{"title":"Analysis of mutli-spectral images from cardiovascular tissue by means of blind source separation methods","authors":"J. Galeano, S. Perez, Deivid Botina, J. Garzon","doi":"10.1109/STSIVA.2014.7010167","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010167","url":null,"abstract":"This article presents the use of blind source separation methods for the decomposition of cardiovascular tissue multi-spectral images in its main morphological components. The evaluated images were acquired with two kinds of systems: one based in a confocal configuration and another based in interference filters. The implemented source separation algorithms are based on a multiplicative coefficient upload and on Principal Component Analysis (PCA) techniques. The goal is to represent a given multi-spectral image as the weighted sum of different components. The resulting weighted coefficients are used to quantify the content of the main components in a given multi-spectral image. The methodology is validated on cardiovascular bovine tissue. The results show that PCA not only allows image reduction but also an increase in the image contrast. This fact allows for a better determination of the tissue's structure. Also, the result of applying NMF shows that the method allows for maps that quantify the principal chromophores that compose cardiovascular tissue.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122987745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Image segmentation blood vessel of retinal using conventional filters, Gabor Transform and skeletonization","authors":"William Lasso, Y. Morales, C. Torres","doi":"10.1109/STSIVA.2014.7010170","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010170","url":null,"abstract":"This paper implements a digital algorithm that allows the segmentation and skeletonization of digital images, this method is very important in the processing of retinographies images, where of analysis inside of the eye enables early detection of diseases such as Diabetic Retinopathy. The algorithm implemented using the Fourier transforms and Gabor Transform two-dimensional and conventional filters. The performance of algorithm under mathematical platform the Matlab implemented has been compared with conventional methods obtaining resulting filtered images with better contrast and higher resolution.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134348514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Gesture recognition system for surgical robot's manipulation","authors":"Hermes F. Vargas, O. A. Vivas","doi":"10.1109/STSIVA.2014.7010172","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010172","url":null,"abstract":"This paper presents a newfangled gesture recognition system for handling two surgical robots in a virtual simulator. The two robots are designed to perform laparoscopy, in order to provide a basis for a surgical trainer. Originally the system is commanded by a joystick, but the inclusion of the new Leap Motion device allows the simulator to be handled by the gestures of the user's hands, which makes it more natural in its management. This device uses infrared signal processing to determine the position and orientation of the objects that are above him and promises to improve the user experience and the usability of 3d applications using natural interfaces instead of mechanical devices.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123937559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving kinematic lab practices by image processing","authors":"Antonio Ramos Murillo, J. I. Marin-Hurtado","doi":"10.1109/STSIVA.2014.7010185","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010185","url":null,"abstract":"Several studies, including the most recent report of the Program for International Students Assessment, accompanied by the annual measurements by the Colombian Institute for Education Evaluation ICFES (for its acronym in Spanish: Instituto Colombiano para la Evaluación de la Educación) agree an obvious deficiency of students tested, both in the apprehension of different knowledge areas, as well as their skills and competences to solve problems on daily situations. Given this weakness and taken into account the relevance of incorporating Information Technology and Communications (ICT) in the teaching process, we develop a software that supported on the Kinect™ sensor, captures images from certain physics lab experiments. This application also extracts information from the real-time experiment to generate an interface in Augmented Reality (AR) that visualizes some specific physical parameters.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122498303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Villa-Cañas, J. Orozco-Arroyave, J. Vargas-Bonilla, J. D. Arias-Londoño
{"title":"Modulation spectra for automatic detection of Parkinson's disease","authors":"T. Villa-Cañas, J. Orozco-Arroyave, J. Vargas-Bonilla, J. D. Arias-Londoño","doi":"10.1109/STSIVA.2014.7010173","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010173","url":null,"abstract":"In this paper, we explore the information provided by a joint acoustic and modulation frequency representation, referred as modulation spectrum, for detection of people with Parkinsons disease through speech signals. The set of features includes the centroids and the energy content of different frequency bands in the modulation spectra of the recordings. Additionally, with the aim to eliminate possible redundancy in the information provided by the features, two different feature extraction techniques are applied, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). The classification was done by means of Gaussian mixture model (GMM). The results show that this approach is acceptable for this purpose, with the best accuracy around 71% for vowel /i/.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124457985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Frequency band displacement for optimizing acoustic boxes above the natural frequency of the loudspeaker","authors":"Albert M. Cruz, Marcelo Herrera Martínez","doi":"10.1109/STSIVA.2014.7010161","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010161","url":null,"abstract":"This project deals with the implementation of an algorithm for frequency band displacement for the optimization of acoustic boxes. This is particularly relevant in the Car-audio industry and similar applications, when limitations of volume and space are present. The work gives an alternative solution to the problem of huge acoustic boxes sizes for the reproduction of low frequencies, using DSP, optimizing small boxes with midrange loudspeaker, without losing the information in the low frequency region. In this paper, information about loudspeaker design and performance is held, as well as the development of an algorithm that analyzes the input signal through the FFT, in order to adapt the fundamental frequency of the input signal to a basic home system or car audio. Analyzing the results of the transfer function it can be observed how the input signal adapts, reaching the optimization of the frequency response of the sound box above the natural frequency of the loudspeaker.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128710582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Diego Hernán Peluffo-Ordóñez, E. J. Revelo-Fuelagán
{"title":"Novel spectral characteristics of the electrical current waveform to quantifying power quality on LED lamps","authors":"Diego Hernán Peluffo-Ordóñez, E. J. Revelo-Fuelagán","doi":"10.1109/STSIVA.2014.7010182","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010182","url":null,"abstract":"LED lamps are widely used in household, nonetheless they are still non-linear. Therefore, LEDs need a power supply system to correcting their operation, which introduces nonlinearities into the electrical grid and distortions on waveform. Then analysis and quantification of electrical signals is becoming a key issue. This work presents a spectral analysis of analysis of electric current signal in LEDs lamps which yields a novel collection of characteristics and measures to quantify the waveform quality. In particular, periodogram and Fourier transform are considered. For experiments, two circuits are considered: one that corresponds to the commercial LEDs lamp connected to AC source and another one incorporating a power factor corrector. Experimentally, the usefulness and applicability of proposed characteristics is proved.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"288 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116391277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Background thermal compensation by filtering (BTCF) for infrared thermography evaluation","authors":"A. Restrepo-Girón, H. Loaiza-Correa","doi":"10.1109/STSIVA.2014.7010162","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010162","url":null,"abstract":"A new contrast enhancement technique is presented for application in active thermography inspection, based on a decimated version of median filtering to decouple the background thermal information from defective areas, without depending on any heat propagation model or the a priori selection of a healthy region. Results over inspected carbon fiber reinforced plastic (CFRP) slabs show that BTCF can reduce in 70% the residuary non-uniformity heating, and after truncation of negative contrast values, it can be obtained an improvement up to 11dB in SNR with respect to original sequences.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"20 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116778312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. J. I. Padilla, Jonathan Avendao, D. German Castellanos
{"title":"Causality analysis of P300 recordings focused on the localization of active brain areas","authors":"B. J. I. Padilla, Jonathan Avendao, D. German Castellanos","doi":"10.1109/STSIVA.2014.7010127","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010127","url":null,"abstract":"This paper focuses on the causal influence in the brain. These effects are analyzed by stimulating visually or aurally a patient with an external sensorial stimulus and investigating the outcome into the brain (event-related potentials) in order to detect causal influences from one neuron or neuronal population to another. This analysis is achieved by applying time varying multivariate autoregressive models to the ERP signals. The causal interaction is measured using the Granger Causality Index (GCI). The obtained results using causality can validate the analysis performed by an specialist, and they demonstrate the causal interactions between electrophysiological signals of different sites of the cortex, occurring during cognitive processes related with ERP.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116301455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Collazos-Burbano, J. L. Ealo Cuello, G. Torres, A. Barandica, T. G. Gomez Alvarez-Arenas
{"title":"Air-coupled ultrasound spectroscopy and its potential application in agro-industry","authors":"D. Collazos-Burbano, J. L. Ealo Cuello, G. Torres, A. Barandica, T. G. Gomez Alvarez-Arenas","doi":"10.1109/STSIVA.2014.7010158","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010158","url":null,"abstract":"Ultrasonic Spectroscopy (US) is a new alternative technique to extract parameters of vegetal tissues and properties of agro-industrial materials. The US technique involves a set-up in transmission of air-coupled ultrasonic transducers to make inspections contactless and in a non-invasive way. This is an advantage for some samples which cannot be in contact with the sensorial system. In this work we have tested Helliconia leaves and paper samples, focusing in the extraction of mechanical properties as density, acoustic velocity, acoustic attenuation and thickness of samples. Special interest is the relationship between the natural vibration mode and the water content in Helliconia leaves. The extraction of properties involves the solution of an inverse problem associated with the transmission of acoustic waves in three media (air-sample-air). Results show that estimation of these characteristics can be obtained with errors less than 12%. Also, a sensitivity analysis was performed to study how well the numerical method works in presence of noise, obtaining minimum errors in computations at signals to noise ratios as low as 6dB.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"372 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124662015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}