaces of integers in residue representations.This paper presents a new class of RNS architectures for the effective implementation of the `diagonal function'. The architectures...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.