{"title":"Multi-spectral based cell segmentation and analysis","authors":"G. Fernandez, Murat Kunt, J. Zrÿd","doi":"10.1109/PBMCV.1995.514682","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514682","url":null,"abstract":"The polychrome analysis of biological samples can yield\u0000information usually masked an monochrome or even color analysis. This\u0000paper shows that after an accurate choice of the spectral bands, the\u0000information obtained can be useful for image analysis purposes (such as\u0000segmentation) and also for biochemical analysis through absorption or\u0000fluorescence measurements. After a description of the image acquisition\u0000system, the core of the algorithm is presented. The method is based on\u0000the approximate reconstruction of the absorption spectrum at each point\u0000in the image. For reconstruction only three observations of\u0000non-overlapping bands are used in an efficient model of the absorption\u0000spectrum of the samples. Such a reconstruction establishes the basis for\u0000the segmentation and also for the analysis of the samples. The\u0000application of this technique has been shown to be specially useful for\u0000pigmented plant cells cultivated in vitro in the framework of the\u0000development of a complete image analysis system for plant cells","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133605478","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}
{"title":"Am Illumination Planner for Convex and Concave Lambertian Polyhedral Objects","authors":"F. Solomon, K. Ikeuchi","doi":"10.1109/PBMCV.1995.514674","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514674","url":null,"abstract":"Abstract : The measurement of shape is a basic object inspection task. We use a noncontact method to determine shape called photometric stereo. The method uses three light sources which sequentially illuminate the object under inspection and a video camera for taking intensity images of the object. A significant problem with using photometric stereo is determining where to place the three light sources and the video camera. In order to solve this problem, we have developed an illumination planner that determines how to position the three light sources and the video camera around the object. The planner determines how to position light sources around an object so that we illuminate a specified set of faces in an efficient manner, and so that we obtain an accurate measurement. We predict the uncertainty in our measurements due to sensor noise by performing a statistical simulation in our planner. This gives us the capability to determine when a measured shape differs in a statistically significant way from what we expect. From a high level, our planner has three major inputs: the CAD model of the object to be inspected, a noise model for our sensor, and a reflectance model for the object to be inspected. We have experimentally verified that the plans generated by the planner are valid and accurate.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133904652","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}
{"title":"Seeing physics, or: physics is for prediction [computer vision]","authors":"M. Brand, P. Cooper, L. Birnbaum","doi":"10.1109/PBMCV.1995.514679","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514679","url":null,"abstract":"We describe how knowledge of the physics of the scene itself is\u0000important to computer vision. High-level knowledge of scene physics can\u0000help programs see the world, and programs that see and understand this\u0000way are useful for planning plan scene interactions. We illustrate these\u0000points with two of our most recent knowledge-intensive vision systems.\u0000One uses knowledge of physics and function to understand noisy and\u0000ambiguous images of gear-train machines; i.e. to report what the machine\u0000does. The other uses physical knowledge to guide a robotic eye-hand\u0000system to pick up a mug of coffee by its handle","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114221803","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}
{"title":"Principal components analysis and neural network implementation of photometric stereo","authors":"Y. Iwahori, R. Woodham, A. Bagheri","doi":"10.1109/PBMCV.1995.514676","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514676","url":null,"abstract":"An implementation of photometric stereo is described in which all\u0000directions of illumination are close to the viewing direction. This has\u0000practical importance but creates a numerical problem that is\u0000ill-conditioned. Ill-conditioning is dealt with in two ways. First, many\u0000more than the theoretical minimum number of required images are\u0000acquired. Second, principal components analysis (PCA) is used as a\u0000linear preprocessing technique to extract a reduced dimensionality\u0000subspace to use as input. Overall, the approach is empirical. The\u0000ability of a radial basis function (RBF) neural network to do\u0000non-parametric functional approximation is exploited. One network maps\u0000image irradiance to surface normal. A second network maps surface normal\u0000to image irradiance. The two networks are trained using samples from a\u0000calibration sphere. Comparison between the actual input and the\u0000inversely predicted input is used as a confidence estimate. Results on\u0000real data are demonstrated","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124610792","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}
{"title":"Polarization based removal of spurious inter-reflections in active ranging","authors":"J. Clark, E. Truces, H.-F. Cheung","doi":"10.1109/PBMCV.1995.514681","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514681","url":null,"abstract":"We report an initial experimental study investigating how polarization analysis can improve the robustness of triangulation-based laser scanners. In particular, we disambiguate the true laser stripe from spurious inter-reflections caused by holes and concavities on metal surfaces by projecting linearly polarised laser light and measuring the polarization state of the linearly polarized component of the reflected light. This takes polarization vision into range sensing, adding, to our best knowledge, a new application to those already explored.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"47 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120812559","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}
{"title":"Nonlinear finite element methods for nonrigid motion analysis","authors":"Wen-Chen Huang, Dmitry Goldgof, L. Tsap","doi":"10.1109/PBMCV.1995.514672","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514672","url":null,"abstract":"The motion of nonrigid or deformable bodies has been studied in\u0000the field of engineering mechanics and applied mathematics for years\u0000with great success. In computer vision, the application of engineering\u0000mechanics for 3D shape fitting and motion analysis is generally called\u0000utilizing deformable shape models or physically-based modeling (usually\u0000using linear FEM). Since many real-world materials behave non-linearly\u0000when they are subjected to large deformations, one cannot expect a\u0000linear FEM to be a good model of many materials undergoing large\u0000deformation. This severely restricts the applications of FEM in many\u0000nonrigid notion analysis problems. In this paper we propose the use of\u0000the nonlinear finite element modeling for the nonrigid motion analysis","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121647491","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}
{"title":"Physically-based adaptive preconditioners for early vision","authors":"S. Lai, B. Vemuri","doi":"10.1109/PBMCV.1995.514680","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514680","url":null,"abstract":"Several problems in early vision have been formulated in the past in a regularization framework. These problems when discretized lead to large sparse linear systems. In this paper, we present a novel physicallybased adaptive preconditioning technique which can be used in conjunction with a conjugate gradient algorithm to drastically improve the speed of convergence for solving the aforementioned linear systems. The adaptation of the preconditioner to an early vision problem is achieved via the explicit use of the spectral characteristics of the regularization filter in conjunction with the data. This spectral function is used to modulate the frequency characteristics of a chosen wavelet basis leading to the construction of our preconditioner. The preconditioning technique is demonstrated for the surface reconstruction, shape from shading and optical flow computation problems. We experimentally establish the superiority of our preconditioning method over previously presented preconditioning techniques for these problems.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121186828","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}
{"title":"New directions in texture modeling using random fields with random spatial interaction","authors":"Athanasios Speis, G. Healey","doi":"10.1109/PBMCV.1995.514683","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514683","url":null,"abstract":"We propose a new model for textured images of real surfaces. We establish a more general theory than the one of ordinary Conditional Markov Fields that allows the strengths of the spatial interaction to be itself a random varaable. For this class of models, we establish the power spectrum and the autocorrelation function as well defined quantities and we extract new features for texture discrimination and analysis. The new set of features that resulted from this approach was applied to real images. In contrast with the traditional Markov Fields (where samples are required to be 50x50 or larger) accurate discrimination was observed even for boxes of site 16x16.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115708663","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}
{"title":"Form from function: a vector field based approach to the analysis of CT images of the vascular tree","authors":"J. Williams, L. B. Wolff","doi":"10.1109/PBMCV.1995.514670","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514670","url":null,"abstract":"We extract topological and local structural information from x-ray computed tomography (CT) volume images of the vascular tree and present it in a form that facilitates creation of physiological models. Physiologists model the vascular tree as a connected network of tubes and, to date, the only accurate data available to produce such models has come from dissection and measurement. Modeling the dynamic behavior of the tree in a living organism has been, until now, impossible. Building models from CT scans will increase the volume and quality of informution available for both the study of physiology and diagnosis. We present an efJicient, accurate analysis technique for volume images of tube networks. Using local operations, the volume image is transformed into a vectorfield which resembles idealized fluid flow through the tube network. This field provides information to condense the salient features of the image into an augmented Euclidean minimum spanning tree (EMST). This augmented EMSTproves to be an information-rich and logical abstract representation of the vascular tree.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114103254","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}
{"title":"Volumetric segmentation of medical images by three-dimensional bubbles","authors":"Hüseyin Tek, B. Kimia","doi":"10.1109/PBMCV.1995.514662","DOIUrl":"https://doi.org/10.1109/PBMCV.1995.514662","url":null,"abstract":"The segmentation of structure from images is an inherently difficult problem in computer vision and a bottleneck to its widespread application, e.g., in medical imaging. This paper presents an approach for integrating local evidence such as regional homogeneity and edge response to form global structure for figure?ground segmentation. This approach is motivated by a shock-based morphogenetic language, where the growth of four types of shocks results in a complete description of shape. Specifically, objects are randomly hypothesized in the form of fourth-order shocks (seeds) which then grow, merge, split, shrink, and, in general, deform under physically motivated “forces,” but slow down and come to a halt near differential structures. Two major issues arise in the segmentation of 3D images using this approach. First, it is shown that the segmentation of 3D images by 3D bubbles is superior to a slice-by-slice segmentation by 2D bubbles or by “212D bubbles” which are inherently 2D but use 3D information for their deformation. Specifically, the advantages lie in an intrinsic treatment of the underlying geometry and accuracy of reconstruction. Second, gaps and weak edges, which frequently present a significant problem for 2D and 3D segmentation, are regularized by curvature-dependent curve and surface deformations which constitute diffusion processes. The 3D bubbles evolving in the 3D reaction?diffusion space are a powerful tool in the segmentation of medical and other images, as illustrated for several realistic examples.","PeriodicalId":343932,"journal":{"name":"Proceedings of the Workshop on Physics-Based Modeling in Computer Vision","volume":"47 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114016889","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}