Topic
Signature recognition
About: Signature recognition is a research topic. Over the lifetime, 2138 publications have been published within this topic receiving 37605 citations.
Papers published on a yearly basis
Papers
More filters
01 Jan 2003
TL;DR: Test procedures for FP verification and identification are advanced for the first time and sets of live-scan dab data for a large database of fingerprints with elastic distortions are used to evaluate the use of distortion-invariant filters for FP recognition.
Abstract: Sets of live-scan dab data for a large database of fingerprints (FPs) with elastic distortions are used to evaluate the use of distortion-invariant filters for FP recognition. Test procedures for FP verification and identification are advanced for the first time. One filter is formed for each FP. A
1 citations
01 Jan 2002
TL;DR: The algorithm that has been derived uses neural-network-based feature detectors to identify localcharacteristic features of a flexible object and proves to be able to generalise to a considerable extent over instances that do not meet the requirements of the training set.
Abstract: The aim of the research described in this paper has been to take an investigative step towards the development o f a general framework for object recognition. The algorithm that has been derived as a result of these explorations uses neural-network-based feature detectors to identify localcharacteristic features of a flexible object. Recognition is a re sult of finding a configuration of features detected in a given imag e that closely resembles the structure of one of a set of known instances of the object. The experiments show that the described approach applied to the object classhorse produces good recognition results for instances that meet the requirements of the training set. Fu rthermore, the method proves to be able to generalise to a considerable extent over instances that do not meet these requi re-
1 citations
25 Aug 2013
TL;DR: The experiment results indicate that it is possible to apply the part-based method to the font recognition, which is always considered as a difficult task by most of the researchers.
Abstract: In this paper, the part-based recognition method is introduced and applied to the arbitrary font recognition. The principle of the part-based method is to represent the character image as a set of parts and then recognize the image by finding the most possible parts set from the reference database. Since the part-based method does not rely on the global structure of a character, it is supposed to be robust against the variant appearances of the character. The experiment results indicate that it is possible to apply the part-based method to the font recognition, which is always considered as a difficult task by most of the researchers.
1 citations
Patent•
20 Feb 2002
TL;DR: In this article, an apparatus and method for referring a credit card using a signature recognition is provided to protect personal property and information by raising a security level using signature information on electronic commerce based on a web.
Abstract: PURPOSE: An apparatus and method for referring a credit card using a signature recognition is provided to protect personal property and information by raising a security level using signature information on electronic commerce based on a web. CONSTITUTION: A credit card reading unit(201) reads a magnetic tap of a credit card and extracts member information on a credit card user. A key input unit(202) receives an input of a key for connecting to a credit card company. A signature input unit(203) receives the credit card user's signature. A signature data processing unit(204) extracts characteristics of signatures from signature data inputted. A transmitting/receiving unit(206) transmits the member information read from the credit card reading unit(201) and signature data information processed from the signature data processing unit(204) to a service providing system. An output unit(207) displays information inputted from the credit card reading unit(201), the key input unit(202) or the signature input unit(203). A sales ticket printing unit(208) prints a sales ticket. A control unit(208) controls information moving between the units(201,206 or 204,208).
1 citations
26 Jul 2011
TL;DR: A novel algorithm of automatic threshold for head recognition is proposed basing on multi-weight and triangle covering based on principle of point distribution in multi-dimensional space and Biomimetic Pattern Recognition.
Abstract: Analyzing object recognition in complicated traffic environment with principle of point distribution in multi-dimensional space and Biomimetic Pattern Recognition, a novel algorithm of automatic threshold for head recognition is proposed basing on multi-weight and triangle covering Getting the initial head samples from head detection of the looked-down video stream, extracting features of these samples and mapping them into multi-dimensional feature space, then obtaining the density-threshold radius according to the distribution density of head samples automatically to cover all the heads with triangle, lastly further dividing the samples that are overlapping covered in order to discriminate the head images Results of experiment in UCI database and video data of head show that the method is valid and efficient
1 citations