Pub Date : 2001-09-26DOI: 10.1109/ICIAP.2001.957068
A. Carrilero, H. Maître, M. Roux
Telecommunication operators intensively use simulation tools for optimizing positioning in mobile communication networks. These simulators are based on digital surface models to estimate electromagnetic wave propagation. In addition to a three dimensional model of the city which is conveniently obtained from aerial images, we propose to establish a cartography of urban materials from the same data. This cartography is derived from an analysis of the BRDF (binomial reflectivity distribution) of the materials under different viewing angles. For this purpose, we use a simple light reflection model and for each building or terrain parcel, we determine the parameters of the model. We found experimentally that the Blinn's model, although not physically derived, is the most adequate for this application. We propose to use a robust estimation method, the least median of squares estimator on Blinn's model. We test it on various materials, like red and dark tiles and slates. Calculated parameters are evaluated according to assumptions made on surface quality of these materials. We present the limits of the method.
{"title":"Material determination from reflectance properties in aerial urban images","authors":"A. Carrilero, H. Maître, M. Roux","doi":"10.1109/ICIAP.2001.957068","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957068","url":null,"abstract":"Telecommunication operators intensively use simulation tools for optimizing positioning in mobile communication networks. These simulators are based on digital surface models to estimate electromagnetic wave propagation. In addition to a three dimensional model of the city which is conveniently obtained from aerial images, we propose to establish a cartography of urban materials from the same data. This cartography is derived from an analysis of the BRDF (binomial reflectivity distribution) of the materials under different viewing angles. For this purpose, we use a simple light reflection model and for each building or terrain parcel, we determine the parameters of the model. We found experimentally that the Blinn's model, although not physically derived, is the most adequate for this application. We propose to use a robust estimation method, the least median of squares estimator on Blinn's model. We test it on various materials, like red and dark tiles and slates. Calculated parameters are evaluated according to assumptions made on surface quality of these materials. We present the limits of the method.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128794386","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957006
P. Scheunders
A new segmentation technique for multivalued images is elaborated. The technique makes use of the first fundamental form to access edge information of a multivalued image. On the obtained edge map, a watershed-based algorithm is applied. In order to remove noise or local texture, before segmentation, an anisotropic diffusion filter is applied, also making use of the first fundamental form. In this way, the entire procedure is applied using multivalued processing. Experiments are performed on colour images, medical multimodal images and multispectral satellite imagery. Segmentation results are compared to single-valued segmentation and filtering, applied to the intensity only or the band-average images.
{"title":"Multivalued image segmentation based on first fundamental form","authors":"P. Scheunders","doi":"10.1109/ICIAP.2001.957006","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957006","url":null,"abstract":"A new segmentation technique for multivalued images is elaborated. The technique makes use of the first fundamental form to access edge information of a multivalued image. On the obtained edge map, a watershed-based algorithm is applied. In order to remove noise or local texture, before segmentation, an anisotropic diffusion filter is applied, also making use of the first fundamental form. In this way, the entire procedure is applied using multivalued processing. Experiments are performed on colour images, medical multimodal images and multispectral satellite imagery. Segmentation results are compared to single-valued segmentation and filtering, applied to the intensity only or the band-average images.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129639243","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957013
Riccardo Distasi, M. Nappi, M. Tucci, S. Vitulano
Many intrinsically 2-dimensional visual signals can be effectively encoded in a 1D form. This simpler representation is well-suited to both pattern recognition and image retrieval tasks. In particular, this paper deals with contour and texture, combined together in order to obtain an effective technique for content-based image indexing. The proposed method, named CONTEXT, represents CONtours and TEXTures by a vector containing the location and energy of the signal maxima. Such a representation has been utilized as the feature extraction engine in an image retrieval system for image databases. The homogeneous treatment reserved to both contour and texture information makes the algorithm elegant and easy to implement and extend. The data used for experimentally assessing CONTEXT were contours and textures from various application domains, plus a database of medical images. The experiments reveal a high discriminating power which in turn yields a high perceived quality of the retrieval results.
{"title":"CONTEXT: a technique for image retrieval integrating CONtour and TEXTure information","authors":"Riccardo Distasi, M. Nappi, M. Tucci, S. Vitulano","doi":"10.1109/ICIAP.2001.957013","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957013","url":null,"abstract":"Many intrinsically 2-dimensional visual signals can be effectively encoded in a 1D form. This simpler representation is well-suited to both pattern recognition and image retrieval tasks. In particular, this paper deals with contour and texture, combined together in order to obtain an effective technique for content-based image indexing. The proposed method, named CONTEXT, represents CONtours and TEXTures by a vector containing the location and energy of the signal maxima. Such a representation has been utilized as the feature extraction engine in an image retrieval system for image databases. The homogeneous treatment reserved to both contour and texture information makes the algorithm elegant and easy to implement and extend. The data used for experimentally assessing CONTEXT were contours and textures from various application domains, plus a database of medical images. The experiments reveal a high discriminating power which in turn yields a high perceived quality of the retrieval results.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127831643","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957067
L. Maddalena
Scratches are one of the most frequent defects appearing in digital film restoration, usually resolved as missing information in subsequent frames of an image sequence in a vertical area of each frame. We describe some methods for line scratch removal in digital image sequences, based on the idea of using an image model as simple as possible in order to interpolate scratch pixels, evaluating the displacement of such model from the real model in a neighbourhood of the scratch not affected by the defect, and correcting the reconstruction by adding the estimated displacement. Experimental results on real images are shown.
{"title":"Efficient methods for scratch removal in image sequences","authors":"L. Maddalena","doi":"10.1109/ICIAP.2001.957067","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957067","url":null,"abstract":"Scratches are one of the most frequent defects appearing in digital film restoration, usually resolved as missing information in subsequent frames of an image sequence in a vertical area of each frame. We describe some methods for line scratch removal in digital image sequences, based on the idea of using an image model as simple as possible in order to interpolate scratch pixels, evaluating the displacement of such model from the real model in a neighbourhood of the scratch not affected by the defect, and correcting the reconstruction by adding the estimated displacement. Experimental results on real images are shown.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"219 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421392","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956982
M. Sadeghi, J. Kittler, K. Messer
We propose a method of image segmentation using a Gaussian mixture model of the colour image histogram. The model construction is based on the model validation philosophy of architecture selection (Kittler et al., 2001). In contrast with the k-means clustering approach, the number of segments in the proposed scheme is determined completely automatically. We show that the modelling method can be strengthened by incorporating spatial contextual information. The proposed approach speeds up the modelling process by a factor of three. The advocated methodology is successfully applied to the problem of lip pixel segmentation in face images.
提出了一种利用彩色图像直方图的高斯混合模型进行图像分割的方法。模型构建基于架构选择的模型验证哲学(Kittler et al.， 2001)。与k-means聚类方法相比，该方案中的片段数量完全自动确定。我们表明，可以通过纳入空间上下文信息来加强建模方法。提出的方法将建模过程加快了三倍。该方法已成功应用于人脸图像的唇像素分割问题。
{"title":"Spatial clustering of pixels in the mouth area of face images","authors":"M. Sadeghi, J. Kittler, K. Messer","doi":"10.1109/ICIAP.2001.956982","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956982","url":null,"abstract":"We propose a method of image segmentation using a Gaussian mixture model of the colour image histogram. The model construction is based on the model validation philosophy of architecture selection (Kittler et al., 2001). In contrast with the k-means clustering approach, the number of segments in the proposed scheme is determined completely automatically. We show that the modelling method can be strengthened by incorporating spatial contextual information. The proposed approach speeds up the modelling process by a factor of three. The advocated methodology is successfully applied to the problem of lip pixel segmentation in face images.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133895151","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957066
L. D. Stefano, Giovanni Neri, Enrico Viarani
We propose a classification for a set of pixel-level algorithms employed in video surveillance applications and define a performance evaluation metric, based on an analysis of experimental data, for comparing the addressed algorithms. The results of such a comparison are presented and discussed. The set of algorithms considered in this work includes several algorithms widely known in the literature.
{"title":"Analysis of pixel-level algorithms for video surveillance applications","authors":"L. D. Stefano, Giovanni Neri, Enrico Viarani","doi":"10.1109/ICIAP.2001.957066","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957066","url":null,"abstract":"We propose a classification for a set of pixel-level algorithms employed in video surveillance applications and define a performance evaluation metric, based on an analysis of experimental data, for comparing the addressed algorithms. The results of such a comparison are presented and discussed. The set of algorithms considered in this work includes several algorithms widely known in the literature.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"2020 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122420000","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956999
L. D. Stefano, S. Mattoccia, Giovanni Neri, D. Piccinini
The paper proposes a temporal filtering technique for the disparity measurements generated by area-based stereo-matching algorithms. The technique improves temporal consistency of disparity measurements by reducing the matching errors due to noise affecting the imaging system. Moreover, the technique is capable of increasing the number of correct matches by locating uncertain measurements with a criterion based on statistical assumptions that has proven to be more accurate and selective than those relying on texture operators only which are typically deployed with standard area-based stereo algorithms.
{"title":"Temporal filtering of disparity measurements","authors":"L. D. Stefano, S. Mattoccia, Giovanni Neri, D. Piccinini","doi":"10.1109/ICIAP.2001.956999","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956999","url":null,"abstract":"The paper proposes a temporal filtering technique for the disparity measurements generated by area-based stereo-matching algorithms. The technique improves temporal consistency of disparity measurements by reducing the matching errors due to noise affecting the imaging system. Moreover, the technique is capable of increasing the number of correct matches by locating uncertain measurements with a criterion based on statistical assumptions that has proven to be more accurate and selective than those relying on texture operators only which are typically deployed with standard area-based stereo algorithms.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"244 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121271563","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957024
F. Odone, A. Verri, E. Trucco
We propose a method for measuring the similarity between grey level images. The method is able to match images successfully even in the presence of small geometric deformations, illumination changes, and severe occlusions. It fits naturally an implementation based on a comparison of data structures which requires no numerical computations. The range of its applications is vast, and in particular it is a useful tool for object detection and iconic search. We present very good results on real images with and without occlusions, and a qualitative comparative study with a well-known correlation method.
{"title":"A flexible algorithm for image matching","authors":"F. Odone, A. Verri, E. Trucco","doi":"10.1109/ICIAP.2001.957024","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957024","url":null,"abstract":"We propose a method for measuring the similarity between grey level images. The method is able to match images successfully even in the presence of small geometric deformations, illumination changes, and severe occlusions. It fits naturally an implementation based on a comparison of data structures which requires no numerical computations. The range of its applications is vast, and in particular it is a useful tool for object detection and iconic search. We present very good results on real images with and without occlusions, and a qualitative comparative study with a well-known correlation method.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116388921","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957072
R. Hult, E. Bengtsson
An algorithm for fully automatic segmentation of the cortex from T1-weighted axial or sagittal MRI data is presented. When analysing 3D MRI images of the brain it is often important to segment the brain from non-brain tissue such as eyes and membranes of the brain. The segmentation algorithm uses a histogram-based method to find accurate threshold values. Four initial masks are created; first two thresholded masks from the original volume, background and brain tissue, then a third mask thresholded from a 3D grey-level eroded version of the volume, brain tissue, and lastly a fourth mask thresholded from a 3D grey-level dilated version of the volume, containing surrounding fat. On the start slice of these masks, binary morphological operations and logical operations are used. Then the rest of the slices are segmented using information from the previous slice combined with the other masks. Information from earlier slices is propagated to keep the segmented volume from leaking into non-brain tissue.
{"title":"Grey-level morphology based segmentation of MRI of the human cortex","authors":"R. Hult, E. Bengtsson","doi":"10.1109/ICIAP.2001.957072","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957072","url":null,"abstract":"An algorithm for fully automatic segmentation of the cortex from T1-weighted axial or sagittal MRI data is presented. When analysing 3D MRI images of the brain it is often important to segment the brain from non-brain tissue such as eyes and membranes of the brain. The segmentation algorithm uses a histogram-based method to find accurate threshold values. Four initial masks are created; first two thresholded masks from the original volume, background and brain tissue, then a third mask thresholded from a 3D grey-level eroded version of the volume, brain tissue, and lastly a fourth mask thresholded from a 3D grey-level dilated version of the volume, containing surrounding fat. On the start slice of these masks, binary morphological operations and logical operations are used. Then the rest of the slices are segmented using information from the previous slice combined with the other masks. Information from earlier slices is propagated to keep the segmented volume from leaking into non-brain tissue.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116150949","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957005
P. Scheunders
A new wavelet representation for multimodal images is presented. The idea for this representation is based on the first fundamental that provides a local measure for the contrast of a multimodal image. This concept is extended towards multiscale fundamental forms using the dyadic wavelet transform of Mallat. The multiscale fundamental forms provide a local measure for the contrast of a multimodal image at different scales. The representation allows for a multiscale edge description of multimodal images. Two applications are presented: multispectral image fusion and colour image noise filtering. In an experimental section, the presented techniques are compared to single valued and/or single scale algorithms that were previously described in the literature. The techniques based on the new representation are demonstrated to outperform the others.
{"title":"Multiscale fundamental forms: a multimodal image wavelet representation","authors":"P. Scheunders","doi":"10.1109/ICIAP.2001.957005","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957005","url":null,"abstract":"A new wavelet representation for multimodal images is presented. The idea for this representation is based on the first fundamental that provides a local measure for the contrast of a multimodal image. This concept is extended towards multiscale fundamental forms using the dyadic wavelet transform of Mallat. The multiscale fundamental forms provide a local measure for the contrast of a multimodal image at different scales. The representation allows for a multiscale edge description of multimodal images. Two applications are presented: multispectral image fusion and colour image noise filtering. In an experimental section, the presented techniques are compared to single valued and/or single scale algorithms that were previously described in the literature. The techniques based on the new representation are demonstrated to outperform the others.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116213707","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：