Simina Emerich

On-line signature recognition approach based on wavelets and Support Vector Machines

In this work, a new on-line signature verification system is proposed. Firstly, the pen-position parameters of the online signature are decomposed into multiscale signals by using the wavelet transform technique. A TESPAR DZ based method is employed to code the approximation and details coefficients. Thus, for each analyzed time function, a fixed dimension feature vector is obtained. Experimental results were reported using the SVC2004 database. The models were trained and tested with the Support Vector Machine classifier. A feature level fusion strategy was adapted.

A new set of features for a bimodal system based on on-line signature and speech

In this work, a new set of features is presented for a biometric system based on speech and on-line signature. The feature vector is nonhomogeneous and it comprises using TESPAR DZ coefficients, wavelet energy coefficients and also some additional features resulted from the time domain analysis in the case of speech. A feature selection procedure is then applied to reduce the feature vector dimension. A modified symbols alphabet for the TESPAR DZ method is presented. Experimental results were reported using the SVC2004 database for signature and our own bimodal database BimDB10 (for on-line signature and speech). A feature level fusion strategy was adapted in order to achieve our goals. The results show that the fusion of biometric features brings improvement to the system performance.

Bimodal approach in emotion recognition using speech and facial expressions

This paper aims to present a multimodal approach in emotion recognition which integrates information from both facial expressions and speech signal. Using two acted databases on different subjects, we were able to emphasize six emotions: sadness, anger, happiness, disgust, fear and neutral state. The models in the system were designed and tested by using a Support Vector Machine classifier. Firstly, the analysis of the strengths and the limitations of the systems based only on facial expressions or speech signal was performed. Data was then fused at the feature level. The results show that in this case the performance and the robustness of the emotion recognition system have been improved.

A new approach to iris recognition

This paper focuses on the development and implementation of a biometric system based on iris. Our approach is different from the most common solution presented in the references, as it proposes a mixture between the wavelet and the TESPAR DZ approaches applied to images. The results provided by our experiments are close to those presented in the literature.

A generic platform to study the basic aspects of DVB-IPTV conversion process

Paper describes briefly the basic concepts and a practical implementation for an original generic platform able to acquire, create and distribute IPTV content, using as primary sources DVB or locally stored video content. A clearly unusual, original feature, is the fact that the system includes both components of the bridge, RF/baseband DVB processing and IPTV streaming elements in an integrated architecture. The architecture is conceived to implement multiple test scenarios. This is particularly important in the educational environment, to clarify this mélange of technologies ranging from video acquisition or RF transmission to networking and embedded systems. Audio-video content is gathered by different traditional technologies: DVB-S, CATV Headend, video streaming servers. This experimental network is intended to be used for throughput, QoS or audio-video quality measurements. The system is used to test even possible hardware/software implementations of commercial systems. The versatility of this system is proven by implementation of few basic test scenarios. Most relevant features of the system and tests implemented in this configuration are described in the final paragraphs of the paper.

Combustion sound classification employing Gaussian Mixture Models

This paper presents a method suitable for the detection of various states of combustion in progress by means of sound analogy analysis. Visual inspection, electro-chemical transducers or analyzing the sound produced during the burning process consist of means by which the quality of the burning process can be assessed. The results may be used when taking decisions with the goal of optimally controlling the combustion process. Classification was performed by using the GMM (Gaussian Mixture Models), the parameters extracted from the recorded sound being the phase parameters and the MFCC (Mel-frequency cepstral coefficients) coefficients. The results prove to be promising and encourage future research in the acoustic relevance in burning quality detection.

Patch based descriptors for iris recognition

In recent years, local texture analysis methods have gained increasing attention in many areas of image processing and computer vision. The current paper deals with iris features extraction, based on dense descriptors. A dense descriptor captures the local details, pixel by pixel over the complete image. Three different techniques were employed: Local Binary Pattern, Local Phase Quantization and Differential Excitation in order to provide both spatial and frequency information. To evaluate the proposed system, experiments were performed on the UPOL database, by using a linear SVM classification scheme. The results show that the iris micro-texture patterns such as crypts, furrows or pigment spots can be well characterized by patched based descriptors.

Image Analysis and Coding Based on Ordinal Data Representation

With the use of computers and Internet in every major activity of our society, security is increasingly important. Biometric recognition is not only challenging but also computationally demanding. This chapter aims develop an iris biometric system. The iris has the advantages of uniqueness, stableness, anti-spoof, non-invasiveness and efficiency and could be applied in almost every area (banking, forensics, access control, etc.). The performance of a biometric classification system is largely depending on the techniques used for feature extraction. Inspired by the biological plausibility of ordinal measures, we propose their employment for iris representation and recognition. Qualitative measurement, associated to the relative ordering of different characteristics, is defined as ordinal measurement. Besides the proposing of a novel, fast and robust, ordinal based feature extraction method, the chapter also considers the problem of designing the decision making model so as to obtain an efficient and effective biometric system. In the literature, there are different approaches for iris recognition, nevertheless, there are still challenging open problems in improving the accuracy, robustness, security and ergonomics of biometric systems.

Random forest feature selection approach for image segmentation

In the field of image segmentation, discriminative models have shown promising performance. Generally, every such model begins with the extraction of numerous features from annotated images. Most authors create their discriminative model by using many features without using any selection criteria. A more reliable model can be built by using a framework that selects the important variables, from the point of view of the classification, and eliminates the unimportant once. In this article we present a framework for feature selection and data dimensionality reduction. The methodology is built around the random forest (RF) algorithm and its variable importance evaluation. In order to deal with datasets so large as to be practically unmanageable, we propose an algorithm based on RF that reduces the dimension of the database by eliminating irrelevant features. Furthermore, this framework is applied to optimize our discriminative model for brain tumor segmentation.

Half iris biometric system based on HOG and LIOP

Automatic iris recognition is becoming increasingly important technique for identity management and hence security. In the computer vision domain and mainly in the image recognition applications, the possibility to compare affined images, which could be distinguished just through small differences, is highly important. Using local image descriptors, similar images could be identified, although they are not part of the same scene or they have a changed parameter. Implemented systems show that HOG (Histogram of Oriented Gradients) and LIOP (Local Intensity Order Pattern) descriptors are promising for human recognition based on iris texture. Experimental results are reported on two public databases: UPOL and CASIA_V1.