Fusion of multiple face and fingerprint matchers based on different biometrics for personal authentication has been investigated in the last years. However, the performance achievable when the expected subject cooperation degree is different from the real one has not yet been sufficiently studied. In this paper, we investigate the performance of several score-level fusion rules when the test set is taken under non-cooperative ("stress") conditions. Results show that fusion allows to increase the robustness of the system under strong changes of the subject's cooperation degree.
{"title":"Score-level fusion of fingerprint and face matchers for personal verification under \"stress\" conditions","authors":"G. Marcialis, F. Roli","doi":"10.1109/ICIAP.2007.114","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.114","url":null,"abstract":"Fusion of multiple face and fingerprint matchers based on different biometrics for personal authentication has been investigated in the last years. However, the performance achievable when the expected subject cooperation degree is different from the real one has not yet been sufficiently studied. In this paper, we investigate the performance of several score-level fusion rules when the test set is taken under non-cooperative (\"stress\") conditions. Results show that fusion allows to increase the robustness of the system under strong changes of the subject's cooperation degree.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128249440","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}
Demetrios Gerogiannis, Christophoros Nikou, A. Likas
We propose a pixel similarity-based algorithm enabling accurate rigid registration between single and multimodal images. The method relies on the partitioning of a reference image by a Gaussian mixture model (GMM). This partition is then projected onto the image to be registered. The main idea is that a Gaussian component in the reference image corresponds to a Gaussian component in the image to be registered. If the images are correctly registered the total distance between the corresponding components is minimum. An advantage of the proposed method is that it may handle multidimensional (vector valued) images where histogram-based methods such as the widely used mutual information is not tractable due to the high dimension of the data. Also, experimental results indicate that, even in the case of images presenting low SNR, the proposed algorithm compares favorably to the histogram-based mutual information method that is widely used in a variety of applications.
{"title":"Rigid Image Registration based on Pixel Grouping","authors":"Demetrios Gerogiannis, Christophoros Nikou, A. Likas","doi":"10.1109/ICIAP.2007.111","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.111","url":null,"abstract":"We propose a pixel similarity-based algorithm enabling accurate rigid registration between single and multimodal images. The method relies on the partitioning of a reference image by a Gaussian mixture model (GMM). This partition is then projected onto the image to be registered. The main idea is that a Gaussian component in the reference image corresponds to a Gaussian component in the image to be registered. If the images are correctly registered the total distance between the corresponding components is minimum. An advantage of the proposed method is that it may handle multidimensional (vector valued) images where histogram-based methods such as the widely used mutual information is not tractable due to the high dimension of the data. Also, experimental results indicate that, even in the case of images presenting low SNR, the proposed algorithm compares favorably to the histogram-based mutual information method that is widely used in a variety of applications.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129037800","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}
The present aim was to develop a fully automatic feature-based method for expression-invariant detection of facial landmarks from still facial images. It is a continuation of our earlier work where we found that some certain muscle contractions made a deteriorating effect on the feature-based landmark detection especially in the lower face. Taking into account this crucial facial behavior, we introduced improvements to the method that allowed facial landmarks to be fully automatically detected from expressive images of high complexity. In the method, information on local oriented edges was utilized to compose edge maps of the image at two levels of resolution. The landmark candidates resulted from this step were further verified by edge orientation matching. We used knowledge on face geometry to find the proper spatial arrangement of the candidates. The results obtained demonstrated a high overall performance of the method while testing a wide range official displays.
{"title":"Automatic Detection of Facial Landmarks from AU-coded Expressive Facial Images","authors":"Y. Gizatdinova, Veikko Surakka","doi":"10.1109/ICIAP.2007.30","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.30","url":null,"abstract":"The present aim was to develop a fully automatic feature-based method for expression-invariant detection of facial landmarks from still facial images. It is a continuation of our earlier work where we found that some certain muscle contractions made a deteriorating effect on the feature-based landmark detection especially in the lower face. Taking into account this crucial facial behavior, we introduced improvements to the method that allowed facial landmarks to be fully automatically detected from expressive images of high complexity. In the method, information on local oriented edges was utilized to compose edge maps of the image at two levels of resolution. The landmark candidates resulted from this step were further verified by edge orientation matching. We used knowledge on face geometry to find the proper spatial arrangement of the candidates. The results obtained demonstrated a high overall performance of the method while testing a wide range official displays.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127630676","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}
Corner detection is used in many computer vision applications that require fast and efficient feature matching. For tasks such as robot localisation and navigation, the use of corners for matching is preferred over edges or other, larger, features. In recent years finite-element based methods have been used to develop gradient operators for edge detection that have improved angular accuracy over standard techniques. We extend this work to corner detection, enabling edge and corner detection to be integrated. We demonstrate that accuracy is comparable to well-known existing corner detectors, and that significantly reduced computation time can be achieved, making the approach appropriate for real-time computer vision and robotics.
{"title":"Integrated Edge and Corner Detection","authors":"S. Coleman, B. Scotney, D. Kerr","doi":"10.1109/ICIAP.2007.80","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.80","url":null,"abstract":"Corner detection is used in many computer vision applications that require fast and efficient feature matching. For tasks such as robot localisation and navigation, the use of corners for matching is preferred over edges or other, larger, features. In recent years finite-element based methods have been used to develop gradient operators for edge detection that have improved angular accuracy over standard techniques. We extend this work to corner detection, enabling edge and corner detection to be integrated. We demonstrate that accuracy is comparable to well-known existing corner detectors, and that significantly reduced computation time can be achieved, making the approach appropriate for real-time computer vision and robotics.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131839657","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}
Effective color image and video coding is usually exploited coupling a compression method with the most suitable color space representation. This work extends a previously proposed high dynamic range (HDR) image coding method, which combines a logarithmic color adaptation module with a JPEG2000 codec. Here we propose to change the original preprocessing stage with a more adequate one, based on the LogLuv color space representation, in order to take fully advantage of wavelet based coding. The experimental comparisons confirm that the proposed method improves the compression performances and simplify the overall coding scheme.
{"title":"Effective color space representation for wavelet based compression of HDR images","authors":"M. Okuda, N. Adami","doi":"10.1109/ICIAP.2007.57","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.57","url":null,"abstract":"Effective color image and video coding is usually exploited coupling a compression method with the most suitable color space representation. This work extends a previously proposed high dynamic range (HDR) image coding method, which combines a logarithmic color adaptation module with a JPEG2000 codec. Here we propose to change the original preprocessing stage with a more adequate one, based on the LogLuv color space representation, in order to take fully advantage of wavelet based coding. The experimental comparisons confirm that the proposed method improves the compression performances and simplify the overall coding scheme.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127262751","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}
P. Zingaretti, E. Frontoni, G. Forlani, C. Nardinocchi
LIDAR (Light Detection And Ranging) data are a primary data source for digital terrain model (DTM) generation and 3D city models. This paper presents an AdaBoost algorithm for the identification of rules for the classification of raw LIDAR data mainly as buildings, ground and vegetation. First raw data are filtered, interpolated over a grid and segmented. Then geometric and topological relationships among regions resulting from segmentation constitute the input to the tree-structured classification algorithm. Results obtained on data sets gathered over the town of Pavia (Italy) are compared with those obtained by a rule-based approach previously presented by the authors for the classification of the regions.
{"title":"Automatic extraction of LIDAR data classification rules","authors":"P. Zingaretti, E. Frontoni, G. Forlani, C. Nardinocchi","doi":"10.1109/ICIAP.2007.31","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.31","url":null,"abstract":"LIDAR (Light Detection And Ranging) data are a primary data source for digital terrain model (DTM) generation and 3D city models. This paper presents an AdaBoost algorithm for the identification of rules for the classification of raw LIDAR data mainly as buildings, ground and vegetation. First raw data are filtered, interpolated over a grid and segmented. Then geometric and topological relationships among regions resulting from segmentation constitute the input to the tree-structured classification algorithm. Results obtained on data sets gathered over the town of Pavia (Italy) are compared with those obtained by a rule-based approach previously presented by the authors for the classification of the regions.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128819779","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}
Research in visual surveillance systems is shifting from using few stationary, passive cameras to employing large heterogeneous sensor networks. One promising type of sensor in particular is the pan-tilt-zoom (PTZ) camera, which can cover a potentially much larger area than passive cameras, and can obtain much higher resolution imagery through zoom capacity. In this paper, a system that can track objects with multiple calibrated PTZ cameras in a cooperative fashion is presented. Tracking and calibration results are combined with several image processing techniques in a statistical segmentation framework, through which the cameras can hand over targets to each other. A prototype system is presented that operates in real time.
{"title":"Cooperative Object Tracking with Multiple PTZ Cameras","authors":"I. Everts, N. Sebe, Graeme A. Jones","doi":"10.1109/ICIAP.2007.46","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.46","url":null,"abstract":"Research in visual surveillance systems is shifting from using few stationary, passive cameras to employing large heterogeneous sensor networks. One promising type of sensor in particular is the pan-tilt-zoom (PTZ) camera, which can cover a potentially much larger area than passive cameras, and can obtain much higher resolution imagery through zoom capacity. In this paper, a system that can track objects with multiple calibrated PTZ cameras in a cooperative fashion is presented. Tracking and calibration results are combined with several image processing techniques in a statistical segmentation framework, through which the cameras can hand over targets to each other. A prototype system is presented that operates in real time.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114707517","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. Masini, Francesco Branchitta, M. Diani, G. Corsini
In this paper we consider the problem of fusing two video streams acquired by an RGB camera and a sensor operating in the long wave infrared (LWIR). The application of interest is area surveillance and the fusion process aims at enhancing the human perception of the monitored scene. We propose a fusion procedure where the background and the moving objects are separated and fused by means of different strategies. With respect to standard video fusion techniques this approach has the advantage of reducing the computational load and mitigating the rapid brightness variations in the fused video. It is also less sensitive to the presence of noise. We discuss the experimental results obtained on a typical area surveillance scenario and demonstrate the effectiveness of the proposed method. For this purpose, the analysis is carried out both subjectively, in terms of visual quality of the fused video stream and objectively, in terms of standard image quality indexes. The computational load is also evaluated.
{"title":"Sight enhancement through video fusion in a surveillance system","authors":"A. Masini, Francesco Branchitta, M. Diani, G. Corsini","doi":"10.1109/ICIAP.2007.117","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.117","url":null,"abstract":"In this paper we consider the problem of fusing two video streams acquired by an RGB camera and a sensor operating in the long wave infrared (LWIR). The application of interest is area surveillance and the fusion process aims at enhancing the human perception of the monitored scene. We propose a fusion procedure where the background and the moving objects are separated and fused by means of different strategies. With respect to standard video fusion techniques this approach has the advantage of reducing the computational load and mitigating the rapid brightness variations in the fused video. It is also less sensitive to the presence of noise. We discuss the experimental results obtained on a typical area surveillance scenario and demonstrate the effectiveness of the proposed method. For this purpose, the analysis is carried out both subjectively, in terms of visual quality of the fused video stream and objectively, in terms of standard image quality indexes. The computational load is also evaluated.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114411709","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}
In this paper, we propose the combination of the self organizing map (SOM) and of the tangent distance for effective clustering in document image analysis. The proposed model (SOM_TD) is used for character and layout clustering, with applications to word retrieval and to page classification. By using the tangent distance it is possible to improve the SOM clustering so as to be more tolerant with respect to small local transformations of the input patterns.
{"title":"Transformation invariant SOM clustering in Document Image Analysis","authors":"S. Marinai, E. Marino, G. Soda","doi":"10.1109/ICIAP.2007.126","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.126","url":null,"abstract":"In this paper, we propose the combination of the self organizing map (SOM) and of the tangent distance for effective clustering in document image analysis. The proposed model (SOM_TD) is used for character and layout clustering, with applications to word retrieval and to page classification. By using the tangent distance it is possible to improve the SOM clustering so as to be more tolerant with respect to small local transformations of the input patterns.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117213382","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}
M. C. Santana, O. Déniz-Suárez, J. Lorenzo-Navarro, D. Hernández-Sosa
Automatic face recognition has been mainly tackled by matching a new image to a set of previously computed identity models. The literature describes approximations where those identity models are based on a single sample or a set of them. However, face representation keeps being a topic of great debate in the psychology literature, with some results suggesting the use of an average image. In this paper, instead of restricting our system to a fixed and precomputed classifier, the system learns iteratively based on the experience extracted from each meeting. The experiments presented introduce the use of an exemplar average based approach. The results show similar performance to an approach based on the use of multiple exemplars per identity, but reducing storage and processing cost. The process is done autonomously, using an automatic face detection system that meets people, excepting the supervision provided by a human to confirm or correct each meeting classification suggested by the system.
{"title":"Becoming Visually Familiar","authors":"M. C. Santana, O. Déniz-Suárez, J. Lorenzo-Navarro, D. Hernández-Sosa","doi":"10.1109/ICIAP.2007.37","DOIUrl":"https://doi.org/10.1109/ICIAP.2007.37","url":null,"abstract":"Automatic face recognition has been mainly tackled by matching a new image to a set of previously computed identity models. The literature describes approximations where those identity models are based on a single sample or a set of them. However, face representation keeps being a topic of great debate in the psychology literature, with some results suggesting the use of an average image. In this paper, instead of restricting our system to a fixed and precomputed classifier, the system learns iteratively based on the experience extracted from each meeting. The experiments presented introduce the use of an exemplar average based approach. The results show similar performance to an approach based on the use of multiple exemplars per identity, but reducing storage and processing cost. The process is done autonomously, using an automatic face detection system that meets people, excepting the supervision provided by a human to confirm or correct each meeting classification suggested by the system.","PeriodicalId":118466,"journal":{"name":"14th International Conference on Image Analysis and Processing (ICIAP 2007)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116477447","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：