Showing papers on "Signature recognition published in 1997"
TL;DR: A new method based on amplitude modulation is presented that has shown to be resistant to both classical attacks, such as filtering, and geometrical attacks and can be extracted without the original image.
Abstract: Watermarking techniques, also referred to as digital signature, sign images by introducing changes that are imperceptible to the human eye but easily recoverable by a computer program. Generally, the signature is a number which identifies the owner of the image. The locations in the image where the signature is embedded are determined by a secret key. Doing so prevents possible pirates from easily removing the signature. Furthermore, it should be possible to retrieve the signature from an altered image. Possible alternations of signed images include blurring, compression and geometrical transformations such as rotation and translation. These alterations are referred to as attacks. A new method based on amplitude modulation is presented. Single signature bits are multiply embedded by modifying pixel values in the blue channel. These modifications are either additive or subtractive, depending on the value of the bit, and proportional to the luminance. This new method has shown to be resistant to both classical attacks, such as filtering, and geometrical attacks. Moreover, the signature can be extracted without the original image.
408 citations
TL;DR: The role of signature shape description and shape similarity measure is discussed in the context of signature recognition and verification and the proposed method allows definite training control and at the same time significantly reduces the number of enrollment samples required to achieve a good performance.
192 citations
TL;DR: This paper proposes a new formalism for signature representation based on visual perception, and two types of classifiers, a nearest neighbor and a threshold classifier, show a total error rate below 0.02 percent and 1.0 percent in the context of random forgeries.
Abstract: A fundamental problem in the field of off-line signature verification is the lack of a signature representation based on shape descriptors and pertinent features. The main difficulty lies in the local variability of the writing trace of the signature which is closely related to the identity of human beings. In this paper, we propose a new formalism for signature representation based on visual perception. A signature image consists of 512/spl times/128 pixels and is centered on a grid of rectangular retinas which are excited by local portions of the signature. Granulometric size distributions are used for the definition of local shape descriptors in an attempt to characterize the amount of signal activity exciting each retina on the focus of the attention grid. Experimental evaluation of this scheme is made using a signature database of 800 genuine signatures from 20 individuals. Two types of classifiers, a nearest neighbor and a threshold classifier, show a total error rate below 0.02 percent and 1.0 percent, respectively, in the context of random forgeries.
154 citations
01 Jan 1997
TL;DR: This book is a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including lipreading, gesture recognition, facial expression recognition, gait analysis, cyclic motion detection, and activity recognition.
Abstract: Motion-based recognition deals with the recognition of an object and/or its motion, based on motion in a series of images. In this approach, a sequence containing a large number of frames is used to extract motion information. The advantage is that a longer sequence leads to recognition of higher level motions, like walking or running, which consist of a complex and coordinated series of events. Unlike much previous research in motion, this approach does not require explicit reconstruction of shape from the images prior to recognition. This book provides the state-of-the-art in this rapidly developing discipline. It consists of a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including lipreading, gesture recognition, facial expression recognition, gait analysis, cyclic motion detection, and activity recognition. Audience: This volume will be of interest to researchers and post- graduate students whose work involves computer vision, robotics and image processing.
143 citations
18 Aug 1997
TL;DR: The authors demonstrate that with the addition to the global features of a local feature based on the signature likelihood obtained from hidden Markov models (HMM) the performance of signature verification improves significantly.
Abstract: A method for the automatic verification of on-line handwritten signatures using both global and local features as described The global and local features capture various aspects of signature shape and dynamics of signature production The authors demonstrate that with the addition to the global features of a local feature based on the signature likelihood obtained from hidden Markov models (HMM) the performance of signature verification improves significantly The current version of the program, has 25% equal error rate At the 1% false rejection (FR) point, the addition of the local information to the algorithm with only global features reduced the false acceptance (FA) rate from 13% to 5%
106 citations
17 Sep 1997
TL;DR: This paper focuses on the description of the gesture recognition method (including data preprocessing) and describes experiments for the evaluation of the performance of the recognition method.
Abstract: In this paper we present a method for the recognition of dynamic gestures with discrete Hidden Markov Models (HMMs) from a continuous stream of gesture input data. The segmentation problem is addressed by extracting two velocity profiles from the gesture data and using their extrema as segmentation cues. Gestures are captured with a TUB-SensorGlove. The paper focuses on the description of the gesture recognition method (including data preprocessing) and describes experiments for the evaluation of the performance of the recognition method. The paper combines and further develops ideas from some of our previous work.
92 citations
17 Sep 1997
TL;DR: In this article, an advanced real-time system for gesture recognition is presented, which is able to recognize complex dynamic gestures, such as hand waving, spin, pointing, and head moving.
Abstract: An advanced real-time system for gesture recognition is presented, which is able to recognize complex dynamic gestures, such as ”hand waving”, ”spin”, ”pointing”, and ”head moving”. The recognition is based on global motion features, extracted from each difference image of the image sequence. The system uses Hidden Markov Models (HMMs) as statistical classifier. These HMMs are trained on a database of 24 isolated gestures, performed by 14 different people. With the use of global motion features, a recognition rate of 92.9% is achieved for a person and background independent recognition.
63 citations
18 Aug 1997
TL;DR: This work focuses on the use of the dynamic time warping (DTW) technique in the signature verification area, where it is a highly appreciated component of speaker specific isolated word recognisers.
Abstract: We focus on the use of the dynamic time warping (DTW) technique in the signature verification area. The DTW algorithm originates from the field of speech recognition, where it is a highly appreciated component of speaker specific isolated word recognisers. A few years ago the DTW algorithm was successfully introduced in the area of online signature verification. The characteristics of speech recognition and signature verification are however rather different. Starting from these dissimilarities, our objective is to extract an alternative DTW approach that is better suited to the signature verification problem.
48 citations
07 Sep 1997
TL;DR: It is shown in this paper that this approach based on hidden Markov models is well adapted for learning and recognition of places by a mobile robot.
Abstract: In this paper, we propose a new method based on hidden Markov models to learn and recognize places in an indoor environment by a mobile robot. Hidden Markov models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (e.g. neural networks) are their capabilities to modelize noisy temporal signals of variable length. We show in this paper that this approach is well adapted for learning and recognition of places by a mobile robot. Results of experiments on a real robot with five distinctive places are given.
36 citations
02 Jul 1997
TL;DR: This paper summarizes a research effort for an off-line signature recognition and verification system that uses three kinds of features extracted from the digital image of the signature: global features, grid information features and texture features.
Abstract: This paper summarizes a research effort for an off-line signature recognition and verification system. The system uses three kinds of features extracted from the digital image of the signature: global features, grid information features and texture features. For each of them a special one-class-one-network classification structure has been implemented. In order for the system to come to a decision, it uses the results from all the three neural network structures, combined with a simple Euclidean norm.
24 citations
Patent•
03 Mar 1997
TL;DR: In this paper, a micro computer consisting of an automatic signature creating section, data extracting section, recognition network section, a retrieval section, and a memory section is used for signature recognition.
Abstract: A micro computer, constituting a signature recognition apparatus, comprises an automatic signature creating section, a data extracting section, a recognition network section, a retrieval section, and a memory section. The data extracting section creates personal data representing a plurality of personal characteristics or features based on an input signature. The recognition network section selects the data to be used for evaluation from the personal data representing personal characteristics or features, and executes an evaluation of thus chosen data. The retrieval section, using the genetic algorithm, finds out a combination pattern having preferable evaluation result. Accordingly, in recognizing signatures, it becomes possible to know beforehand what kind of personal characteristics or features data should be utilized for the recognition of the given signatures, thereby increasing the accuracy in the recognition.
18 Aug 1997
TL;DR: New moment features for Chinese character recognition are proposed that provide significant improvements in terms of Chinese character Recognition, especially for those characters that are very close in shapes.
Abstract: Moment descriptors have been developed as features in pattern recognition since the moment method was first introduced. In this paper, new moment features for Chinese character recognition are proposed. These provide significant improvements in terms of Chinese character recognition, especially for those characters that are very close in shapes.
18 Aug 1997
TL;DR: This paper presents two approaches for handling rejects in a hidden Markov based handwriting recognition system, one of the techniques relies on relative frequencies of those values, the other one utilizes standard classification techniques to train a reject decision unit, the reject classifier.
Abstract: The most scientific papers dealing with handwriting recognition systems make statements relating to the recognition performance based on a forced-recognition rate. This rate describes the ratio between the number of the correct recognized samples and the number of all possible samples. For systems applied in real applications this rate is not very relevant. They have to work with a very low error-rate, which can be only achieved by introducing effective reject criteria. So the real interesting thing is a function describing the recognition rate in relation to a specific error rate, including implicitly a corresponding reject rate. This paper presents two approaches for handling rejects in a hidden Markov based handwriting recognition system. The features to determine a reject are values which are derived from the hidden Markov recognizer. One of the techniques relies on relative frequencies of those values, the other one utilizes standard classification techniques to train a reject decision unit, the reject classifier. Both methods are presented with some noteworthy results.
17 Jun 1997
TL;DR: An efficient approach to pose invariant object recognition employing pictorial recognition of image patches using Spectral Signatures that allows to recognize image patches that correspond to object surfaces which are roughly planar-invariant to their pose in space.
Abstract: This paper describes an efficient approach to pose invariant object recognition employing pictorial recognition of image patches. A complete affine invariance is achieved by a representation which is based on a new sampling configuration in the frequency domain. Employing Singular Value Decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale and 2D translation. From this decomposition, we derive an affine invariant representation that allows to recognize image patches that correspond to object surfaces which are roughly planar-invariant to their pose in space. The representation is in the form of Spectral Signatures that are derived from a set of Cartesian logarithmic-logarithmic (log-log) sampling configuration in the frequency domain. Unlike previous log-polar representations which are not invariant to slant (i.e. foreshortening only in one direction), our new configuration yields complete affine invariance. The proposed log-log configuration can be employed both globally or locally by a Gabor or Fourier transforms. Local representation enables to recognize separately several objects in the same image. The actual signature recognition is performed by multidimensional indexing in a pictorial dataset represented in the frequency domain. The recognition also provides 3D pose information.
26 Oct 1997
TL;DR: The affine invariant spectral signatures (AISS), a representation which is based on a new sampling configuration in the frequency domain, enables the recognition of image patches that correspond to roughly planar object surfaces-regardless of their poses in space.
Abstract: This paper presents an efficient scheme for affine-invariant object recognition. Affine invariance is obtained by a representation which is based on a new sampling configuration in the frequency domain. We discuss the decomposition of affine transform into slant, tilt, swing, scale and 2D translation by applying singular value decomposition (SVD). The affine invariant spectral signatures (AISS) are derived from a set of Cartesian logarithmic-logarithmic (log-log) sampling configuration in the frequency domain. The AISS enables the recognition of image patches that correspond to roughly planar object surfaces-regardless of their poses in space. Unlike previous log-polar representations which are not invariant to slant (i.e. foreshortening only in one direction), the AISS yields a complete affine invariance. The proposed log-log configuration can be employed either by a global Fourier transform or by a local Gabor transform. Local representation enables one to recognize separately several objects in the same image. The actual signature recognition is performed by multi-dimensional indexing in a pictorial dataset. 3D pose information is also derived as a by-product.
01 Jan 1997
TL;DR: A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime.
Abstract: A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime. The GesRec system is introduced which provides a framework for data acquisition, training, recognition, and gesture-to-speech transcription in a Windows environment. A recognition accuracy of 92.5% was obtained for the hybrid system, compared to 89.6% for the neural network only and 82.7% for rules only. Training and recognition times are given for an able-bodied and a disabled user.
Proceedings Article•
01 Jan 1997
TL;DR: Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.
Abstract: This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.
21 Apr 1997
TL;DR: A stochastic framework for the recognition of binary random patterns which advantageously combine HMMs and Markov random fields (MRFs), andpects concerning definition, training and recognition via this type of model are developed.
Abstract: We present a stochastic framework for the recognition of binary random patterns which advantageously combine HMMs and Markov random fields (MRFs). The HMM component of the model analyzes the image along one direction, in a specific state observation probability given by the product of causal MRF-like pixel conditional probabilities. Aspects concerning definition, training and recognition via this type of model are developed throughout the paper. Experiments were performed on handwritten digits and words in a small lexicon. For the latter, we report a 89.68% average word recognition rate on the SRTP French postal cheque database (7057 words, 1779 scriptors).
18 Aug 1997
TL;DR: A tool for visualizing hidden Markov recognizers (HMR) which allows the developer to get a detailed view of the recognition process using an appropriate processing and visualization tool.
Abstract: The article describes a tool for visualizing hidden Markov recognizers (HMR) which allows the developer to get a detailed view of the recognition process. Improvements are suggested for a hidden Markov recognizer using an appropriate processing and visualization tool.
09 Sep 1997
TL;DR: The minimum number of training required to achieve an acceptable level of accuracy for a speaker dependent speech recognition system based on the hidden Markov model (HMM) is investigated and a method is proposed which retains the same degree of accuracy of recognition with much reduced training.
Abstract: One of the problems faced in automatic speech recognition is the amount of training required to adapt the machine to the speaker way of pronunciation. To a certain extent, the accuracy of correct recognition is proportional to the amount of training and adaptation carried out. This is especially true when a large vocabulary is involved. For certain applications, it is desirable that the training requirement be reduced to the bare minimum without sacrificing the accuracy of recognition. The minimum number of training required to achieve an acceptable degree of accuracy for a speaker dependent speech recognition system based on the hidden Markov model (HMM) is investigated. A method is also proposed which retains the same degree of accuracy of recognition with much reduced training.
28 Apr 1997
TL;DR: It is shown that the evaluation of predicates leads to a classical problem of retrieval on secondary keys and the so-called false drop probability in the context of key-based image recognition, and a 2-level scheme is considered which can be employed because of a suboptimal choice of parameters.
Abstract: First of all we show that the evaluation of predicates leads to a classical problem of retrieval on secondary keys. After a brief sketch of the signature file technique we collect some known probabilistic results. This allows us to treat two distinct mathematical models simultaneously. We then consider the so-called false drop probability in the context of key-based image recognition. It is shown that known optimality results do not necessarily remain valid in this situation. This suggests shifting the emphasis from optimizing the false drop probability to optimizing the search time (both aims do not necessarily coincide). Thus we are led to consider a 2-level scheme which is simple compared to other 2-level schemes which have been used before. This scheme can be employed because of a suboptimal choice of parameters. Finally theoretical predictions derived from a somewhat crude abstract model are validated by experimental work carried out on a Smalltalk prototype. Encouraging results are obtained.
12 Oct 1997
TL;DR: An approach for weighting the contribution of the acoustic and visual sources of information in a bimodal connected speech recognition system that considers that a different acoustic-labial weight is attached to each recognition unit.
Abstract: Describes an approach for weighting the contribution of the acoustic and visual sources of information in a bimodal connected speech recognition system. We consider that a different acoustic-labial weight is attached to each recognition unit. The values of the weighting vector are optimised in order to minimise the error rate on a learning set. Experiments are performed on a two-speakers audiovisual database, composed of connected letters, with two different acoustic-labial speech recognition systems. For both speakers and both systems, the weights optimisation allows us to increase the recognition rate of our bimodal system.