S. Sarkar and K. L. Boyer, "Perceptual organization in computer vision: A review and proposal for a classificatory structure," IEEE trans. on Systems, Man, and Cybernetics, 23(2), 382-399, 1993.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....features (curves, points, contours, symmetries and ribbons) Segmentation of a scene is achieved by choosing good collations, and reasoning on the geometric relationships between them. Applications to stereo, object level segmentation and shape description are described. A recent survey article [41] on perceptual organization stresses its hierarchical nature, starting with preattentive grouping and reaching up to knowledge driven construction. A classification scheme is proposed for sorting the instances of grouping by domain and abstraction level. 3.2 Axial representation of planar shape ....

S. Sarkar, K.L. Boyer, Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure, IEEE Trans. on Systems, Man and Cybern., 23, 1993, 382-399.

....planar groups between Frame 1 (shown) and Frame 2. The motion of the hnes lying in the plane has been correctly modelled by the arline deformation, whereas the motion of those out of the plane has not. 37] and Lowe [18] that it was considered seriously for computer vision. Sarkar and Boyer [26] offer a very good review of what work has been done in what areas of this field, and in what regions there has been little effort, particularly mentioning motion analysis and the role motion segmentation can play in improving algo rithms. Sarkar and Boyer [25] have also offered a structure for ....

S. Sarkar and K.L. Boyer. Perceptual organization in computer vision: A review and a proposal for a classificatory structure. IEEE Trans. on Systems, Man, and Cybernetics, 23(2):382-399, 1993.

....learned from examples. For instance, g i might denote an edge element computed at location i in the image plane, and d ij might denote some measure corresponding to smooth continuation, co circularity, etc. For an overview over various features and strategies for perceptual grouping we refer to [23]. According to the spatial context modeled by d ij , we wish to separate familiar con gurations from the (unknown) background. To this end, following [10] we label each primitive g i with a decision variable x i 2 f1; 1g ( 1 corresponding to gure, 1 corresponding to background and noise) ....

S. Sarkar and K.L. Boyer. Perceptual organization in computer vision: A review and a proposal for a classicatory structure. IEEE Tr. Systems, Man, and Cyb., 23(2):382-399, 1993.

....INTELLIGENCE, VOL. 20, NO. 2, FEBRUARY 1998 187 2GROUPING CUES AND THEIR REPRESENTATION Perceptual grouping is traditionally concerned with the use of grouping information (or cues) for image partitioning tasks, such as figure ground discrimination, segmentation, and edge completion [19] [18]. Here, on the other hand, such grouping cues are not used to partition the image but to confirm an existing, modelbased segmentation. To represent the grouping information, we recall the framework developed in our work on a generic grouping algorithm and its analysis [1] 3] We shall use ....

.... the framework developed in our work on a generic grouping algorithm and its analysis [1] 3] We shall use the following three concepts: 1) Grouping cues: Many grouping cues (some known as Wertheimer s Laws of Grouping [12] were suggested in the grouping literature (see, e.g. 12] 19] [18]) In the following examples, the grouping cue is a smoothness criterion: a function which decides whether or not two edge points belong to the same smooth curve. 1 Grouping cues (or just cues) are considered here to be random binary functions of data features pairs (e.g. edge points) For ....

S. Sarkar and K.L. Boyer, "Perceptual Organization in Computer Vision: A Review and Proposal for a Classifactory Structure," IEEE Trans. Systems, Man and Cybernetics, vol. 23, no. 2, pp. 382-- 399, Mar./Apr. 1993.

.... (in contrary to random sub sampling, that is sometimes used for similar saving reasons, e.g. with the Hough transform [15] but has no effect on the signal to noise ratio) Figure ground discrimination is, therefore, a useful pre processing filtering stage for many computer vision applications [7, 13, 4]. Our starting point is the following observation. We argue that the figure ground discrimination problem is asymmetric. A data feature which belong to the figure set must be a part of some structure. In order to figure this out, we need to find this structure, either explicitly or implicitly. On ....

S. Sarkar and K. L. Boyer. Perceptual organization in computer vision: a review and proposal for a classifactory structure. IEEE Transactions on System, Man and Cybernetics 23, 2 (March/April 1993), 382--399.

.... (in contrary to random sub sampling, that is sometimes used for similar saving reasons, e.g. with the Hough transform [17] but has no effect on the signal to noise ratio) Figure ground discrimination is, therefore, a useful pre processing filtering stage for many computer vision applications [8, 15, 5]. Our starting point in this paper is the following observation. We argue that the figure ground discrimination problem is asymmetric. A data feature which belong to the figure set must be a part of some structure. In order to figure this out, we need to find this 5 structure, either explicitly ....

S. Sarkar and K. L. Boyer. Perceptual organization in computer vision: a review and proposal for a classifactory structure. IEEE Transactions on System, Man and Cybernetics, 23(2):382-- 399, March/April 1993.

.... features; a system that identifies perceptually significant grouping properties in human vision based upon features such as co termination, continuation along a straight or smoothly changing path, symmetry and closure [15] A survey of perceptual organisation in computer vision can be found in [25]. There is a significant difference between these computer vision systems and the application detailed here; the computer vision system is inherently probabilistic in nature, where a fundamentally correct image is distorted by noise, optical imperfections or problems associated with the feature ....

S. Sarker and K. Boyer. Perceptual organization in computer vision: A review and a proposal for a classification structure. IEEE Transactions on Systems, Man and Cybernetics, 23(2):382 -- 99, 1993.

....additional challenge is that objects may be arbitrarily complex in terms of size and shape. Many segmentation methods proposed for medical image data are either direct applications or extensions of approaches from computer vision. image segmentation algorithms can be classified in many ways [14] [21], 34] We identify three broad classes that divide algorithms to segment sampled image data: manual, semiautomatic, and automatic. Reviews of algorithms from each class can be found in [10] and [24] The image segmentation algorithm presented in this paper is a 0278 0062 99 10.00 1999 IEEE ....

S. Sarkar and K. L. Boyer, "Perceptual organization in computer vision: A review and a proposal for a classificatory structure," IEEE Trans. Syst. Man Cybern., vol. 23, pp. 382--399, 1993.

....have to be employed to stabilize the search process. After feature extraction, feature grouping is used in order to reduce the search space dimension and concentrate the image information [19] Grouping uses perceptual organization criteria generally expressed as geometric constraints [25] [29], 15] 27] Nevertheless, in noisy and complex images of superposed structures, low level feature grouping can get trapped in local optima. In order to overcome this difficulty, additional model based information is needed such as the intrinsic grouping properties of the geometric shapes used in ....

....subjects related to our work: dynamic contours, elastic models, and template matching. A dynamic contour (DC) is a deformable continuous closed curve. The use of DC in computer vision can inherently overcome two important difficulties in feature grouping: edge organization and region merging [25] [29], 19] This is due to their connectivity and closure intrinsic properties [16] 33] 34] The connectivity implicitly incorporates the continuity and proximity criteria that are extensively used in perceptual organization [25] 29] 23] Contour closure reflects the line region duality and ....

[Article contains additional citation context not shown here]

S. Sarkar and K.L. Boyer, "Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure," IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382-399, 1993.

....An additional challenge is that objects may be arbitrarily complex in terms of size and shape. Many segmentation methods proposed for medical image data are either direct applications or extensions of approaches from computer vision. Image segmentation algorithms can be classified in many ways [15][11] 27] We identify three broad classes that divide algorithms to segment sampled image data as: manual, semi automatic, and automatic. Reviews of algorithms from each class can be found in [7] 18] The image segmentation algorithm presented in this paper is a semiautomatic approach. The manual ....

S. Sarkar and K. L. Boyer, "Perceptual organization in computer vision: a review and a proposal for a classificatory structure," IEEE Trans. Syst. Man. Cybern., vol. 23, pp. 382-399, 1993.

....image features together than are themselves too weak to be useful recognition or navigation cues, but once combined provide strong visual constraints. Binford [5] and Lowe [23] demonstrated early examples of grouping mechanisms; a more recent review is contained in the paper by Sarkar and Boyer [35]. Typically grouping uses geometric measures such as proximity or orientation to associate features rather than employing topology. One clear situation in which the benefits of using topological cues for grouping overcome the brute force methods occurs in the alignment algorithm of Huttenlocher ....

Sarkar, S. and Boyer, K.L. "Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure," IEEE Systems, Man, and Cybernetics, Vol. 23, p.382-399, 1993.

....experiments are needed for quality assessment and threshold setting of procedures of line extraction and perceptual grouping. Fourth, we integrate a series of gestaltic cues spanning over signal level, primitive level, structural level, and assembly level (four level classi cation proposed in [5]) We present a catalogue of propositions each describing a compatibility. They depend on thresholds i which must be determined in an experimentation phase. 2 Geometric photometric compatibilities The propositions in this section describe compatibilities between global geometric entities and ....

S. Sarkar and K. Boyer. Perceptual organization in Computer Vision { A review and a proposal for a classicatory structure. IEEE Transactions on Systems, Man, and Cybernetics, 23:382-399, 1993.

....some of these problems. The rules for grouping features are either very general and do not apply to real imagery or are rather specific and depend on the specific task. Most of the work was done in grouping two dimensional features but there also exists some work in 3D, for an overview see (Sarkar and Boyer, 1993). Apart from early work (cf. Clowes, 1971) Brooks, 1987) Herman and Kanade, 1986) grouping straight lines or planes in 3D mostly appears in the context of building extraction from aerial images (cf. Roux and McKeown, 1994) Henricsson, 1996) Frere et al. 1997) Baillard et al. 1999) ....

Sarkar, S. and Boyer, K., 1993. Perceptual organization in computer vision: A review and a proposal for a classificatory structure. Transaction on Systems, Man, and Cybernetics 23, pp. 382--399.

....models, each corresponding to a different object in the image. Recall that in Section III A: Local Models, we assigned each pixel as belonging to a particular local model. Thus we have segmented the pixels in the image into objects. The algorithm above uses principles of perceptual organisation [21] to group the local models. Similar work has been done by Boldt et al. 22] and Dolan et al. 23] The algorithm as is has been found to sometimes fail under either of two common conditions. The first is when two objects intersect. At such a point, the dominant eigenvector of a local model does ....

Sudeep Sarkar and Kim L. Boyer, "Perceptual organization in computer vision: A review and a proposal for a classificatory structure," IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382--399, Mar 1993.

.... role of perceptual organization in human vision was known by the Gestalt psychologists long before it was first introduced in computer vision [31, 10] In computer vision, there is evidently much more interest in perceptual grouping since 1983 than there was before (e.g. see the review in [28]) This is probably due to a combination of system needs and of the great progress achieved during a short period by Lowe [21] Witkin and Tenenbaum [32] Zucker [35] and others. A major part of grouping study in computer vision was devoted to support object recognition systems. Object ....

....we recall the framework developed in our work on a generic grouping algorithm and its analysis [2, 4] We shall use the following three concepts: 1. Grouping cues Many grouping cues (some known as Wertheimer s Laws of Grouping [31] were suggested in the grouping literature (see e.g. [21, 32, 28]) In the following 4 examples the grouping cue is a smoothness criterion: a function which decides whether or not two edge points belong to the same smooth curve 1 . Grouping cues (or just cues) are considered here to be random binary functions of data features pairs (e.g. edge points) For a ....

S. Sarkar and K. L. Boyer. Perceptual organization in computer vision: a review and proposal for a classifactory structure. IEEE Transactions on System, Man and Cybernetics, 23(2):382--399, March/April 1993.

.... of grouping is a delicate issue, as in many practical cases situations, it is not straightforward or even possible to specify the correct result for a grouping process (An indirect evaluation of the grouping quality is possible by measuring its effect on higher processes (e.g. recognition, see [Jac88, SB93]) Still, we shall assume here that such a specification exists, in the form of image partitioning to several subsets. In the simplest form, which we consider first, the image is partitioned into a figure subset and a noise background subset. One quantifier of the grouping quality is the ....

Sudeep Sarkar and Kim L. Boyer. Perceptual organization in computer vision: A review and proposal for a classifactory structure. IEEE Transactions on System, Man and Cybernetics, 23(2):382--399, March/April 1993.

No context found.

S. Sarkar and K. L. Boyer, "Perceptual organization in computer vision: A review and proposal for a classificatory structure," IEEE trans. on Systems, Man, and Cybernetics, 23(2), 382-399, 1993.

....Section IX. II. Relationship to Prior Research In this section we provide a brief review of the work in perceptual organization and the related work in motion tracking. For a detailed review of the work in perceptual organization along with a synopsis of the various computational approaches see [18]. We present a short summary here. The prior work in perceptual organization can be classified with respect to the types of features used, in order of increasing complexity: signal, primitive, structural, and assembly, and the dimensions over which the organizations are sought [18] 2D, 3D or ....

....approaches see [18] We present a short summary here. The prior work in perceptual organization can be classified with respect to the types of features used, in order of increasing complexity: signal, primitive, structural, and assembly, and the dimensions over which the organizations are sought [18]: 2D, 3D or 2 1 2 D, 2D plus motion, and 3D (2 1 2D) plus motion. Thus one can talk of 2D signal level perceptual organization or 2D time structural level organization. Most of the work in perceptual organization involves 2D static images. The 2D signal level is concerned with organizing ....

S. Sarkar and K. L. Boyer, "Perceptual organization in computer vision: A review and a proposal for a classificatory structure," IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, pp. 382--399, Mar. 1993.

No context found.

S. Sarkar and K. L. Boyer. Perceptual organization in computer vision: A review and proposal for a classifactory structure. IEEE Transactions on System, Man and Cybernetics, 23(2):382399, March/April 1993.

No context found.

S. Sarkar and K.L. Boyer, "Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure," IEEE Trans. Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382399, 1993.

No context found.

S. Sarkar, K. L. Boyer, "Perceptual Organization in Computer Vision: a Review and a Proposal for a Classification Structure", IEEE Transactions on Systems, Man and Cybernetics, Vol. 23, No. 2, March/April, 1993.

No context found.

Sarkar, S. and Boyer, K. L., "Perceptual Organization in Computer Vision: A Review and a proposal for a Classificatory Structure," IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 2, pp. 382-399, Mar. 1993.

No context found.

S. Sarkar and K. Boyer. Perceptual Organization in Computer Vision: A Review and a Proposal for a Classificatory Structure. IEEE Transactions on Systems, Man, and Cybernetics, 23(2):382--399, 1993.

No context found.

S. Sarkar and K. L. Boyer. Perceptual organization in computer vision: A review and a proposal for a classificatory structure. IEEE Transaction on Systems, Man, and Cybernetics, 23(2):382--399, March 1993.

No context found.

Sarkar, S., and Boyer, K. L. 1993b. Perceptual organization in computer vision: a review and a proposal for a classificatory structure. IEEE Trans. Syst. Man Cybern. 23, 382-399.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC