Karina Toscano

Fingerprint Recognition

Fingerprint recognition is one of the most popular and successful methods used for person identification, which takes advantage of the fact that the fingerprint has some unique characteristics called minutiae; which are points where a curve track finishes, intersect with other track or branches off. Biometric identification systems using fingerprints patterns are called AFIS (Automatic Fingerprint Identification System). In this paper a novel method for Fingerprint recognition is considered using a combination of Fast Fourier Transform (FFT) and Gabor Filters to enhancement the fingerprint image was captured using a UareU 4000 fingerprint reader of Digital Person, Inc.

Multimodal biometric system using fingerprint

Fingerprint recognition is one of the most popular methods used for identification with greater degree of success. The fingerprint has unique characteristics called minutiae, which are points where a curve track finishes, intersect or branches off. Identification systems using fingerprints biometric patterns are called AFIS (Automatic Fingerprint Identification System). In this work a method multi-biometric is considered using a combination of Fast Fourier Transform (FFT) and Gabor Filters to enhancement the image and later a novel stage of recognition using Local Features and Statistical Parameters.

Cursive Character Recognition System

During the last two decade, numerous handwriting character recognition systems have been proposed. Many of them presented their limitation when the handwriting character is cursive type and it has some deformation. However this type of cursive character is easily recognized by the human being. In this paper we research its human ability and apply it to the dynamic handwriting character recognition. In the proposed system, significant knots of each character are extracted using natural spline function named SLALOM and their position is optimized steepest descent method. Using a training set consisting of the sequence of optimal knots, each character model is constructed. Finally the unknown input character is compared with each model of all characters to get the similarity scores. The character model with higher similarity score is considered as the recognized character of the input data. The recognition stage consists in two-steps: classification using global feature and classification using local feature

Security attack prediction based on user sentiment analysis of Twitter data

In recent years, security attacks on the web have been perpetrated by hacker activist organizations that aim to destabilize (using different techniques) web services in a specific context for which they are motivated. Predicting these attacks is an important task that helps to consider what actions should be taken if the attack is latent. Although there are applications to detect security threats on the web, currently there is no system that can predict or forecast whether the attacks can reach consummation. This paper presents a sentiment analysis method on Twitter content to predict future attacks on the web. The method is based on the daily collection of tweets from two sets of users; those who use the platform as a means of expression for views on relevant issues, and those who use it to present contents related to security attacks in the web. Daily information is converted into data that can be analysed statistically to predict whether there is a possibility of an attack. The latter is done by analyzing the collective sentiment of users and groups of hacking activists in response to a global event.

A novel parallel multiplier using spiking neural P systems with dendritic delays

High performance spiking neural multiplier.Parallel input data processing in SN P systems.Scalable parallel architecture based on SN P systems. In the last 10 years, there has been a considerable increase in the number of studies on the development of multiplier circuits based on spiking neural P systems with the aim of taking advantage of their intrinsic distributed parallel computing characteristics. Nevertheless, these efforts have had difficulties in adequately exploiting parallel data processing because they are designed to process the input data using a sequential protocol and thus suffer from the resulting increase in processing time. This paper develops a novel parallel multiplier that is based on spiking neural P systems and is capable of multiplying two natural numbers with many digits in parallel. The proposed method employs the divide and conquer strategy (i.e., segmenting the numbers into units, tens, hundreds, thousands, etc.), to optimize the processing time of the arithmetic operations, and every two units are treated by a single neuron that can calculate up to 9 9 sequentially. The use of one neuron to perform a sequential multiplication represents the best improvement in terms of the number of neurons that has been reported to date.

Fingerprint Recongnition Using Espatial Minutae Information

A fingerprint is the visible impression or molded that papillary produces with the papillary crest contact in a surface. It depends on the conditions under which the fingerprint is made, and the support characteristics (plastics or soft matters in due conditions), however, it is an individual characteristic that is used as a main pattern for people identification. In this research the image enhancement is carry out using FFT (Fast Fourier Transform) and Gabor filters, the minutiae extraction approach is done to obtain a characteristic vector which has distance, angle and minutiae coordinates those vectors will be used for training and recognition.

View-Invariant Gait Recognition Using a Joint-DLDA Framework

In this paper, we propose a new view-invariant framework for gait analysis. The framework profits from the dimensionality reduction advantages of Direct Linear Discriminant Analysis (DLDA) to build a unique view-invariant model. Among these advantages is the capability to tackle the under-sampling problem (USP), which commonly occurs when the number of dimensions of the feature space is much larger than the number of training samples. Our framework employs Gait Energy Images (GEIs) as features to create a single joint model suitable for classification of various angles with high accuracy. Performance evaluations shows the advantages of our framework, in terms of computational time and recognition accuracy, as compared to state-of-the-art view-invariant methods.

Frequency-Based Fingerprint Recognition

abstract Fingerprint recognition is one of the most popular methods used for identification with greater success degree. Fingerprint has unique characteristics called minutiae, which are points where a curve track ends, intersects, or branches off. In this chapter a fingerprint recognition method is proposed in which a combination of fast Fourier transform (FFT) and Gabor filters is used for image enhancement. A novel recognition stage using local features for recognition is also proposed. Also a verification stage is introduced to be used when the system output has more than one person.

Aerial image classification using texture and color-based descriptors

In this paper, we evaluate eleven image descriptors for urban-rural classification using aerial images. The eleven image descriptors are composed by seven texture-based descriptors and four combinations of texture and color descriptors. The classification is carried out using Support Vector Machine (SVM) with radial basis function as kernel function. The performance of these images descriptors are evaluated using accuracy, precision, sensitivity and specificity. From the evaluation, the combination of Gabor descriptor and Dominant Color descriptor provides a better performance, obtaining accuracy more than 91%.

New optimized approach for written character recognition using symlest wavelet

The technological changes over the time, have allowed todays society focuses on the acquisition of all types of electronic documents, which is why there is a need to implement new systems to help us in the handwriting characters recognition field, since 70s years have been made research in this area but there are still problems without a solution, especially in cursive handwriting characters recognition In recent years there have been various schemes aimed at handwritten character recognition for automatic database applications creation in libraries, automatic reading checks, among others. That is why this research proposes an algorithm for cursive character recognition, which is to obtain the characteristic points of each character, which are interpolated using the Natural Spline Function. The handwriting characters recognition process is developed in inverse order using wavelet by its smoothing properties, also compare the performance system using three different classifiers: SVM (Support Vector Machines), GMM (Gaussian Mixture Model) and ANN (Artificial Neural Network)