Pub Date : 2007-11-12DOI: 10.1109/ICIP.2007.4379951
Qing Wu, Tian Xia, Yizhou Yu
Visual data comprises of multi-scale and inhomogeneous signals. In this paper, we exploit these characteristics and develop an adaptive data approximation technique based on a hierarchical tensor-based transformation. In this technique, an original multi-dimensional image is transformed into a hierarchy of signals to expose its multi-scale structures. The signal at each level of the hierarchy is further divided into a number of smaller tensors to expose its spatially inhomogeneous structures. These smaller tensors are further transformed and pruned using a collective tensor approximation technique. Experimental results indicate that our technique can achieve higher compression ratios than existing functional approximation methods, including wavelet transforms, wavelet packet transforms and single-level tensor approximation.
{"title":"Hierarchical Tensor Approximation of Multidimensional Images","authors":"Qing Wu, Tian Xia, Yizhou Yu","doi":"10.1109/ICIP.2007.4379951","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379951","url":null,"abstract":"Visual data comprises of multi-scale and inhomogeneous signals. In this paper, we exploit these characteristics and develop an adaptive data approximation technique based on a hierarchical tensor-based transformation. In this technique, an original multi-dimensional image is transformed into a hierarchy of signals to expose its multi-scale structures. The signal at each level of the hierarchy is further divided into a number of smaller tensors to expose its spatially inhomogeneous structures. These smaller tensors are further transformed and pruned using a collective tensor approximation technique. Experimental results indicate that our technique can achieve higher compression ratios than existing functional approximation methods, including wavelet transforms, wavelet packet transforms and single-level tensor approximation.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116379607","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379821
Fatih Kamisli, D. Baylon
Weighted prediction (WP) is one way of overcoming the limitations of simple motion compensation for scenes with gradual transitions such as fades or dissolves. In WP, the predictions for inter coded blocks are obtained from scaled versions of the reference frames. H.264/AVC is the first video coding standard that has incorporated WP tools. In this paper, we focus on the estimation of weights for WP in dissolves. Our findings indicate that the estimation approaches for dissolves should be different from the estimation approaches for fades. Specifically, estimating the weights jointly for the two reference frames of B-frames gives better performance for dissolves under most circumstances.
{"title":"Estimation of Fade and Dissolve Parameters for Weighted Prediction in H.264/AVC","authors":"Fatih Kamisli, D. Baylon","doi":"10.1109/ICIP.2007.4379821","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379821","url":null,"abstract":"Weighted prediction (WP) is one way of overcoming the limitations of simple motion compensation for scenes with gradual transitions such as fades or dissolves. In WP, the predictions for inter coded blocks are obtained from scaled versions of the reference frames. H.264/AVC is the first video coding standard that has incorporated WP tools. In this paper, we focus on the estimation of weights for WP in dissolves. Our findings indicate that the estimation approaches for dissolves should be different from the estimation approaches for fades. Specifically, estimating the weights jointly for the two reference frames of B-frames gives better performance for dissolves under most circumstances.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116578055","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4378949
R. Chartrand
We show that using a nonconvex penalty term to regularize image reconstruction can substantially improve the preservation of object shapes. The commonly-used total-variation regularization, int |nablau|, penalizes the length of object edges. We show that int |nablau|p, 0 < p < 1, only penalizes edges of dimension at least 2 - p, and thus finite-length edges not at all. We give numerical examples showing the resulting improvement in shape preservation.
我们证明了使用非凸惩罚项来正则化图像重建可以大大提高物体形状的保存。常用的全变分正则化(int |nablau)惩罚对象边的长度。我们证明了int |nablau|p, 0 < p < 1，只惩罚维度至少为2 - p的边，因此不惩罚有限长边。我们给出了数值例子来证明在形状保存方面的改进。
{"title":"Nonconvex Regularization for Shape Preservation","authors":"R. Chartrand","doi":"10.1109/ICIP.2007.4378949","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4378949","url":null,"abstract":"We show that using a nonconvex penalty term to regularize image reconstruction can substantially improve the preservation of object shapes. The commonly-used total-variation regularization, int |nablau|, penalizes the length of object edges. We show that int |nablau|p, 0 < p < 1, only penalizes edges of dimension at least 2 - p, and thus finite-length edges not at all. We give numerical examples showing the resulting improvement in shape preservation.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122293457","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4380011
Weijia Shen, A. Kassim
This paper presents a novel scheme for automatic initialization for all types of deformable models. Our method is able to automatically generate a close-to-boundary initialization which is independent of the subsequent segmentation process. Therefore, our method enables different types of deformable models achieve more accurate and robust results. Topographic independent component analysis (TICA) based feature extraction technique is presented for learning a representation from a set of un-labeled image patches. During learning, a topographic map of basis components emerge. An intelligent contour generation procedure is also proposed. Experimental results on abdominal CT images demonstrate the potential of our approach.
{"title":"A New Scheme for Automatic Initialization of Deformable Models","authors":"Weijia Shen, A. Kassim","doi":"10.1109/ICIP.2007.4380011","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4380011","url":null,"abstract":"This paper presents a novel scheme for automatic initialization for all types of deformable models. Our method is able to automatically generate a close-to-boundary initialization which is independent of the subsequent segmentation process. Therefore, our method enables different types of deformable models achieve more accurate and robust results. Topographic independent component analysis (TICA) based feature extraction technique is presented for learning a representation from a set of un-labeled image patches. During learning, a topographic map of basis components emerge. An intelligent contour generation procedure is also proposed. Experimental results on abdominal CT images demonstrate the potential of our approach.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122491859","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379873
Jingwei Wang, Xinbo Gao, J. Zhong
A video watermarking embedding and detection algorithm is proposed in complex wavelet transform (CWT) domain. The host video sequence is firstly segmented into shots. Then each shot is projected onto 3D CWT domain. To achieve robustness while keeping imperceptibility, a perceptual mask derived from 3D complex wavelet coefficients is introduced to weight the watermarks and the results is added back to the complex wavelet coefficients. Finally the inverse 3D CWT is applied to obtain the watermarked video shots. The experimental results illustrate that the proposed algorithm has more advantages in remaining video qualities while keeping the same resistance to attacks over that in discrete wavelet transform (DWT) domain.
{"title":"A Video Watermarking Based on 3-D Complex Wavelet","authors":"Jingwei Wang, Xinbo Gao, J. Zhong","doi":"10.1109/ICIP.2007.4379873","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379873","url":null,"abstract":"A video watermarking embedding and detection algorithm is proposed in complex wavelet transform (CWT) domain. The host video sequence is firstly segmented into shots. Then each shot is projected onto 3D CWT domain. To achieve robustness while keeping imperceptibility, a perceptual mask derived from 3D complex wavelet coefficients is introduced to weight the watermarks and the results is added back to the complex wavelet coefficients. Finally the inverse 3D CWT is applied to obtain the watermarked video shots. The experimental results illustrate that the proposed algorithm has more advantages in remaining video qualities while keeping the same resistance to attacks over that in discrete wavelet transform (DWT) domain.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122554023","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4380049
M. Gueham, A. Bouridane, D. Crookes
In this paper, a method for automatically recognizing partial shoeprint images for use in forensic science is presented. The technique uses the phase-only correlation (POC) for shoeprints matching. The main advantage of this method is its capability to match low quality shoeprint images accurately and efficiently. In order to achieve superior performance, the use of a spectral weighting function is also proposed. Experiments were conducted on a database of images of 100 different shoes available on the market. For experimental evaluation, test images including different perturbations such as noise addition, blurring and textured background addition were generated. Results have shown that the proposed method is very practical and provides high performance when processing low quality partial-prints. The use of a weighting function provides an improvement in the recognition rate in particularly difficult cases.
{"title":"Automatic Recognition of Partial Shoeprints Based on Phase-Only Correlation","authors":"M. Gueham, A. Bouridane, D. Crookes","doi":"10.1109/ICIP.2007.4380049","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4380049","url":null,"abstract":"In this paper, a method for automatically recognizing partial shoeprint images for use in forensic science is presented. The technique uses the phase-only correlation (POC) for shoeprints matching. The main advantage of this method is its capability to match low quality shoeprint images accurately and efficiently. In order to achieve superior performance, the use of a spectral weighting function is also proposed. Experiments were conducted on a database of images of 100 different shoes available on the market. For experimental evaluation, test images including different perturbations such as noise addition, blurring and textured background addition were generated. Results have shown that the proposed method is very practical and provides high performance when processing low quality partial-prints. The use of a weighting function provides an improvement in the recognition rate in particularly difficult cases.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122606875","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379266
G. Maclair, B. D. Senneville, M. Ries, B. Quesson, P. Desbarats, J. Benois-Pineau, C. Moonen
Real-time magnetic resonance (MR) thermometry provides continuous temperature mapping inside the human body and is therefore a promising tool to monitor and control interventional therapies based on thermal ablation. Temperature information must be mapped to a reference position of observed organs in order to allow thermal dose computation, as the history of temperature is required for each pixel. Motion compensated MR-thermometry for thermotherapy has to cope with radio-frequency (RF) artifacts and relaxation-time changes of the monitored tissue. While purely optical-flow-based realignment may lead to temperature map computation errors for the case of local or global intensity changes, principal component analysis based realignment results in accurately registered temperature maps. The motion estimation process described in this paper consists of two steps : a parameterized flow models is initially computed using a principal component analysis during a preparative learning step; during the intervention, motion is characterized with a small set of parameters using a least square solver.
{"title":"PCA-Based Image Registration : Application to On-Line MR Temperature Monitoring of Moving Tissues","authors":"G. Maclair, B. D. Senneville, M. Ries, B. Quesson, P. Desbarats, J. Benois-Pineau, C. Moonen","doi":"10.1109/ICIP.2007.4379266","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379266","url":null,"abstract":"Real-time magnetic resonance (MR) thermometry provides continuous temperature mapping inside the human body and is therefore a promising tool to monitor and control interventional therapies based on thermal ablation. Temperature information must be mapped to a reference position of observed organs in order to allow thermal dose computation, as the history of temperature is required for each pixel. Motion compensated MR-thermometry for thermotherapy has to cope with radio-frequency (RF) artifacts and relaxation-time changes of the monitored tissue. While purely optical-flow-based realignment may lead to temperature map computation errors for the case of local or global intensity changes, principal component analysis based realignment results in accurately registered temperature maps. The motion estimation process described in this paper consists of two steps : a parameterized flow models is initially computed using a principal component analysis during a preparative learning step; during the intervention, motion is characterized with a small set of parameters using a least square solver.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122908423","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379948
P. A. Raj, V. Appala
This paper proposes a method for fast computation of inverse Krawtchouk moment transform for signal and image reconstruction using Clenshaw's recurrence formula. It is shown that the proposed approach requires lesser computations than the straightforward method of computation for signal and image reconstruction. In order to verify the proposed approach, simulation results are reported for 1D signal and 2D image reconstructions from the given Krawtchouk moments for signal and image. The proposed approach is suitable for parallel VLSI implementation because the proposed structure is simple, regular and modular.
{"title":"Fast Computation of Inverse Krawtchouk Moment Transform using Clenshaw's Recurrence Formula","authors":"P. A. Raj, V. Appala","doi":"10.1109/ICIP.2007.4379948","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379948","url":null,"abstract":"This paper proposes a method for fast computation of inverse Krawtchouk moment transform for signal and image reconstruction using Clenshaw's recurrence formula. It is shown that the proposed approach requires lesser computations than the straightforward method of computation for signal and image reconstruction. In order to verify the proposed approach, simulation results are reported for 1D signal and 2D image reconstructions from the given Krawtchouk moments for signal and image. The proposed approach is suitable for parallel VLSI implementation because the proposed structure is simple, regular and modular.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122223829","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4380054
Jaideep Vaidya, Bhakti Tulpule
Privacy is of growing concern in today's day and age. Protecting the privacy of health data is of paramount importance. With the rapid advancement in imaging technology, analysis of medical images is now one of the most dynamic fields of study today. Image analysis is performed for a variety of purposes, ranging from image enhancement to image segmentation. It can easily be seen that having access to more information makes the analysis results more accurate. For example, supervised classification based image segmentation requires good and plentiful training data. We wish to utilize the training data at different locations to obtain more accurate image segmentation while still protecting the privacy of individual patients. Work in the field of secure multi-party computation (SMC) in cryptography shows how to compute functions securely and quantifies what it means to be secure. Applying SMC protocols in image processing is a challenging problem. This paper looks at how some of this work can be leveraged to perform privacy-preserving image analysis and classification.
{"title":"Enabling Better Medical Image Classification Through Secure Collaboration","authors":"Jaideep Vaidya, Bhakti Tulpule","doi":"10.1109/ICIP.2007.4380054","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4380054","url":null,"abstract":"Privacy is of growing concern in today's day and age. Protecting the privacy of health data is of paramount importance. With the rapid advancement in imaging technology, analysis of medical images is now one of the most dynamic fields of study today. Image analysis is performed for a variety of purposes, ranging from image enhancement to image segmentation. It can easily be seen that having access to more information makes the analysis results more accurate. For example, supervised classification based image segmentation requires good and plentiful training data. We wish to utilize the training data at different locations to obtain more accurate image segmentation while still protecting the privacy of individual patients. Work in the field of secure multi-party computation (SMC) in cryptography shows how to compute functions securely and quantifies what it means to be secure. Applying SMC protocols in image processing is a challenging problem. This paper looks at how some of this work can be leveraged to perform privacy-preserving image analysis and classification.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116883093","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379753
Dongqing Chen, A. Farag, M. Hassouna, R. Falk, G. Dryden
Curvature-based geometric features have been proven to be important for colonic polyp detection. In this paper, we present an automatic detection framework and color coding scheme to highlight the detected polyps. The key idea is to place the detected polyps at the same locations in a newly created polygonal dataset with the same topology and geometry properties as the triangulated mesh surface of real colon dataset, and assign different colors to the two separated datasets to highlight the polyps. Finally, we validate the proposed framework by computer simulated and real colon datasets. For fifteen synthetic polyps with different shapes and different sizes, the sensitivity is 100%, and false positive is 0. For four real colon datasets, the proposed algorithm has achieved the sensitivity of 75%.
{"title":"Geometric Features Based Framework for Colonic Polyp Detection using a New Color Coding Scheme","authors":"Dongqing Chen, A. Farag, M. Hassouna, R. Falk, G. Dryden","doi":"10.1109/ICIP.2007.4379753","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379753","url":null,"abstract":"Curvature-based geometric features have been proven to be important for colonic polyp detection. In this paper, we present an automatic detection framework and color coding scheme to highlight the detected polyps. The key idea is to place the detected polyps at the same locations in a newly created polygonal dataset with the same topology and geometry properties as the triangulated mesh surface of real colon dataset, and assign different colors to the two separated datasets to highlight the polyps. Finally, we validate the proposed framework by computer simulated and real colon datasets. For fifteen synthetic polyps with different shapes and different sizes, the sensitivity is 100%, and false positive is 0. For four real colon datasets, the proposed algorithm has achieved the sensitivity of 75%.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117026298","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：