发布求助
文献互助 智能选刊 最新文献

Computer Vision, Graphics, and Image Processing最新文献

筛选
英文 中文
Symbolic reasoning in object extraction 对象抽取中的符号推理
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90087-C
Amnon Meisels, Doron Mintz
{"title":"Symbolic reasoning in object extraction","authors":"Amnon Meisels,&nbsp;Doron Mintz","doi":"10.1016/0734-189X(90)90087-C","DOIUrl":"10.1016/0734-189X(90)90087-C","url":null,"abstract":"<div><p>A realization of the top-down use of knowledge in the process of extraction of simple man-made objects from aerial photographs is presented. The finding of objects is performed by a reasoning rule-based program written in prolog. The program is purely symbolic and has no access to digital data, yet it produces the needed objects by controlling three other modules of the system through a purely symbolic interface. The program was run as a road finder on aerial images and the experiment is described in detail. We demonstrate the simple “programmability architecture” of the program by presenting examples of simple additions that make it find different kinds of simple objects. Our paradigm makes it possible to understand much better, via the reasoning mechanism, the process of object extraction.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 447-459"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90087-C","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132674585","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}
引用次数: 8
On topology as applied to image analysis 论拓扑学在图像分析中的应用
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90084-9
Gabor T Herman
{"title":"On topology as applied to image analysis","authors":"Gabor T Herman","doi":"10.1016/0734-189X(90)90084-9","DOIUrl":"10.1016/0734-189X(90)90084-9","url":null,"abstract":"<div><p>We discuss the recently published claim of V. A. Kovalevsky that the topology of cellular complexes is the only appropriate topology for image analysis. In some sense we confirm this claim and even generalize it from the finite domain to an infinite one. We prove some results which can be interpreted to show that the class of partially ordered sets is strictly equivalent to a class of topological spaces which is certainly powerful enough to handle all of image analysis. However, such equivalence does not carry over when the partially ordered sets are complemented with a dimension function so as to form cellular complexes. In fact, it remains unclear whether the <em>subclass</em> of cellular complexes which use the assignment of dimension which is standard in image analysis is indeed powerful enough to encompass all problems of image analysis.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 409-415"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90084-9","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121916090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 50
On characterizing ribbons and finding skewed symmetries 关于色带的特征和发现偏斜对称性
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90079-B
Jean Ponce
{"title":"On characterizing ribbons and finding skewed symmetries","authors":"Jean Ponce","doi":"10.1016/0734-189X(90)90079-B","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90079-B","url":null,"abstract":"<div><p>Following Rosenfeld, we compare Blum, Brooks, and Brady ribbons. We prove that Blum and Brady ribbons are not, in general, Brooks ribbons. Conversely, we prove that Brooks ribbons are, in general, neither Blum nor Brady ribbons. For Blum and Brady ribbons, it is in principle trivial to decide whether two contour points may form a ribbon pair: they have to form a local symmetry. This property is not true for Brooks ribbons. It is possible to characterize locally the pairs of contour points which form a Brooks ribbon pair? Using the curvature of the contour of a Brooks ribbon, we show that the answer to this question is yes for some classes of Brooks ribbons, including skewed symmetries. This result is used in an implemented algorithm for finding skewed symmetries in an image, and examples of segmentation of real images are given.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 328-340"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90079-B","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"137438521","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}
引用次数: 0
Systolic implementation of the adaptive solution to normal equations 实现了收缩正常方程的自适应解
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90083-8
P Comon, Y Robert, D Trystram
{"title":"Systolic implementation of the adaptive solution to normal equations","authors":"P Comon,&nbsp;Y Robert,&nbsp;D Trystram","doi":"10.1016/0734-189X(90)90083-8","DOIUrl":"10.1016/0734-189X(90)90083-8","url":null,"abstract":"<div><p>We are interested in the systolic computation of projection operators entering digital signal processing, or more precisely, solution of the so-called normal equations involved in adaptive systems. The systolic array proposed achieves a real-time adaptive solution, i.e., updates the left- and right-hand sides of the linear equation and computes its solution at each time step.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 402-408"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90083-8","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116321313","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}
引用次数: 0
Vector field restoration by the method of convex projections 向量场的凸投影复原方法
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90081-6
Patrice Y Simard , Guy E Mailloux
{"title":"Vector field restoration by the method of convex projections","authors":"Patrice Y Simard ,&nbsp;Guy E Mailloux","doi":"10.1016/0734-189X(90)90081-6","DOIUrl":"10.1016/0734-189X(90)90081-6","url":null,"abstract":"<div><p>In this paper, the theory of image restoration by projections onto closed convex sets is applied to the restoration of vector fields. A set of useful projection operators is presented together with a linear time numerical implementation. These projection operators can be used to restore from partial information the velocity or deformation fields computed between successive views of a scene. They also find applications in the restoration of vector fields of physical quantities as those encountered in mechanics, hydrodynamics, or electromagnetism. The method is compared with the variational approach and illustrated by restoring simulated vector fields.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 360-385"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90081-6","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126464945","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}
引用次数: 25
Finding point correspondence and determining motion of a rigid object from two weak perspective views 从两个弱透视图中寻找点对应并确定刚体的运动
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90078-A
Chia-Hoang Lee, Thomas Huang
{"title":"Finding point correspondence and determining motion of a rigid object from two weak perspective views","authors":"Chia-Hoang Lee,&nbsp;Thomas Huang","doi":"10.1016/0734-189X(90)90078-A","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90078-A","url":null,"abstract":"<div><p>Given two images of an <em>n</em>-point configuration which undergoes 3D rotation, translation, and scaling, our problems are (i) How can we match the corresponding points in the two images? Can all the possible mapping be found? (ii) What underlying motions and associated depth components of these points could account for the two images? (iii) Can the object be recovered uniquely? This formulation of the <em>n</em>-point problem is in the most general setting and does not assume attributes or features. A natural question to ask is whether an <em>n</em>-point problem is equivalent to a set of fewer-point problems. This paper presents a method which reduces an <em>n</em>-point problem to a set of 4-point problems. The effort of reduction takes <em>O(n)</em> steps and it also takes <em>O(n)</em> steps to construct all possible mappings of an <em>n</em>-point set from the solution to a 4-point problem. Other results include (1) coplanarity condition of four points in two views, (2) recovering the tilt direction of the rotational axis using four points in two views, (3) recovering the scaling factor.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 309-327"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90078-A","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"137438167","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}
引用次数: 0
Synchronous multiprocessor implementation of the Hough transform 同步多处理器实现的霍夫变换
Computer Vision, Graphics, and Image Processing Pub Date : 1990-12-01 DOI: 10.1016/0734-189X(90)90086-B
D Ben-Tzvi, A Naqvi, M Sandler
{"title":"Synchronous multiprocessor implementation of the Hough transform","authors":"D Ben-Tzvi,&nbsp;A Naqvi,&nbsp;M Sandler","doi":"10.1016/0734-189X(90)90086-B","DOIUrl":"10.1016/0734-189X(90)90086-B","url":null,"abstract":"<div><p>Normally, in parallel implementations of the Hough transform either the transform space or the set of image features can be distributed among the processing elements. A method is proposed to link parallel access to feature points in the image, and parallel access to the transform space. A synchronous processing sequence is suggested such that both can be distributed. Real-time performance has been obtained on a MIMD distributed memory architecture.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 3","pages":"Pages 437-446"},"PeriodicalIF":0.0,"publicationDate":"1990-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90086-B","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128603114","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}
引用次数: 26
Polygonal representation: A maximum likelihood approach 多边形表示:最大似然方法
Computer Vision, Graphics, and Image Processing Pub Date : 1990-11-01 DOI: 10.1016/0734-189X(90)90056-2
Thomas L Hemminger, Carlos A Pomalaza-Ráez
{"title":"Polygonal representation: A maximum likelihood approach","authors":"Thomas L Hemminger,&nbsp;Carlos A Pomalaza-Ráez","doi":"10.1016/0734-189X(90)90056-2","DOIUrl":"10.1016/0734-189X(90)90056-2","url":null,"abstract":"<div><p>Image boundaries are frequently approximated with polygons. The polygonal approximation technique described here constructs straight lines from digital line segments having the same angular orientation. The procedure sequentially analyzes the segmented contour while producing a diminishing set of candidate lines. When particular conditions prevail, a straight line may be recognized. These operations are performed on integer and set variables only, obviating the need for floating point calculations.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 2","pages":"Pages 239-247"},"PeriodicalIF":0.0,"publicationDate":"1990-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90056-2","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134203995","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}
引用次数: 11
Shape from texture using the Wigner distribution 形状从纹理使用维格纳分布
Computer Vision, Graphics, and Image Processing Pub Date : 1990-11-01 DOI: 10.1016/0734-189X(90)90057-3
Jack Y Jau , Roland T Chin
{"title":"Shape from texture using the Wigner distribution","authors":"Jack Y Jau ,&nbsp;Roland T Chin","doi":"10.1016/0734-189X(90)90057-3","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90057-3","url":null,"abstract":"<div><p>This paper presents a method for estimating the orientation of a textured surface as a descriptor of surface shape. It is based on the analysis of local spectral information of the texture in an image. The local spectrum representation is computed by the two-dimensional Wigner distribution, which gives the spatial-frequency information as a function of location. The change in texture density, or the so-called <em>texture gradient</em>, caused by the perspective projection of a surface in the three-dimensional world onto the two-dimensional image plane, is computed from this space-frequency representation by measuring the high frequency energy distribution at each location of the image. The surface orientation is then estimated from the texture gradient. This method was implemented for the limited case of planar surfaces. Simulations were performed and results were analyzed to address issues related to the method's estimation accuracy, implementation, and limitations.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 2","pages":"Pages 248-263"},"PeriodicalIF":0.0,"publicationDate":"1990-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90057-3","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"137281692","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}
引用次数: 0
Automated stereophotogrammetry 自动化立体摄影测量术
Computer Vision, Graphics, and Image Processing Pub Date : 1990-11-01 DOI: 10.1016/0734-189X(90)90059-5
Greg Brookshire, Morton Nadler, Choon Lee
{"title":"Automated stereophotogrammetry","authors":"Greg Brookshire,&nbsp;Morton Nadler,&nbsp;Choon Lee","doi":"10.1016/0734-189X(90)90059-5","DOIUrl":"10.1016/0734-189X(90)90059-5","url":null,"abstract":"<div><p>In this paper we outline a structural pattern recognition approach to the stereo matching problem of automated stereophotogrammetry. Oriented-edge graphs are obtained with the edge vectors and filtered to obtained feature points for matching purposes. A resolution pyramid is based to aid the accurate matching of the feature points. At each stage of the pyramid, pseudo-hexagonal gray scale arrays are used to bypass the four-eight connectivity paradox in the implementation of association of oblique vectors in Bowker's association filter. The Fisher-<span><math><mtext>z</mtext></math></span> transform is used to determine the correlation function threshold in matching. To fill the gaps between the matched nodes, a local interpolation method that linearly weights the disparity values in a window was developed. The interpolated points are not used for matching, but give the initial approximation at the next lower stage of the resolution pyramid. Finally, a modified normalized gray-scale correlation is used to refine the parallax found at the lowest level of the pseudo-hex resolution pyramid using the original 2D raster. The correlation scheme used here works in both directions: from left to right and from right to left, to obtain reliable matching. We have tried to use as simple operations as possible in each stage to allow the algorithm to run in real-time, possibly leading to an economical hardware implementation.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 2","pages":"Pages 276-296"},"PeriodicalIF":0.0,"publicationDate":"1990-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90059-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115704927","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}
引用次数: 9
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信