发布求助
文献互助 智能选刊 最新文献

2007 15th European Signal Processing Conference最新文献

筛选
英文 中文
Image classification with user defined ontology 使用用户自定义本体的图像分类
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40351
Rémi Vieux, J. Domenger, J. Benois-Pineau, A. Braquelaire
{"title":"Image classification with user defined ontology","authors":"Rémi Vieux, J. Domenger, J. Benois-Pineau, A. Braquelaire","doi":"10.5281/ZENODO.40351","DOIUrl":"https://doi.org/10.5281/ZENODO.40351","url":null,"abstract":"In this paper we are interested in classification of objects in images according to user defined scenarios. We show how the user-defined ontology with a specialisation by a concrete scenario / object of interest allows for an adapted choice of methods and their tuning through the whole framework: selection of the area of interest, descriptors choice, classification of objects. Particular attention here is payed to the classification. We use SVM classifiers for their good capacity of generalisation. We show that in an adapted descriptor space, the choice of a “light” linear kernel together with boosting of classifiers is interesting compared to more complex and computationally expensive RBF kernels. The results on real-life images are promising. The paper results from the research we conduct in the framework of X-Media EU-funded Integrated Project.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133012375","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}
引用次数: 3
Fisher's discriminant and relevant component analysis for static facial expression classification 静态面部表情分类的Fisher判别及相关成分分析
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40227
Matteo Sorci, G. Antonini, J. Thiran
{"title":"Fisher's discriminant and relevant component analysis for static facial expression classification","authors":"Matteo Sorci, G. Antonini, J. Thiran","doi":"10.5281/ZENODO.40227","DOIUrl":"https://doi.org/10.5281/ZENODO.40227","url":null,"abstract":"This paper addresses the issue of automatic classification of the six universal emotional categories (joy, surprise, fear, anger, disgust, sadness) in the case of static images. Appearance parameters are extracted by an active appearance model(AAM) representing the input for the classification step. We show how Relevant Component Analysis (RCA) in combination with Fisher's Linear Discriminant (FLD) provides a good “plug-&-play” classifier in the context of facial expression recognition framework. We test this method against several other classification techniques, including LDA, GDA and SVM, on the Cohn-Kanade database.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133229764","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}
引用次数: 4
A ‘gas of circles’ phase field model and its application to tree crown extraction “圆气”相场模型及其在树冠提取中的应用
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40260
P. Horváth, Ian H. Jermyn
{"title":"A ‘gas of circles’ phase field model and its application to tree crown extraction","authors":"P. Horváth, Ian H. Jermyn","doi":"10.5281/ZENODO.40260","DOIUrl":"https://doi.org/10.5281/ZENODO.40260","url":null,"abstract":"The problem of extracting the region in the image domain corresponding to an a priori unknown number of circular objects occurs in several domains. We propose a new model of a `gas of circles', the ensemble of regions in the image domain composed of circles of a given radius. The model uses the phase field reformulation of higher-order active contours (HOACs). Phase fields possess several advantages over contour and level set approaches to region modelling, in particular for HOAC models. The reformulation allows us to benefit from these advantages without losing the strengths of the HOAC framework. Combined with a suitable likelihood energy, and applied to the tree crown extraction problem, the new model shows markedly improved performance, both in quality of results and in computation time, which is two orders of magnitude less than the HOAC level set implementation.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"423 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116564971","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}
引用次数: 13
Early auditory processing inspired features for robust automatic speech recognition 早期的听觉处理激发了鲁棒自动语音识别的特性
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40692
Ozlem Kalinli, Shrikanth S. Narayanan
{"title":"Early auditory processing inspired features for robust automatic speech recognition","authors":"Ozlem Kalinli, Shrikanth S. Narayanan","doi":"10.5281/ZENODO.40692","DOIUrl":"https://doi.org/10.5281/ZENODO.40692","url":null,"abstract":"In this paper, we derive bio-inspired features for automatic speech recognition based on the early processing stages in the human auditory system. The utility and robustness of the derived features are validated in a speech recognition task under a variety of noise conditions. First, we develop an auditory based feature by replacing the filterbank analysis stage of Mel-frequency cepstral coefficients (MFCC) feature extraction with an auditory model that consists of cochlear filtering, inner hair cell, and lateral inhibitory network stages. Then, we propose a new feature set that retains only the cochlear channel outputs that are more likely to fire the neurons in the central auditory system. This feature set is extracted by principal component analysis (PCA) of nonlinearly compressed early auditory spectrum. When evaluated in a connected digit recognition task using the Aurora 2.0 database, the proposed feature set has 40% and 18% average word error rate improvement relative to the MFCC and RelAtive SpecTrAl (RASTA) features, respectively.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116612741","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}
引用次数: 4
Early detection of abnormal emergent behaviour 早期发现异常紧急行为
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40559
L. Spaanenburg
{"title":"Early detection of abnormal emergent behaviour","authors":"L. Spaanenburg","doi":"10.5281/ZENODO.40559","DOIUrl":"https://doi.org/10.5281/ZENODO.40559","url":null,"abstract":"Emergent behaviour has become a plague of automation systems based on communication networks. Centralized monitoring of the network comes generally to late to suppress unwanted behaviour. It is required to mark the tendency towards state changes in a decentralized manner. The paper discusses the role of local awareness by inspection of the model learning behaviour of feed-forward networks. The correlated movement of weight changes over time provides a clear indication of such profound changes, as demonstrated by some initial experience in industrial automation.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125811873","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}
引用次数: 0
An improved partial Haar dual adaptive filter for sparse echo cancellation 一种改进的局部Haar双自适应滤波器用于稀疏回波抵消
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.34764
P. Kechichian, B. Champagne
{"title":"An improved partial Haar dual adaptive filter for sparse echo cancellation","authors":"P. Kechichian, B. Champagne","doi":"10.5281/ZENODO.34764","DOIUrl":"https://doi.org/10.5281/ZENODO.34764","url":null,"abstract":"This paper proposes the use of a peak tendency estimator (PTE) based on Dezert Smarandache Theory (DSmT) and fuzzy inference to overcome two inherent limitations of a recently proposed partial Haar dual adaptive filter (PHDAF) for sparse echo cancellation. These limitations include the dependence of the PHDAF's performance on the echo path impulse response's bulk delay as a result of the lack of shift-invariance of the wavelet transform, and the PHDAF's difficulty in quickly tracking a new dispersive region after an abrupt change in bulk delay occurs. The improved PHDAF is analyzed in terms of its mean-square error (MSE) curves as well as its mean time to properly locate a dispersive regions under different SNRs. The simulations show that enhanced performance can be obtained using the proposed solutions at a minimal increase in computational cost.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123612562","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}
引用次数: 1
Enhancement of residual echo for improved acoustic echo cancellation 增强残余回波以改善声学回声消除
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40533
Ted S. Wada, B. Juang
{"title":"Enhancement of residual echo for improved acoustic echo cancellation","authors":"Ted S. Wada, B. Juang","doi":"10.5281/ZENODO.40533","DOIUrl":"https://doi.org/10.5281/ZENODO.40533","url":null,"abstract":"This paper investigates the use of a signal enhancement technique, namely a noise suppressing nonlinearity, on the adaptive filter error in order to increase the stability and the performance of acoustic echo cancellation (AEC) when there is a continuous distortion to the acoustic echo signal. The algorithm presented here differs from others in that the enhancement of signal is done in the adaptation loop, rather than as a post-processing technique for further reduction of residual echo in the signal, and that the resulting nonlinearity for the cancellation error is formulated as a solution to the signal enhancement problem. Combining the nonlinear error suppression method with NLMS and other adaptive step-size algorithms based on NLMS shows an improvement of between 5 to 15 dB in the average ERLE for additive white noise and around 2 dB for speech coding distortion when a simulated acoustic echo is used. The reduction of the misalignment of 5 dB or more for both noise cases can be expected. The technique is shown to be beneficial also with a real acoustic echo. The new method is seen as a viable technique for improving the existing AEC algorithms when the acoustic echo is corrupted by linear distortion in the form of additive noise or by nonlinear distortion in the form of speech coding.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125110842","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}
引用次数: 8
CCD image demosaicing using localized correlations 使用局部相关的CCD图像去马赛克
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40592
R. Sher, M. Porat
{"title":"CCD image demosaicing using localized correlations","authors":"R. Sher, M. Porat","doi":"10.5281/ZENODO.40592","DOIUrl":"https://doi.org/10.5281/ZENODO.40592","url":null,"abstract":"A new approach to image interpolation using spatial relationships between adjacent pixels is introduced. In its first stage, the localized statistical relationships are studied based on the sparse version of the image. In the second stage, the governing rules of the image are used to build an interpolated version. The proposed interpolation method is suitable for color single-CCD images for demosaicing purposes. The correlation rule is studied first for each color component separately, then difference images (modified hues) are built to eliminate the color correlation, leading to a smoother reconstructed signal. Since in Bayer pattern not all the color components are equally represented, the algorithm deals with the major green component differently from the red and blue, using the green as a basis for the whole image reconstruction. Further statistical tools are added to the algorithm to improve the visual results. We compare our method to presently available demosaicing techniques for single CCD color imaging with the major emphasis on reducing ghost colors and unreal edges. Our conclusion is that the proposed method can significantly improve interpolation and demosaicing tasks in image processing.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126149185","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}
引用次数: 5
Energy-efficient software-defined radio solutions for MIMO-based broadband communication 基于mimo的宽带通信的节能软件定义无线电解决方案
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40436
B. Bougard, A. Bourdoux, F. Naessens, M. Glassée, V. Derudder, L. Perre
{"title":"Energy-efficient software-defined radio solutions for MIMO-based broadband communication","authors":"B. Bougard, A. Bourdoux, F. Naessens, M. Glassée, V. Derudder, L. Perre","doi":"10.5281/ZENODO.40436","DOIUrl":"https://doi.org/10.5281/ZENODO.40436","url":null,"abstract":"Multi-antenna transmission over multi-input, multi-output (MIMO) channels are considered in almost all recent broadband wireless communication standards. Besides, the fast-pacing diversity and evolution of those standards, next to the deep submicron integration cost explosion, urges multi-mode reconfigurable solutions. Software Defined Radio (SDR) is envisioned to enable low-cost, high-volume multi-mode baseband modems both for base-station and user terminals. Yet, supporting high-throughput MIMO standard with limited energy budget as in user terminals is a challenge for SDR architectures. With Space Division Multiplexing (SDM) for instance, N being the number of antennas, the computation load is multiplied by >N2. Capitalizing on a low complexity SDM-OFDM functional architecture, a heterogeneous multi-processor SoC platform with DSP cores delivering 50 to 250MOPS/mW and an integrated software development flow, we demonstrate the SDR implementation of 100Mbps+ SDM-OFDM with 3.6 nJ/bit energy efficiency (383mW average power).","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126186124","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}
引用次数: 5
Automated characterization of esophageal and severely injured voices by means of acoustic parameters 利用声学参数自动表征食道和严重损伤的声音
2007 15th European Signal Processing Conference Pub Date : 2007-09-03 DOI: 10.5281/ZENODO.40660
B. G. Zapirain, I. Ruiz, A. M. Zorrilla, J. Vicente, M. Mendezona
{"title":"Automated characterization of esophageal and severely injured voices by means of acoustic parameters","authors":"B. G. Zapirain, I. Ruiz, A. M. Zorrilla, J. Vicente, M. Mendezona","doi":"10.5281/ZENODO.40660","DOIUrl":"https://doi.org/10.5281/ZENODO.40660","url":null,"abstract":"In the scope of digitized speech signals with severe pathologies, as the esophageal voices are, it is impossible the objective assessment of the voice based on a set of parameters accepted by the scientific community like pitch, jitter, shimmer or HNR. This impossibility is due to healthy voices or with slight pathologies can be only evaluated with commercial applications. However, this paper presents a robust and precise algorithm that allows the automated calculation of pitch and jitter on very noisy and low quality voice signals. Therefore, both the improvement achieved due to medical treatment and the evaluation of digital signal processing algorithms will be measurable based on objective criteria.","PeriodicalId":176384,"journal":{"name":"2007 15th European Signal Processing Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130247367","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}
引用次数: 3
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信