C. Pedraza, Jaime Vitola, J. Sepúlveda, J. Martínez
{"title":"Fast content-based audio retrieval algorithm","authors":"C. Pedraza, Jaime Vitola, J. Sepúlveda, J. Martínez","doi":"10.1109/STSIVA.2013.6644941","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644941","url":null,"abstract":"Fingerprinting is one of the most used techniques for searching and identification audio with a wide spectrum of applications. Different algorithms defines different fingerprint extraction and the match techniques, with different efficiency, computational load, robustness, response time and location search. Nowadays music audio retrieval faces two main challenges in order to be efficient: robustness and speed. This article proposes a fast algorithm to the audio content-based retrieval with the fingerprint technique, based on the extraction of the frequency features of the audio and a hash function. Experiments determined a high success rate and a response time lower than other techniques, optimal to real time applications like monitoring radio stations or songs identifying.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124797997","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}
E. Morales, G. Saurez Martinez, Carlos Cabal Mirabal, Evelio González Dalmau
{"title":"Tool of segmentation and 3D reconstruction of MRI to quantify cranial tumor activity","authors":"E. Morales, G. Saurez Martinez, Carlos Cabal Mirabal, Evelio González Dalmau","doi":"10.1109/STSIVA.2013.6644914","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644914","url":null,"abstract":"Currently in the biomedical field of image processing software are used for quantitative measurement of tumor lesions, but the analysis of longitudinal studies has limitations; mainly for monitoring of treatment effect and some of this software are owners. Existing software from brain tumor diagnosis and evaluation treatment is a manual process of mensuration of the size of the tumor and alone slide measurement selected, without one a tool that integrates all the functionalities for the quantitative evaluation of the lesions and applied treatments. This justifies finding new and validated tools for imaging biomarkers (IB) applied to magnetic resonance image (MRI). A series of 29 pediatric patients, 14 females and 15 males, between 3 to 18 years, with confirmed malignant brain tumors and treated with a monoclonal antibody nimotuzumab, were evaluated during 2 years for to validate IB-MRI. The MRI were obtained with a 1.5 T MR Symphony Maestro Class System (Siemens, Germany). The protocol included weighted images in T2, T1 and FLAIR. A tool developed in Matlab was obtained. Segmentation and reconstruction methods in three dimensions (3D) were applied and were also integrated in a single interface to integrate others separate tools. Additionally includes the use of an automated method of segmentation of background noise that reduces the amount of points to be processed. The volumes calculated overlap each technique reflecting different biological realities. Our tool is effective to quantitatively evaluate the antitumor effect to treatment.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127399520","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":"RASCAN type radar image resolution enhancement for non-metallic landmine detection","authors":"Andrés Quintero-Zea, Marisol Osorio-Cardenas","doi":"10.1109/STSIVA.2013.6644923","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644923","url":null,"abstract":"Category 3. This paper presents two resolution enhancement techniques applied to images of buried landmines acquired using a RASCAN radar, a holographic radar that is used mainly for sounding structural components of buildings, although it can be used to find buried objects too. The first technique is a phase-driven spatially variant regularization, and the second one is a wavelet-based image interpolation.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125373841","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}
Juan F. Molina, R. Gil, C. Bojacá, Gloria Díaz, Hugo Franco
{"title":"Color and size image dataset normalization protocol for natural image classification: A case study in tomato crop pathologies","authors":"Juan F. Molina, R. Gil, C. Bojacá, Gloria Díaz, Hugo Franco","doi":"10.1109/STSIVA.2013.6644938","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644938","url":null,"abstract":"In computer vision research, the construction of image datasets is a critical process, given the need for robust experimentation frameworks that ensure the quality and validity of the resulting conclusions and performance measurements in each particular study. Therefore, experimental datasets must optimize their statistical, visual and computational properties through an adequate selection of representative and useful visual data, according to the specific research question being addressed. This paper proposes a dataset construction protocol for ad hoc acquired images in a particular Machine Learning application: tomato crop health assessment.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122631665","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}
Carlos A. Gutiérrez, Xavier García, E. Zurek, Augusto Salazar
{"title":"Statistical model of a signal of Raman spectroscopy: Detection","authors":"Carlos A. Gutiérrez, Xavier García, E. Zurek, Augusto Salazar","doi":"10.1109/STSIVA.2013.6644935","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644935","url":null,"abstract":"Raman spectroscopy (RS) is a technique to find the spectral fingerprint of a material under study. To reach the spectrum, it is necessary to pass the acquired signal at the spectrometer by a bank of filters known as Raman signal's preprocessing system, which should eliminate all noise components accompanying the signal. The behavior of these noise components, and even the signal itself, are information that can be useful in order to optimize the system and to study the signal itself. This paper proposes a statistical model of Raman signal as the pre-processing system receives it, the signal's noise components and their statistical behavior, including its mathematical representation are presented. Additionally, it shows the results of the implementation of the simulation model leaving the door open for the validation, on which work is being done. The implementation of this model may be useful as an input signal for the optimization of the filter banks, since there are not always sufficient Raman signals for detailed study and development of filters for a specific signal under study. The model could also be used as a base for the study for systems using Raman spectroscopy to recognize substances.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131210721","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":"Strawberries collecting robot prototype in greenhouse hydroponic systems","authors":"Edwin Saenz, Mario Jimenez, Andrés F. Ramirez","doi":"10.1109/STSIVA.2013.6644933","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644933","url":null,"abstract":"In the last decades, the agricultural sector development has been oriented to the optimization in planting spaces, seeking to reduce resources and the procurement of the best products with low levels of fertilizers, insecticides, and fungicides, among others. One example of farming are greenhouse hydroponic systems, which optimize resources for obtaining a higher density of sowing and the highest performance per unit area is the strawberry cultivation. For the harvest process, the farmers use of the qualitative observation for classifying the strawberry, using that selection process take considerable time that can be optimized. Due to the aforementioned problems, the aim of this project is to develop a strawberries collecting robot prototype in greenhouse hydroponic systems, using artificial vision for identifying the state of ripeness based on reddish tonality of strawberries.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"87 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113996343","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}
Andres Rodriguez, S. A. Orjuela Vargas, W. Philips
{"title":"Robust video feature extraction invariant to natural lighting by using LBP techniques with adaptive thresholding","authors":"Andres Rodriguez, S. A. Orjuela Vargas, W. Philips","doi":"10.1109/STSIVA.2013.6644942","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644942","url":null,"abstract":"Real time applications in video processing require low computational cost algorithms that allow processing a considerable number, commonly 25, of frames per second. Particularly, in outdoor visual scenes, a challenge is to develop robust algorithms with environmental conditions such as natural lighting. We propose to compute an adaptive threshold based on de probability distribution of the differences in intensity between the pixels and the points on their neighborhoods when applying the LBP technique. We assume, and prove it experimentally, that such distribution is a generalized Gaussian distribution under normal conditions. We consider normal conditions a visual scene in an outdoor field composed of different objects, colors and textures. To compute the adaptive threshold, we first estimate the parameters of the generalized Gaussian distribution using the set of all differences in the image between the intensity values of pixels and points in the neighbourhood. We test the methods on four videos captures during day and night in different places in the city of Ibague. The results of this approach are of interest to determine patterns, identify objects or detect background in a further step. However, an extra step for blur correction must be still included, considering that the images of the frames at night are commonly blurred.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127517410","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}
A. F. Torres-Monsalve, J. D. Bolanos-Jojoa, Jaime Velasco-Medina
{"title":"Design of 2-D filters for video processing using FPGAs","authors":"A. F. Torres-Monsalve, J. D. Bolanos-Jojoa, Jaime Velasco-Medina","doi":"10.1109/STSIVA.2013.6644915","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644915","url":null,"abstract":"Image and video processing algorithms implemented in software, require most computation time when the image-size is increased. However, for real time applications the algorithms must be processed at high-speed, for example 2-D filter algorithms. Then, in order to address this inconvenient, the algorithms must be implemented in hardware. In this paper, we present the hardware architectures for 2-D FIR filters and a median filter. The designs are described using generic structural VHDL and synthesized on the FPGA EP2C70F896C6N. The architectures were verified using an image acquisition system based on the D5M camera and the DE2-70 development kit of Terasic.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132765873","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":"Evaluation of Mean, Gaussian and S&G aggregation windows in stereo correspondence under presence of noise","authors":"F. Calderon, C. Parra, Cesar L. Nino","doi":"10.1109/STSIVA.2013.6644940","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644940","url":null,"abstract":"Few topics in image processing have been as extensively studied as stereo correspondence, these algorithms can be divided into two categories, local and global, depending on how the processing is done in the image. A stereo correspondence algorithm is called local if operate on sections of the images and global this treatment is performed on the entire images. In local algorithms specifically, this aggregation window is used for smoothing volume pairing cost, so that a better match is performed in presence of fronto-parallel regions. This article presents a comparison between Mean, Gaussian and Savitzky-Golay aggregation windows in local algorithms, analyzing the noise in test images and how the selection of the aggregation window affects the performance of the stereo matching algorithm.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131744482","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":"An interactive floor for shape-based interactions using a client-server architecture","authors":"Gonzalo Luzardo, B. Guamán, K. Chiluiza","doi":"10.1109/STSIVA.2013.6644917","DOIUrl":"https://doi.org/10.1109/STSIVA.2013.6644917","url":null,"abstract":"Interaction with large surfaces such as walls and floors has become an interesting topic among scholars and researchers. Several approaches to implement such surfaces have been explored, as well as ways of evaluating its user interaction. The objective of this paper is three-folded: first, it sought to shed light on how to implement a low-cost computer vision interactive floor, based on a shape-based interaction approach (conversely, to the common point-based interaction approach used in other solutions); second, the performance of the client-server system was studied; third, a usability study was set up and examined quantitatively the users' satisfaction and realism of their interaction with the system. The results demonstrated that a maximum of four people can interact simultaneously compromising the CPU usage up to 50% on the server and up to 90% on the client. The network traffic was also analyzed showing that due to the simplifications of the shapes sent from the server to the client, the traffic was between 127 Kbps and 759 Kbps. Moreover, the user experience and realism are enhanced using the approach proposed. Conclusions and perspectives for further development and future work are presented at the end of the article.","PeriodicalId":359994,"journal":{"name":"Symposium of Signals, Images and Artificial Vision - 2013: STSIVA - 2013","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127741788","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}