This paper details a novel approach to specifying the optimal pose of planar targets in camera calibration that both reduces the number of images required, and improves the parameter estimates. This is accomplished within a semi supervised trategy where virtual images of planar calibration targets are generated and displayed. These virtual targets are then replicated by the user to generate an image network with optimal geometry for the recovery of the camera parameters. Optimal planar pose is specified by enforcing maximum independence within the calibration constraints offered by each image within the network. This solution space is further refined to ensure that the generated target pose is suitable for easy acquisition and subsequent feature extraction processes. The results on simulated and real data demonstrate that proper consideration of image network geometry directly leads to more accurate camera parameter estimates.
{"title":"Capturing Optimal Image Networks for Planar Camera Calibration","authors":"Brendan P. Byrne, J. Mallon, P. Whelan","doi":"10.1109/IMVIP.2011.17","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.17","url":null,"abstract":"This paper details a novel approach to specifying the optimal pose of planar targets in camera calibration that both reduces the number of images required, and improves the parameter estimates. This is accomplished within a semi supervised trategy where virtual images of planar calibration targets are generated and displayed. These virtual targets are then replicated by the user to generate an image network with optimal geometry for the recovery of the camera parameters. Optimal planar pose is specified by enforcing maximum independence within the calibration constraints offered by each image within the network. This solution space is further refined to ensure that the generated target pose is suitable for easy acquisition and subsequent feature extraction processes. The results on simulated and real data demonstrate that proper consideration of image network geometry directly leads to more accurate camera parameter estimates.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129526982","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}
3D reconstruction with sparse image sets requires more accurate view geometry estimation than a large number of images based 3D reconstruction. In this paper, we have proposed an automatic 3D reconstruction system based on a small set of images which can estimate the view transformation between different views accurately. The proposed system can build a more complete 3D result when only part of the scene has been initially reconstructed (which often appears in sparse image sets).
{"title":"3D Reconstruction with Sparse Image Sets","authors":"Jiao Tian, D. Molloy","doi":"10.1109/IMVIP.2011.28","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.28","url":null,"abstract":"3D reconstruction with sparse image sets requires more accurate view geometry estimation than a large number of images based 3D reconstruction. In this paper, we have proposed an automatic 3D reconstruction system based on a small set of images which can estimate the view transformation between different views accurately. The proposed system can build a more complete 3D result when only part of the scene has been initially reconstructed (which often appears in sparse image sets).","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128387233","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 study and analysis of blood vessel geometry has become the basis of medical applications related to early diagnosis and effective monitoring of therapies in vascular diseases. This paper presents a new method to trace the outline of blood vessels from imperfect images and extract useful information about their dimensions in an automated manner.The system consists of a segmentation procedure that uses two Active Contours to detect blood vessel boundaries and a novel approach to measure blood vessel diameters directly as the distance between two points. We have succeeded in designing and implementing an automated, robust, measurement method that is not only accurate (it takes away human error) but also user-friendly and requires very little image pre-processing. The system is tested with a set of grey scale images of blood vessels.Results of all the aspects of the design and implementation are presented along with graphs and images.
{"title":"Blood Vessel Diameter Estimation System Using Active Contours","authors":"A. Tizón, J. Courtney","doi":"10.1109/IMVIP.2011.40","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.40","url":null,"abstract":"The study and analysis of blood vessel geometry has become the basis of medical applications related to early diagnosis and effective monitoring of therapies in vascular diseases. This paper presents a new method to trace the outline of blood vessels from imperfect images and extract useful information about their dimensions in an automated manner.The system consists of a segmentation procedure that uses two Active Contours to detect blood vessel boundaries and a novel approach to measure blood vessel diameters directly as the distance between two points. We have succeeded in designing and implementing an automated, robust, measurement method that is not only accurate (it takes away human error) but also user-friendly and requires very little image pre-processing. The system is tested with a set of grey scale images of blood vessels.Results of all the aspects of the design and implementation are presented along with graphs and images.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121962740","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}
This paper describes a skull stripping method for premature infant data. Skull stripping involves the extraction of brain tissue from medical brain images. Our algorithm initially addresses the reduction of the image artefacts and the generation of the binary mask that is used in the initialisation of a region growing brain segmentation process. After segmenting the brain tissue, we detail two novel post processing steps. First, we refine the edges using Kapur entropy, Low Pass Filter and gradient magnitude. Second, we remove the lacrimal glands by applying shape detection, morphological operators and Canny edge detection. The performance evaluation was conducted by comparing the segmented results with the ground truth data marked by our clinical partners.
{"title":"A Morphological Approach for Infant Brain Segmentation in MRI Data","authors":"Michèle Péporté, D. Ilea, E. Twomey, P. Whelan","doi":"10.1109/IMVIP.2011.36","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.36","url":null,"abstract":"This paper describes a skull stripping method for premature infant data. Skull stripping involves the extraction of brain tissue from medical brain images. Our algorithm initially addresses the reduction of the image artefacts and the generation of the binary mask that is used in the initialisation of a region growing brain segmentation process. After segmenting the brain tissue, we detail two novel post processing steps. First, we refine the edges using Kapur entropy, Low Pass Filter and gradient magnitude. Second, we remove the lacrimal glands by applying shape detection, morphological operators and Canny edge detection. The performance evaluation was conducted by comparing the segmented results with the ground truth data marked by our clinical partners.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125568367","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}
F. Sukno, T. A. Chowdhury, J. Waddington, P. Whelan
This work addresses the localization of 11 prominent facial landmarks in 3D by fitting state of the art shape models to 2D data. Quantitative results are provided for 34 scan sat high resolution (texture maps of 10 M-pixels) in terms of accuracy (with respect to manual measurements) and precision(repeatability on different images from the same individual). We obtain an average accuracy of approximately 3 mm, and median repeatability of inter-landmark distances typically below2 mm, which are values comparable to current algorithms on automatic localization of facial landmarks. We also show that, in our experiments, the replacement of texture information by curvature features produced little change in performance, which is an important finding as it suggests the applicability of the method to any type of 3D data.
{"title":"A Quantitative Assessment of 3D Facial Key Point Localization Fitting 2D Shape Models to Curvature Information","authors":"F. Sukno, T. A. Chowdhury, J. Waddington, P. Whelan","doi":"10.1109/IMVIP.2011.14","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.14","url":null,"abstract":"This work addresses the localization of 11 prominent facial landmarks in 3D by fitting state of the art shape models to 2D data. Quantitative results are provided for 34 scan sat high resolution (texture maps of 10 M-pixels) in terms of accuracy (with respect to manual measurements) and precision(repeatability on different images from the same individual). We obtain an average accuracy of approximately 3 mm, and median repeatability of inter-landmark distances typically below2 mm, which are values comparable to current algorithms on automatic localization of facial landmarks. We also show that, in our experiments, the replacement of texture information by curvature features produced little change in performance, which is an important finding as it suggests the applicability of the method to any type of 3D data.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129634518","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}
Parkinson's disease (PD) is a degenerative neurological disease affecting motor, cognitive and autonomic function with symptoms including a resting tremor, rigidity and reduced overall movement. Sufferers often experience communication changes, such as reduced vocal loudness and imprecise articulation, as a result of motor speech disorder. The extent of motor speech disorder (dysarthria) and the efficacy of treatment is currently subjectively assessed by speech and language therapists using standardised tests such as the Frenchay Dysarthria Assessment which assesses speech characteristics and oro-motor control. The outcome of these subjective assessments can be adversely affected by external factors such as the experience of the therapist, therefore there is a recognised need for more objective assessment methods. 3D dynamic computer modelling can be used to capture the movements of the human face in real time to produce a sequence of 3D face meshes over time. This dynamic 3D modelling can be used to objectively assess the extent of facial mobility inParkinson's disease patients with dysarthria. An important step in measuring facial mobility from a sequence of 3D meshes is to identify, in each mesh of the sequence, the location of facial features such as the lip outline. We describe an approach for identifying the lip outline using the mesh data and texture data of a face mesh using integral projection models and an active contour model.
{"title":"Lip Contour Identification in Texture Data of 3D Face Mesh Sequences","authors":"Keith Johnston, P. Morrow, B. Scotney, O. Duffy","doi":"10.1109/IMVIP.2011.13","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.13","url":null,"abstract":"Parkinson's disease (PD) is a degenerative neurological disease affecting motor, cognitive and autonomic function with symptoms including a resting tremor, rigidity and reduced overall movement. Sufferers often experience communication changes, such as reduced vocal loudness and imprecise articulation, as a result of motor speech disorder. The extent of motor speech disorder (dysarthria) and the efficacy of treatment is currently subjectively assessed by speech and language therapists using standardised tests such as the Frenchay Dysarthria Assessment which assesses speech characteristics and oro-motor control. The outcome of these subjective assessments can be adversely affected by external factors such as the experience of the therapist, therefore there is a recognised need for more objective assessment methods. 3D dynamic computer modelling can be used to capture the movements of the human face in real time to produce a sequence of 3D face meshes over time. This dynamic 3D modelling can be used to objectively assess the extent of facial mobility inParkinson's disease patients with dysarthria. An important step in measuring facial mobility from a sequence of 3D meshes is to identify, in each mesh of the sequence, the location of facial features such as the lip outline. We describe an approach for identifying the lip outline using the mesh data and texture data of a face mesh using integral projection models and an active contour model.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"498 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116538453","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}
We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.
{"title":"Real-Time Diffuse Behavior Detection of Pixels from Outdoor Image Sequence","authors":"B. Lal, C. Madsen","doi":"10.1109/IMVIP.2011.37","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.37","url":null,"abstract":"We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126004773","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}
Breast cancer is a major cause of cancer related death worldwide. Screening for breast cancer is achieved using mammography. In this research, we propose a web-based training system for remote access mammography in order to train the radiologists for improving their skills and experiences in interpretation of mammograms, so as to reduce the misdiagnosis. At this stage, we have developed a software viewing tool, called Viewer that allows user to teach themselves by displaying the images on it and drawing the overlay on images.
{"title":"A Web-Based Training System for Remote Access Mammography Screening","authors":"Ye Xiong, D. Molloy, R. Sadleir","doi":"10.1109/IMVIP.2011.33","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.33","url":null,"abstract":"Breast cancer is a major cause of cancer related death worldwide. Screening for breast cancer is achieved using mammography. In this research, we propose a web-based training system for remote access mammography in order to train the radiologists for improving their skills and experiences in interpretation of mammograms, so as to reduce the misdiagnosis. At this stage, we have developed a software viewing tool, called Viewer that allows user to teach themselves by displaying the images on it and drawing the overlay on images.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122367790","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}
Shoaib Ehsan, A. Clark, Wah M. Cheung, Arjunsingh M. Bais, Bayar I. Menzat, N. Kanwal, K. Mcdonald-Maier
In embedded vision systems, parallel computation of the integral image presents several design challenges in terms of hardware resources, speed and power consumption. Although recursive equations significantly reduce the number of operations for computing the integral image, the required internal memory becomes prohibitively large for an embedded integral image computation engine for increasing image sizes. With the objective of achieving high-throughput with minimum hardware resources, this paper proposes a memory-efficient design strategy for a parallel embedded integral image computation engine. Results show that the design achieves nearly 35% reduction in memory for common HD video.
{"title":"Memory-Efficient Design Strategy for a Parallel Embedded Integral Image Computation Engine","authors":"Shoaib Ehsan, A. Clark, Wah M. Cheung, Arjunsingh M. Bais, Bayar I. Menzat, N. Kanwal, K. Mcdonald-Maier","doi":"10.1109/IMVIP.2011.29","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.29","url":null,"abstract":"In embedded vision systems, parallel computation of the integral image presents several design challenges in terms of hardware resources, speed and power consumption. Although recursive equations significantly reduce the number of operations for computing the integral image, the required internal memory becomes prohibitively large for an embedded integral image computation engine for increasing image sizes. With the objective of achieving high-throughput with minimum hardware resources, this paper proposes a memory-efficient design strategy for a parallel embedded integral image computation engine. Results show that the design achieves nearly 35% reduction in memory for common HD video.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129498183","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}
Ketheesan Thirusittampalam, M. J. Hossain, O. Ghita, P. Whelan
The quantitative analysis of cellular migration has found many clinical applications as it can be used in the study of a large spectrum of biological processes such as tumor development and wound healing. These studies are commonly conducted on datasets that consists of a large number of time lapse images, a fact that rendered the application of human assisted procedures as unfeasible, especially when applied to large datasets. In the development of automatic tracking strategies the problem of robust cell segmentation plays a central role as the segmentation errors have adverse effects on the performance of the overall tracking process. While the phase contrast image data is often characterized by low contrast, changes in the morphology of the cells over time and cell agglomeration, the cell segmentation process is far from a trivial task. In this paper we present a new cell segmentation approach that maximizes the information related to the local contrast between the cells and the background in each image of the dataset. The proposed method has been evaluated on MDCK and HUVEC cellular datasets and experimental results are reported.
{"title":"Cell Segmentation in Time-Lapse Phase Contrast Data","authors":"Ketheesan Thirusittampalam, M. J. Hossain, O. Ghita, P. Whelan","doi":"10.1109/IMVIP.2011.30","DOIUrl":"https://doi.org/10.1109/IMVIP.2011.30","url":null,"abstract":"The quantitative analysis of cellular migration has found many clinical applications as it can be used in the study of a large spectrum of biological processes such as tumor development and wound healing. These studies are commonly conducted on datasets that consists of a large number of time lapse images, a fact that rendered the application of human assisted procedures as unfeasible, especially when applied to large datasets. In the development of automatic tracking strategies the problem of robust cell segmentation plays a central role as the segmentation errors have adverse effects on the performance of the overall tracking process. While the phase contrast image data is often characterized by low contrast, changes in the morphology of the cells over time and cell agglomeration, the cell segmentation process is far from a trivial task. In this paper we present a new cell segmentation approach that maximizes the information related to the local contrast between the cells and the background in each image of the dataset. The proposed method has been evaluated on MDCK and HUVEC cellular datasets and experimental results are reported.","PeriodicalId":179414,"journal":{"name":"2011 Irish Machine Vision and Image Processing Conference","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115269816","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：