Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010132
E. Dianderas, K. Rojas, G. Kemper
In this article is developed a technique that allows to calculate the presence of vegetation, glaciers and water bodies through multispectral image processing employing a Multi-layer Perceptron Neural Netwok, giving the option to discriminate the presence of lakes to generate the cadastral registration of these. The supervised classification that was implemented has a high level of robustness and reliability, since the validation of the data obtained at a geolocation level have a 0% of error and the parameters of the area and perimeter an approximate error of 10%.
{"title":"Identification and cadastral registration of water bodies through multispectral image processing with multi-layer Perceptron Neural Network","authors":"E. Dianderas, K. Rojas, G. Kemper","doi":"10.1109/STSIVA.2014.7010132","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010132","url":null,"abstract":"In this article is developed a technique that allows to calculate the presence of vegetation, glaciers and water bodies through multispectral image processing employing a Multi-layer Perceptron Neural Netwok, giving the option to discriminate the presence of lakes to generate the cadastral registration of these. The supervised classification that was implemented has a high level of robustness and reliability, since the validation of the data obtained at a geolocation level have a 0% of error and the parameters of the area and perimeter an approximate error of 10%.","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":"121109817","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010159
Horderlin Vrangel Robles, V. Molina, Luis Martinez, Hermann Dávila
The results obtained after comparing several algorithms which use basic methods of signal processing for speech activity detection of voice or VAD (Voice Activity Detection-VAD), were assessed in order to determine their effectiveness. The algorithms presented in this article are short-time or spectral energy based endpoint detection algorithm, the zero crossing rate method, and the higher order differential (High Order Difference, HOD) method. First, an introduction of the concept of VAD is presented and the need to apply such language algorithms in River Plate is Spanish. Then a summary of the state of the art techniques and algorithms for detecting voice activity is shown with evidence and experiments used to implement algorithms with BEPPA corpus (Evaluation Battery for Patients with Auditive Prostheses, BEPPA - in Spanish).
{"title":"Evaluation and comparison using activity signals of speech methods in river plate spanish using BEPPA corpus","authors":"Horderlin Vrangel Robles, V. Molina, Luis Martinez, Hermann Dávila","doi":"10.1109/STSIVA.2014.7010159","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010159","url":null,"abstract":"The results obtained after comparing several algorithms which use basic methods of signal processing for speech activity detection of voice or VAD (Voice Activity Detection-VAD), were assessed in order to determine their effectiveness. The algorithms presented in this article are short-time or spectral energy based endpoint detection algorithm, the zero crossing rate method, and the higher order differential (High Order Difference, HOD) method. First, an introduction of the concept of VAD is presented and the need to apply such language algorithms in River Plate is Spanish. Then a summary of the state of the art techniques and algorithms for detecting voice activity is shown with evidence and experiments used to implement algorithms with BEPPA corpus (Evaluation Battery for Patients with Auditive Prostheses, BEPPA - in Spanish).","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"46 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":"127471517","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010187
Roger Gomez Nieto, J. I. Marin-Hurtado, Luis Miguel Capacho-Valbuena, Alexander Amaya Suarez, Elkyn Alexander Belalcazar Bolanos
The Cleft and Lip Palate (CLP) is a malformation with high recurrence in Colombia, which affects the ability of the phonation system, making difficult the effective communication of the patient. This research seeks to find patterns that enable to detect hypernasality without using invasive diagnostic methods. We performed an analysis of a large range of acoustic features to identify those capable of discriminating hypernasality. The analyzed features include: Teager energy operator (TEO), linear predictive coding (LPC), Mel Frequency Cepstral Coefficients (MFCC), Pitch, Jitter, Shimmer, and the first three formants together with the bandwidth of the first formant. With the correct configuration is achieved discriminant patterns classify 99 percent of patients hypernasal of the database with a false positive rate of less than 1 percent of healthy patients, which are promising results as a starting point for creating a tool for automatic noninvasive detection of hypernasality.
唇腭裂(Cleft and Lip Palate, CLP)是哥伦比亚一种复发率很高的畸形，它影响了发声系统的能力，使患者难以进行有效的沟通。本研究旨在寻找不使用侵入性诊断方法即可检测鼻音亢进的模式。我们进行了一个大范围的声学特征的分析，以确定那些能够区分高鼻音。分析的特征包括:Teager能量算子(TEO)、线性预测编码(LPC)、Mel频率倒谱系数(MFCC)、基音、抖动、闪烁、前三个共振峰以及第一共振峰的带宽。通过正确的配置，鉴别模式将数据库中99%的高鼻窦炎患者与不到1%的健康患者进行了分类，这是一个有希望的结果，可以作为创建自动无创检测高鼻窦炎工具的起点。
{"title":"Pattern recognition of hypernasality in voice of patients with Cleft and Lip Palate","authors":"Roger Gomez Nieto, J. I. Marin-Hurtado, Luis Miguel Capacho-Valbuena, Alexander Amaya Suarez, Elkyn Alexander Belalcazar Bolanos","doi":"10.1109/STSIVA.2014.7010187","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010187","url":null,"abstract":"The Cleft and Lip Palate (CLP) is a malformation with high recurrence in Colombia, which affects the ability of the phonation system, making difficult the effective communication of the patient. This research seeks to find patterns that enable to detect hypernasality without using invasive diagnostic methods. We performed an analysis of a large range of acoustic features to identify those capable of discriminating hypernasality. The analyzed features include: Teager energy operator (TEO), linear predictive coding (LPC), Mel Frequency Cepstral Coefficients (MFCC), Pitch, Jitter, Shimmer, and the first three formants together with the bandwidth of the first formant. With the correct configuration is achieved discriminant patterns classify 99 percent of patients hypernasal of the database with a false positive rate of less than 1 percent of healthy patients, which are promising results as a starting point for creating a tool for automatic noninvasive detection of hypernasality.","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":"116530222","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010188
Hernán García, C. A. Torres, Jorge Ivan Marin Hurtado
In this paper we present our framework for facial expression analysis using static models and kernel methods for classification. We describe the characterization methodology from parametric model. Also quantitatively evaluated the accuracy for feature detection and estimation of the parameters associated with facial expressions, analyzing its robustness to variations in pose. Then, a methodology of emotion characterization is introduced to perform the recognition. Furthermore, a cascade classifiers using kernel methods it is performed for emotion recognition. The experimental results show that the proposed model can effectively detect the different facial expressions. The model used and characterization methodology showed efficient to detect the emotion type in 93.4% of the cases.
{"title":"Facial expression analysis for emotion recognition using kernel methods and statistical models","authors":"Hernán García, C. A. Torres, Jorge Ivan Marin Hurtado","doi":"10.1109/STSIVA.2014.7010188","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010188","url":null,"abstract":"In this paper we present our framework for facial expression analysis using static models and kernel methods for classification. We describe the characterization methodology from parametric model. Also quantitatively evaluated the accuracy for feature detection and estimation of the parameters associated with facial expressions, analyzing its robustness to variations in pose. Then, a methodology of emotion characterization is introduced to perform the recognition. Furthermore, a cascade classifiers using kernel methods it is performed for emotion recognition. The experimental results show that the proposed model can effectively detect the different facial expressions. The model used and characterization methodology showed efficient to detect the emotion type in 93.4% of the cases.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"7 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":"127751166","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010128
Jose P. Pinilla, S. Plata, Oscar Alberto Mantilla, L. A. Rodriguez
Medical devices response is highly sensitive because of the dependence of human lives on them, thus common problems in electronics like synchronization and delays are often targeted to be reduced to its bare minimum. The use of FPGA ICs as co-processing slave modules for CPU chips in embedded systems is a common approach to solve these issues, not only among commercial medical equipment, but also in different industry sectors. This paper takes into account Medical Devices such as (Vital Signs Monitors) VSMs using this topology. Furthermore, a project at (Fundación Cardiovascular de Colombia) FCV to upgrade the PC-based systems used for Telemedicine services in Colombia, takes FPGAs as an integrated solution for an embedded system, achieving the replacement of the CPU and additional integrated circuits, with softcore architectures, IP cores, and hardware modules description. Moreover, critical applications such as medical devices need characteristics like real-time response and high accuracy in order to make health care personnel able to respond appropriately in case of an event. A working prototype, based on a Dual-Core architecture using the Nios II softcore processor running uC/OSII along with Video IP cores and custom hardware description for a 22kLE FPGA has been designed and implemented to create a VSM embedded system, with similar characteristics and behaviour to a commercial device, plus the advantages of higher integration, lower power consumption, WLAN, and WWAN connectivity.
由于人类生命对医疗设备的依赖，医疗设备的响应是高度敏感的，因此电子设备中常见的问题，如同步和延迟，往往被目标减少到最低限度。在嵌入式系统中，使用FPGA作为CPU芯片的协同处理从模块是解决这些问题的常用方法，不仅适用于商业医疗设备，也适用于不同的工业部门。本文考虑了使用这种拓扑的医疗设备，如(生命体征监视器)vsm。此外，(Fundación Cardiovascular de Colombia) FCV的一个项目旨在升级哥伦比亚用于远程医疗服务的基于pc的系统，该项目将fpga作为嵌入式系统的集成解决方案，通过软核架构、IP核和硬件模块描述实现了CPU和额外集成电路的替换。此外，医疗设备等关键应用需要实时响应和高精度等特性，以便医疗保健人员能够在发生事件时做出适当的响应。一个基于双核架构的工作原型，使用运行uC/OSII的Nios II软核处理器以及视频IP核和22kLE FPGA的定制硬件描述，设计并实现了一个VSM嵌入式系统，具有与商用设备相似的特性和行为，以及更高集成，更低功耗，WLAN和WWAN连接的优势。
{"title":"Dual core architecture on FPGA as an integrated solution in the development of Telemedicine-capable devices","authors":"Jose P. Pinilla, S. Plata, Oscar Alberto Mantilla, L. A. Rodriguez","doi":"10.1109/STSIVA.2014.7010128","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010128","url":null,"abstract":"Medical devices response is highly sensitive because of the dependence of human lives on them, thus common problems in electronics like synchronization and delays are often targeted to be reduced to its bare minimum. The use of FPGA ICs as co-processing slave modules for CPU chips in embedded systems is a common approach to solve these issues, not only among commercial medical equipment, but also in different industry sectors. This paper takes into account Medical Devices such as (Vital Signs Monitors) VSMs using this topology. Furthermore, a project at (Fundación Cardiovascular de Colombia) FCV to upgrade the PC-based systems used for Telemedicine services in Colombia, takes FPGAs as an integrated solution for an embedded system, achieving the replacement of the CPU and additional integrated circuits, with softcore architectures, IP cores, and hardware modules description. Moreover, critical applications such as medical devices need characteristics like real-time response and high accuracy in order to make health care personnel able to respond appropriately in case of an event. A working prototype, based on a Dual-Core architecture using the Nios II softcore processor running uC/OSII along with Video IP cores and custom hardware description for a 22kLE FPGA has been designed and implemented to create a VSM embedded system, with similar characteristics and behaviour to a commercial device, plus the advantages of higher integration, lower power consumption, WLAN, and WWAN connectivity.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"17 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":"127883879","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010123
A. López-Parrado, Juan-Camilo Valderrama-Cuervo
This paper presents the design and implementation of an OpenRISC-based System-on-Chip (SoC), which is composed of hardware cores implementing the Digital Signal Processing (DSP) functions: Finite Impulse Response (FIR) filter, Infinite Impulse Response (IIR) filter and Fast Fourier Transform (FFT). The FIR-filter core is based on the transpose realization form, the IIR-filter core is based on the Second Order Sections (SOS) architecture and the FFT core is based on the Radix 22 Single Delay Feedback (R22SDF) architecture. The three cores are compatible with the Wishbone SoC bus, and they were described using generic and structural VHDL. In-system hardware verification was performed by using an OpenRisc-based SoC synthesized on an Altera FPGA. Tests showed that the designed DSP cores are suitable for building SoC based on the OpenRisc processor and the Wishbone bus.
{"title":"OpenRISC-based System-on-Chip for digital signal processing","authors":"A. López-Parrado, Juan-Camilo Valderrama-Cuervo","doi":"10.1109/STSIVA.2014.7010123","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010123","url":null,"abstract":"This paper presents the design and implementation of an OpenRISC-based System-on-Chip (SoC), which is composed of hardware cores implementing the Digital Signal Processing (DSP) functions: Finite Impulse Response (FIR) filter, Infinite Impulse Response (IIR) filter and Fast Fourier Transform (FFT). The FIR-filter core is based on the transpose realization form, the IIR-filter core is based on the Second Order Sections (SOS) architecture and the FFT core is based on the Radix 22 Single Delay Feedback (R22SDF) architecture. The three cores are compatible with the Wishbone SoC bus, and they were described using generic and structural VHDL. In-system hardware verification was performed by using an OpenRisc-based SoC synthesized on an Altera FPGA. Tests showed that the designed DSP cores are suitable for building SoC based on the OpenRisc processor and the Wishbone bus.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"69 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":"126208218","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010156
Douglas Baquero, Juan F. Molina, R. Gil, C. Bojacá, Hugo Franco, Francisco Gomez
Tomato represents an important vegetable crop worldwide. During cropping cycle several diseases and abnormal conditions may affect tomato plants resulting on considerable losses of production. A precise identification of these pathologies in early phases is fundamental for the implementation of control strategies. Nevertheless, the right identification of symptoms of plants diseases require highly specialized knowledge and facilities, which are not available for small growers. Recently, computer vision tools have been proposed as an alternative for tomato diseases characterization. These works mainly focus on identification of affected regions and classification tasks. Nevertheless, non-specialists may lack of clarity about what they are looking for during the assessment. In these cases, Content Based Image Retrieval (CBIR) systems can be helpful as a complementary strategy to improve the quality of the search by allowing exploration of databases with supplementary information. This work presents a novel strategy for image retrieval of tomato leaves for greenhouse crops suitable to support disease diagnosis. The strategy is based on color structure descriptors and nearest neighbors. Experimental results show that the proposed approach can successfully characterize in several abnormal conditions, such as, chlorosis, sooty moulds and early blight.
{"title":"An image retrieval system for tomato disease assessment","authors":"Douglas Baquero, Juan F. Molina, R. Gil, C. Bojacá, Hugo Franco, Francisco Gomez","doi":"10.1109/STSIVA.2014.7010156","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010156","url":null,"abstract":"Tomato represents an important vegetable crop worldwide. During cropping cycle several diseases and abnormal conditions may affect tomato plants resulting on considerable losses of production. A precise identification of these pathologies in early phases is fundamental for the implementation of control strategies. Nevertheless, the right identification of symptoms of plants diseases require highly specialized knowledge and facilities, which are not available for small growers. Recently, computer vision tools have been proposed as an alternative for tomato diseases characterization. These works mainly focus on identification of affected regions and classification tasks. Nevertheless, non-specialists may lack of clarity about what they are looking for during the assessment. In these cases, Content Based Image Retrieval (CBIR) systems can be helpful as a complementary strategy to improve the quality of the search by allowing exploration of databases with supplementary information. This work presents a novel strategy for image retrieval of tomato leaves for greenhouse crops suitable to support disease diagnosis. The strategy is based on color structure descriptors and nearest neighbors. Experimental results show that the proposed approach can successfully characterize in several abnormal conditions, such as, chlorosis, sooty moulds and early blight.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"6 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":"121961192","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010181
Cristian A. Torres-Valencia, Hernan F. Garcia-Arias, Mauricio A. Alvarez Lopez, A. Orozco-Gutierrez
Multimodal Emotion recognition (MER) is an application of machine learning were different biological signals are used in order to automatically classify a determined affective state. MER systems has been developed for different type of applications from psychological evaluation, anxiety assessment, human-machine interfaces and marketing. There are several spaces of classification proposed in the state of art for the emotion recognition task, the most known are discrete and dimensional spaces were the emotions are described in terms of some basic emotions and latent dimensions respectively. The use of dimensional spaces of classification allows a higher range of emotional states to be analyzed. The most common dimensional space used for this purpose is the Arousal/Valence space were emotions are described in terms of the intensity of the emotion that goes from inactive to active in the arousal dimension, and from unpleasant to pleasant in the valence dimension. The use of physiological signals and the EEG is well suited for emotion recognition due to the fact that an emotional states generates responses from different biological systems of the human body. Since the expression of an emotion is a dynamic process, we propose the use of generative models as Hidden Markov Models (HMM) to capture de dynamics of the signals for further classification of emotional states in terms of arousal and valence. For the development of this work an international database for emotion classification known as Dataset for Emotion Analysis using Physiological signals (DEAP) is used. The objective of this work is to determine which of the physiological and EEG signals brings more relevant information in the emotion recognition task, several experiments using HMMs from different signals and combinations of them are performed, and the results shows that some of those signals brings more discrimination between arousal and valence levels as the EEG and the Galvanic Skin Response (GSR) and the Heart rate (HR).
{"title":"Comparative analysis of physiological signals and electroencephalogram (EEG) for multimodal emotion recognition using generative models","authors":"Cristian A. Torres-Valencia, Hernan F. Garcia-Arias, Mauricio A. Alvarez Lopez, A. Orozco-Gutierrez","doi":"10.1109/STSIVA.2014.7010181","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010181","url":null,"abstract":"Multimodal Emotion recognition (MER) is an application of machine learning were different biological signals are used in order to automatically classify a determined affective state. MER systems has been developed for different type of applications from psychological evaluation, anxiety assessment, human-machine interfaces and marketing. There are several spaces of classification proposed in the state of art for the emotion recognition task, the most known are discrete and dimensional spaces were the emotions are described in terms of some basic emotions and latent dimensions respectively. The use of dimensional spaces of classification allows a higher range of emotional states to be analyzed. The most common dimensional space used for this purpose is the Arousal/Valence space were emotions are described in terms of the intensity of the emotion that goes from inactive to active in the arousal dimension, and from unpleasant to pleasant in the valence dimension. The use of physiological signals and the EEG is well suited for emotion recognition due to the fact that an emotional states generates responses from different biological systems of the human body. Since the expression of an emotion is a dynamic process, we propose the use of generative models as Hidden Markov Models (HMM) to capture de dynamics of the signals for further classification of emotional states in terms of arousal and valence. For the development of this work an international database for emotion classification known as Dataset for Emotion Analysis using Physiological signals (DEAP) is used. The objective of this work is to determine which of the physiological and EEG signals brings more relevant information in the emotion recognition task, several experiments using HMMs from different signals and combinations of them are performed, and the results shows that some of those signals brings more discrimination between arousal and valence levels as the EEG and the Galvanic Skin Response (GSR) and the Heart rate (HR).","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":"124663926","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010166
Juan F. Molina, R. Gil, C. Bojacá, Francisco Gomez, Hugo Franco
This work presents a Computer Vision prototype strategy for the automatic detection of mycotic infections on tomato crops. This Computer Vision method is based on the characterization of tomato leaflets (both healthy and early blight-infected regions of interest - ROIs) by color description (MPEG-7 standard descriptors). A small size ROI collection manually annotated by experts is used for both training and testing of a simple classifier (1-NN). The performance of each descriptor under study (Color Structure Descriptor, CSD; Color Layout descriptor, CLD; and Scalable Color Descriptor, SCD) is analysed by a nested-leave-one-out cross validation. The inner loop permits a individual descriptor configuration evaluation, while the outer loop yields an average performance comparison between different descriptors. Our results show that CSD had a better performance than SCD and CLD.
{"title":"Automatic detection of early blight infection on tomato crops using a color based classification strategy","authors":"Juan F. Molina, R. Gil, C. Bojacá, Francisco Gomez, Hugo Franco","doi":"10.1109/STSIVA.2014.7010166","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010166","url":null,"abstract":"This work presents a Computer Vision prototype strategy for the automatic detection of mycotic infections on tomato crops. This Computer Vision method is based on the characterization of tomato leaflets (both healthy and early blight-infected regions of interest - ROIs) by color description (MPEG-7 standard descriptors). A small size ROI collection manually annotated by experts is used for both training and testing of a simple classifier (1-NN). The performance of each descriptor under study (Color Structure Descriptor, CSD; Color Layout descriptor, CLD; and Scalable Color Descriptor, SCD) is analysed by a nested-leave-one-out cross validation. The inner loop permits a individual descriptor configuration evaluation, while the outer loop yields an average performance comparison between different descriptors. Our results show that CSD had a better performance than SCD and CLD.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"2015 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":"132467048","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}
Pub Date : 2014-09-01DOI: 10.1109/STSIVA.2014.7010160
Fabian Sanchez, Carlos A. Fajardo, Carlos A. Angulo, Oscar M. Reyes, C. Bouman
The Discrete Wavelet Transform (DWT) is an important technique for signal analysis, compressing and denoising due to its excellent locality in the time-frequency domain. The DWT is developed by convolutions which demand both a large number of mathematical operations and a large amount of storage. The lifting scheme reduces both computational and storage requirements. We have developed a computational architecture for inverse DWT using the lifting scheme. The design was developed in VHDL and then implemented into a Virtex 5 FPGA. We aim to reach a high throughput and reduce the design area. The architecture takes 3L + N(1-0.5L) clock cycles to compute L levels of 1D reconstruction for data of size N. Some comparisons suggest that our work could be faster than previous works.
{"title":"A computational architecture for discrete wavelet transform using lifting scheme","authors":"Fabian Sanchez, Carlos A. Fajardo, Carlos A. Angulo, Oscar M. Reyes, C. Bouman","doi":"10.1109/STSIVA.2014.7010160","DOIUrl":"https://doi.org/10.1109/STSIVA.2014.7010160","url":null,"abstract":"The Discrete Wavelet Transform (DWT) is an important technique for signal analysis, compressing and denoising due to its excellent locality in the time-frequency domain. The DWT is developed by convolutions which demand both a large number of mathematical operations and a large amount of storage. The lifting scheme reduces both computational and storage requirements. We have developed a computational architecture for inverse DWT using the lifting scheme. The design was developed in VHDL and then implemented into a Virtex 5 FPGA. We aim to reach a high throughput and reduce the design area. The architecture takes 3L + N(1-0.5L) clock cycles to compute L levels of 1D reconstruction for data of size N. Some comparisons suggest that our work could be faster than previous works.","PeriodicalId":114554,"journal":{"name":"2014 XIX Symposium on Image, Signal Processing and Artificial Vision","volume":"140 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":"130818947","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：