Pub Date : 2003-09-17DOI: 10.1109/ICIAP.2003.1234046
S. Bouchafa, B. Zavidovique
A new level-line registration technique is proposed for image transform estimation. This approach is robust towards contrast changes, does not require any estimate of the unknown transformation between images and tackles very challenging situations that usually lead to pairing ambiguities, such as repetitive patterns in the images. The registration itself is performed through an efficient level-line cumulative matching based on a multistage primitive election procedure. Each stage provides a coarse estimate of the transformation that the next stage gets to refine. Although we deal with similarity transforms (rotation, scale and translation), our approach can be easily adapted to more general transformations.
{"title":"Cumulative level-line matching for image registration","authors":"S. Bouchafa, B. Zavidovique","doi":"10.1109/ICIAP.2003.1234046","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234046","url":null,"abstract":"A new level-line registration technique is proposed for image transform estimation. This approach is robust towards contrast changes, does not require any estimate of the unknown transformation between images and tackles very challenging situations that usually lead to pairing ambiguities, such as repetitive patterns in the images. The registration itself is performed through an efficient level-line cumulative matching based on a multistage primitive election procedure. Each stage provides a coarse estimate of the transformation that the next stage gets to refine. Although we deal with similarity transforms (rotation, scale and translation), our approach can be easily adapted to more general transformations.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114888437","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234042
W. Chojnacki, M. Brooks, A. Hengel, D. Gawley
Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here it is shown that FNS (fundamental numerical scheme) and a core version of HEIV (heteroscedastic errors-in-variables) are essentially equivalent, solving a common underlying equation via different means. The analysis is driven by the search for a nondegenerate form of a certain generalised eigenvalue problem, and effectively leads to a new derivation of the relevant case of the HEIV algorithm. This work may be seen as an extension of previous efforts to rationalise and inter-relate a spectrum of estimators, including the renormalisation method of Kanatani and the normalised eight-point method of Hartley.
{"title":"FNS and HEIV: relating two vision parameter estimation frameworks","authors":"W. Chojnacki, M. Brooks, A. Hengel, D. Gawley","doi":"10.1109/ICIAP.2003.1234042","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234042","url":null,"abstract":"Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here it is shown that FNS (fundamental numerical scheme) and a core version of HEIV (heteroscedastic errors-in-variables) are essentially equivalent, solving a common underlying equation via different means. The analysis is driven by the search for a nondegenerate form of a certain generalised eigenvalue problem, and effectively leads to a new derivation of the relevant case of the HEIV algorithm. This work may be seen as an extension of previous efforts to rationalise and inter-relate a spectrum of estimators, including the renormalisation method of Kanatani and the normalised eight-point method of Hartley.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116629103","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234050
L. Cinque, S. Levialdi, A. Malizia
Paper document recognition is fundamental for office automation becoming every day a more powerful tool in those fields where information is still on paper. Document recognition follows from data acquisition, from both journals and entire books, in order to transform them into digital objects. We present a new system for document recognition that follows the open source methodologies, XML description for document segmentation and classification, which turns out to be beneficial in terms of classification precision, and general-purpose availability.
{"title":"A system for the automatic layout segmentation and classification of digital documents","authors":"L. Cinque, S. Levialdi, A. Malizia","doi":"10.1109/ICIAP.2003.1234050","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234050","url":null,"abstract":"Paper document recognition is fundamental for office automation becoming every day a more powerful tool in those fields where information is still on paper. Document recognition follows from data acquisition, from both journals and entire books, in order to transform them into digital objects. We present a new system for document recognition that follows the open source methodologies, XML description for document segmentation and classification, which turns out to be beneficial in terms of classification precision, and general-purpose availability.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"67 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131020725","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234109
F. Tortorella
Support vector machines (SVM) are currently one of the classification systems most used in pattern recognition and data mining because of their accuracy and generalization capability. However, when dealing with very complex classification tasks where different errors bring different penalties, one should take into account the overall classification cost produced by the classifier more than its accuracy. It is thus necessary to provide some methods for tuning the SVM on the costs of the particular application. Depending on the characteristics of the cost matrix, this can be done during or after the learning phase of the classifier. In this paper we introduce two optimization schemes based on the two possible approaches and compare their performance on various data sets and kernels. The first experimental results show that both the proposed schemes are suitable for tuning SVM in cost-sensitive applications.
{"title":"An empirical comparison of in-learning and post-learning optimization schemes for tuning the support vector machines in cost-sensitive applications","authors":"F. Tortorella","doi":"10.1109/ICIAP.2003.1234109","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234109","url":null,"abstract":"Support vector machines (SVM) are currently one of the classification systems most used in pattern recognition and data mining because of their accuracy and generalization capability. However, when dealing with very complex classification tasks where different errors bring different penalties, one should take into account the overall classification cost produced by the classifier more than its accuracy. It is thus necessary to provide some methods for tuning the SVM on the costs of the particular application. Depending on the characteristics of the cost matrix, this can be done during or after the learning phase of the classifier. In this paper we introduce two optimization schemes based on the two possible approaches and compare their performance on various data sets and kernels. The first experimental results show that both the proposed schemes are suitable for tuning SVM in cost-sensitive applications.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131542190","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234086
S. Battiato, A. Bruna, A. Buemi, F. Naccari
In this paper we present a comparison between different approaches to CFA (colour filter array) image encoding. We show different performance offered by a new algorithm based on a vector quantization technique, JPEG-LS, a low complexity encoding standard and classical JPEG. We also show the effects of CFA image encoding on the colour reconstructed images by a typical image generation pipeline. A discussion about the computational complexity and memory requirement of the different encoding approaches is also presented.
{"title":"Coding techniques for CFA data images","authors":"S. Battiato, A. Bruna, A. Buemi, F. Naccari","doi":"10.1109/ICIAP.2003.1234086","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234086","url":null,"abstract":"In this paper we present a comparison between different approaches to CFA (colour filter array) image encoding. We show different performance offered by a new algorithm based on a vector quantization technique, JPEG-LS, a low complexity encoding standard and classical JPEG. We also show the effects of CFA image encoding on the colour reconstructed images by a typical image generation pipeline. A discussion about the computational complexity and memory requirement of the different encoding approaches is also presented.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132636791","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234020
L. Lombardi, A. Petrosino
We present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, length, and symmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. The recognition procedure is formulated as a training procedure made by recursive neural networks followed by a testing procedure over unknown tree structured patterns.
{"title":"Shape recognition by distributed recursive learning of multiscale trees","authors":"L. Lombardi, A. Petrosino","doi":"10.1109/ICIAP.2003.1234020","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234020","url":null,"abstract":"We present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, length, and symmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. The recognition procedure is formulated as a training procedure made by recursive neural networks followed by a testing procedure over unknown tree structured patterns.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133140909","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234060
S. Barotti, L. Lombardi, P. Lombardi
In this paper, we address two of the common faults of indoor background modeling, namely the light switch and the bootstrapping problems. Light switch concerns sudden changes in lighting conditions that cause the failure of a background model of the scene. Bootstrapping problems occur when a training sequence free of moving objects is not available for model building. Our study investigates how rearrangements in the structure of multi-modular vision systems can improve the system performance in a changing environment. In other words, we want to introduce in the system the capability to select the most reliable method for extracting useful information among those available, and to exclude inadequate modules from the flow of signal analysis.
{"title":"Multi-module switching and fusion for robust video surveillance","authors":"S. Barotti, L. Lombardi, P. Lombardi","doi":"10.1109/ICIAP.2003.1234060","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234060","url":null,"abstract":"In this paper, we address two of the common faults of indoor background modeling, namely the light switch and the bootstrapping problems. Light switch concerns sudden changes in lighting conditions that cause the failure of a background model of the scene. Bootstrapping problems occur when a training sequence free of moving objects is not available for model building. Our study investigates how rearrangements in the structure of multi-modular vision systems can improve the system performance in a changing environment. In other words, we want to introduce in the system the capability to select the most reliable method for extracting useful information among those available, and to exclude inadequate modules from the flow of signal analysis.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127811232","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234117
P. Leclercq, John Morris
We have measured the performance of several area-based stereo matching algorithms with noise added to synthetic images. Dense disparity maps were computed and compared with the ground truth using three metrics: the fraction of correctly computed disparities, the mean and the standard deviation of the disparity error distribution. For a noise-free image, S. Birchfield and C. Tomasi's pixel-to-pixel dynamic algorithm performed slightly better than a simple sum-of-absolute-differences algorithm (67% correct matches vs 65%) $considered to be within experimental error. A census algorithm performed worst at only 54%. The dynamic algorithm performed well until the S/N ratio reached 36 dB after which its performance started to drop. However, with correctly chosen parameters, it was superior to correlation and census algorithms until the images became very noisy (/spl sim/15 dB). The dynamic algorithm also ran faster than the fastest correlation algorithms using an optimum window radius of 4, and more than 10 times faster than the census algorithm.
{"title":"Robustness to noise of stereo matching","authors":"P. Leclercq, John Morris","doi":"10.1109/ICIAP.2003.1234117","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234117","url":null,"abstract":"We have measured the performance of several area-based stereo matching algorithms with noise added to synthetic images. Dense disparity maps were computed and compared with the ground truth using three metrics: the fraction of correctly computed disparities, the mean and the standard deviation of the disparity error distribution. For a noise-free image, S. Birchfield and C. Tomasi's pixel-to-pixel dynamic algorithm performed slightly better than a simple sum-of-absolute-differences algorithm (67% correct matches vs 65%) $considered to be within experimental error. A census algorithm performed worst at only 54%. The dynamic algorithm performed well until the S/N ratio reached 36 dB after which its performance started to drop. However, with correctly chosen parameters, it was superior to correlation and census algorithms until the images became very noisy (/spl sim/15 dB). The dynamic algorithm also ran faster than the fastest correlation algorithms using an optimum window radius of 4, and more than 10 times faster than the census algorithm.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127980052","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234023
V. Gesù, Giosuè Lo Bosco, B. Zavidovique
The paper shows an application of a new operator named the iterated object transform (IOT) for cell classification. The IOT has the ability to grasp the internal structure of a digital object and this feature can be usefully applied to discriminate structured images. This is the case of cells representing chondrocytes in bone tissue, giarda protozoan, and myeloid leukaemia. A tree classifier allows us to discriminate the three classes with a good accuracy.
{"title":"Classification based on iterative object symmetry transform","authors":"V. Gesù, Giosuè Lo Bosco, B. Zavidovique","doi":"10.1109/ICIAP.2003.1234023","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234023","url":null,"abstract":"The paper shows an application of a new operator named the iterated object transform (IOT) for cell classification. The IOT has the ability to grasp the internal structure of a digital object and this feature can be usefully applied to discriminate structured images. This is the case of cells representing chondrocytes in bone tissue, giarda protozoan, and myeloid leukaemia. A tree classifier allows us to discriminate the three classes with a good accuracy.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116963882","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234114
S. Cuenca
The paper presents a new efficient approach to texture analysis based on distributions of simple spatial and tonal relationships. The texture description proposed makes use of a semicover concept over binary planes derived from grey images. A measure of the local semicover tendency based on joint occurrences of elementary semicover patterns is described, and a computation simplification method is presented to reduce the computational cost. The method presents a reduced set of parameters that facilitates its optimization in different types of application. The performance of the method is evaluated by means of a comparative study, including other algorithms widely used in texture analysis. The results show a similar or superior performance to other more complex approaches.
{"title":"Texture analysis based on local semicovers","authors":"S. Cuenca","doi":"10.1109/ICIAP.2003.1234114","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234114","url":null,"abstract":"The paper presents a new efficient approach to texture analysis based on distributions of simple spatial and tonal relationships. The texture description proposed makes use of a semicover concept over binary planes derived from grey images. A measure of the local semicover tendency based on joint occurrences of elementary semicover patterns is described, and a computation simplification method is presented to reduce the computational cost. The method presents a reduced set of parameters that facilitates its optimization in different types of application. The performance of the method is evaluated by means of a comparative study, including other algorithms widely used in texture analysis. The results show a similar or superior performance to other more complex approaches.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115476849","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：