Y. Lamdan and H. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme. Intl. Conf. on Computer Vision (ICCV), pages 238--249, 1988.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of three graphs; b) the pattern exactly occurring in two graphs in S; c) the pattern approximately occurring, within one mutation, in all the three graphs. Our strategy to find the patterns in a set of 3D graphs is to decompose the graphs into rigid substructures and then use geometric hashing [14] to organize the substructures and then to find the frequently occurring ones. In [35] we applied the approach to the discovery of patterns in chemical compounds under a restricted set of edit operations including node insert and node delete, and tested the quality of the patterns by using them ....

....hashing technique to find approximately common patterns in a set of 3D graphs without prior knowledge of their structures, positions, or occurrence frequency. The geometric hashing technique used here originated from the work of Lamdan and Wolfson for model based recognition in computer vision [14]. Several researchers attempted to parallelize the technique based on various architectures, such as the Hypercube and the Connection Machine [3, 19, 20] It was observed that the distribution of the hash table entries might be skewed. To balance the distribution of the hash function values, ....

Y. Lamdan and H. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc. Int'l Conf. Computer Vision, 1988, pp. 237--249.

....points are typically corners or mid points of edges extracted from the input image. Thus the number of feature points is smaller than the number of pixels in a region of interest and they contain more useful information per point. For more information on GH we refer you to the original paper [1] or more recent survey article [2] 3. Field Programmable Gate Arrays Reconfigurable computing is becoming a mainstream technology, competing with general purpose processors in a growing marketplace for high performance and low power solutions for mobile and embedded solutions. Modern FPGAs ....

Y. Lamdan and H. Wolfson, "Geometric Hashing: A general and Efficient Modelbased Recognition Scheme", 2nd International Conference on Computer Vision, 1988.

....we can conquer this problem by using some physical features of aspects. In the current example, we may use the location relation of contours shared by two faces, viz. parallel vs intersection, to determine further whether an AIN of Aspect ## or Aspect ## is generated when the score is high enough[7]. In fact, the enforced representation has been used in the previous experiment. 10 Conclusions We have proposed a parallel voting scheme for aspect recovery in the context of the hybrid object recognition . Unlike the previous approach, the parallel voting network simply uses local ....

Y. Lamdan and H.J. Wolfson, "Geometric Hashing: A General And Efficient Model-Based Recognition Scheme," Proc. ICCV'88, 1988, 238-249.

....sequence, search a set of spatial sequences to locate subsequences that are similar to the query sequence. However, traditional database indexing techniques are inadequate for this purpose. There is currently much excellent work in indexing multidimensional data, including geometric hashing[25], grid based index structures[15] and the R tree family[9, 8] index structures. These spatial access methods, are designed to index unsequenced spatial objects. The order among the entities in the database is not taken into consideration when the index structures are created and hence no ....

Y. Lamdan, H. Wolfson, "Geometric Hashing: A General and Efficient Model Based Recognition Scheme." In International Conference on Computer Vision, 213-29, 1988.

....sharing resembling structures may perform similar functions. It is desirable to md common substructures among proteins rather than the whole structures. To perform substructure matching, Fischer et al. 1] have exploited the geometric hashing paradigm previously introduced in computer vision [2]. Their method is based on preprocessing and recognition algorithms of complexity O(n3) where n is the number of residues of interest. Later, Pennec and Ayache [3] introduced a 3D reference frame attached to each residue, which drastically reduces the complexity of recognition. Andrew et al. also ....

....we discuss the algorithm. Some experiment results with the Enzyme Classification Database are provided in Section 3. Conclusions and extension of our work are in Section 4. 2. PROTEIN MODELING AND MATCHING STRATEGY 2. 1 Geometric hashing algorithm The geometric hashing algorithm was introduced [2] for model based recognition in computer vision. It is composed of two stages: pre processing and recognition. The basic idea is to store in a database at pre processing time a redundant representation of the models by rigid transformarion, based on local features to allow for occlusion. By doing ....

Y. Lamdan and H. J. Wolfson. Geometric Hashing: A General and Efficient Model-Based Recognition Scheme: In Proceedings of the IEEE Int. Conf. on Computer Vision, 1988.

....false matches. One interesting dimension of abstraction is rigidity. Near one end of this dimension are the several object recognition algorithms that abstract objects into a rigid or semi rigid geometric juxtaposition of image features. These include Hausdorff distance[1] geometric hashing[2], active blobs[3] and eigenimages[4, 5] In constrast, histogram based approaches abstract away (nearly) all geometric relationships between pixels. In pure histogram matching, e.g. Swain Ballard[6] there is no preservation of geometry, just an accounting of the number of pixels of given ....

Y. Lamdan and H. J. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," presented at Second International Conference on Computer Vision, Tampa, Florida, 1988.

....error. The differences between methods are the transformations (i.e. Projective, Affine, Euclidean etc. and the error metrics used. In contrast, invariants are functions of points that are independent of the transformation and affine invariants are well studied as a tool for matching and indexing [8, 5]. The affine model is also useful since planes under a weak perspective camera model behave in an affine manner. The limitation of standard techniques is that they do not correctly account for data noise. Thus in the case of registration, the commonly used least squares metric might be ....

H.J. Wolfson and Y. Lamdan. Geometric hashing: A general and efficient model-based recognition scheme. In International Conference on Computer Vision, pages 238--249, 1988.

....is that the deformations of object appearance caused by viewpoint changes, although being globally complex, can be approximated by simple transformations at the local scale. Various methods in this category differ in the choice of local image regions and in the features computed over these regions [5, 9, 12, 4, 10, 7, 14, 13]. Invariance in object recognition. In general, invariance to a more complex transformation means better immunity to changes in the image formation process, but also reduction in discriminative power. One would like to be invariant to only such changes, that are really going to happen. Let us ....

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient model based recognition scheme. In Proceedings of International Conference on Computer Vision, pages 238--249, 1988.

....features on an object model and features in the image. Unfortunately, as the number of model features and image features grows, the space of correspondences can grow intractably large, especially if the image contains significant clutter or noise. Indexing techniques such as geometric hashing[23] suffer in the presence of clutter as well. In these approaches, each k tuple of image features casts votes for the identities and or poses of objects in the image, based on their geometric arrangement. If the image contains significant noise[17] or clutter, the votes cast by sets of clutter ....

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proc. ICCV, pages 238--249, 1988.

....on dynamic programming (e.g. 85, 88] cannot be applied to 3D objects. Another problem is the higher dimensionality of 3D data, which makes registration, finding feature correspondences, and fitting model parameters more expensive. As a result, methods that match shapes using geometric hashing [49] or deformations [3, 45, 65, 77, 87] are more difficult in 3D. Shape based recognition of 3D objects is a core problem in computer vision. However, in vision, images or range scans of objects are usually obtained from specific viewpoints, in scenes with clutter and occlusion. Range images ....

Y. Lamdam and H.J. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme. In Proc. ICCV, December 1988.

....error. The differences between methods are the transformations (i.e. Projective, Affine, Euclidean etc. and the error metrics used. In contrast, invariants are functions of points that are independent of the transformation and affine invariants are well studied as a tool for matching and indexing [6, 4]. The affine model is also useful since planes under a weak perspective camera model behave in an affine manner. The limitation of standard techniques is that they do not truly account for the noise in the data. Thus in the case of registration, the commonly used least squares metric might be ....

H.J. Wolfson and Y. Lamdan. Geometric hashing: A general and efficient model-based recognition scheme. In ICCV88, pages 238--249, 1988. 6

....sought to align these points to the model. In the context of molecular docking the ligand provides the model, and the re ceptor provides the set of 3D points that are checked against the model. Techniques developed for model based recognition, like interpretation trees [54] or geometric hashing [77, 109], are thus applicable to the docking problem. In fact, geometric hashing has already been used for molecular docking in protein ligand and protein protein studies [6, 100] In geometric hashing, a hash table for the ligand is computed and this is a transformation invariant representation of the ....

Y. Laindan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In [EEE International Conference on Computer Vision, pages 238-249, Tampa, FL, 1988.

....2D images of these models. 2D recognition systems have long implicitly relied on the descriptions of 2D objects that do not vaxy as the object is rotated or translated in the plane. More recently, invariants have been used for the recognition of planar models from arbitrary, 3D views ( 28] 17] [18], 9] 10] 25] Recently, 3] 5] 6] and [20] have proven that there are no non trivial invariants when models may consist of arbitrary collections of 3D point features. These proofs took the following form. Given any two models, M1 and M2, a set of intermediate models, P, P2 . Pn were ....

....groups that could have produced them. This approach was first used by [19] and has since been taken in: 13] 22] 12] 27] 6] and [7] A number of recent indexing systems for recognizing planax objects from arbitrary 3D views have been based on invariant functions of the image [28] 17] [18], 9] 10] 25] For example, as we have noted, the affine coordinates of a planar model are invariant under affine transformations. 17] 18] use this invariance in their system. 27] describes an indexing system that makes use of invariant descriptions of planar faces of objects, or of ....

[Article contains additional citation context not shown here]

Lamdan, Y. and Wolfson, H., 1988. "Geometric Hashing: A General and Efficient Model-Based Recog- nition Scheme." IEEE Proc. Robotics and Automation:238-249.

....center of each region are used to represent the object. We address both two dimensional as well as three dimensional recognition problems. In both cases, techniques are presented for automatically acquiring the object models. The recognition algorithms are based on the geometric hashing technique [11]. The indices [12] of the hash table are the reflectance ratios of three regions on an object as well as their relative positions. The entries of the table include an object identifier followed by reflectance ratios of other regions on the object and their relative positions. The indices provide a ....

....of the three regions. As geometric invariants we use two angles, and , of the triangle formed by the three regions. Note that these angles are invariant to sinilarit transformations. Hence, the invariant index for the set of three regions is i, Pj, P, which is stored in the hash table [31, 11, 12] as shown below. Pj Figure 7: Three regions form an index for the two dimensional recognition problem. Other regions are used for verification. INDEX ENTRY Not all combinations of regions are used as indices We only use those triplets that lie within a radius D:i that is small relative to ....

Y. Lambdan and H. J. Wolfson. Geometric hashing: A general and efficient model- based recognition scheme. In Proc. ltcratioal Cofcrccc o Computer Visions, pages 238 249, December 1988.

....are more difficult to detect. For example, Grimson s work [12] on matching polyhedral objects to models uses edge features; as every image feature can potentially match every object feature it is necessary to search the space of possible correspondences using an interpretation tree. Other authors [21, 19, 30, 3] have emphasized the grouping of lower level image elements into higher level features. An alternative approach is to work directly in parameter space. A simple example of this can be found in [15] where Horn shows how to instantiate a model of a binary image using image moments. Another ....

Y. Lamdan and H. J. Wolfson, Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. In Proceedings of the Second International Conference on Computer Vision. IEEE, 1988.

....the image data in a redundant manner it is even possible to avoid any communications. The situation changes drastically for high level image processing algorithms like the Fast Fourier Transform, the Viterbi algorithm ( Fou73] or for pattern recognition algorithms like geometric hashing ([YL88]) and other invariant based recognition methods ( NSSM94] Here it is far from trivial to ensure a balanced network workload. Furthermore the communication demands are in general different on the processors and may vary at runtime. the work is supported by the German Science Foundation (DFG) ....

H. J. Wolfson Y. Lamdan. Geometric hashing: A general and efficient model-based recognition scheme. In Proceedings Second International Conference on Computer Vision, pages 238--249, 1988.

....and several perceptual grouping steps can be performed in 5:0 seconds using a partition of CM 5 having 32 PNs. A serial implementation of these steps on a Sun Sparc 400 takes more than 2 minutes. In [18] we have presented scalable algorithms for recognizing flat object using geometric hashing [6]. Object recognition is a key step in an integrated vision system. Recently, geometric hashing [6] has been proposed as an alternate approach for object recognition. However, parallel techniques are needed to perform geometric hashing in high speed [3] We have shown that using a 4M entries model ....

....having 32 PNs. A serial implementation of these steps on a Sun Sparc 400 takes more than 2 minutes. In [18] we have presented scalable algorithms for recognizing flat object using geometric hashing [6] Object recognition is a key step in an integrated vision system. Recently, geometric hashing [6] has been proposed as an alternate approach for object recognition. However, parallel techniques are needed to perform geometric hashing in high speed [3] We have shown that using a 4M entries model database distributed over the entire processor array, a probe on a scene consisting of 256 feature ....

Y. Lamdan and H. Wolfson, Geometric Hashing: A General and Efficient Model Based Recognition Scheme, International Conference on Computer Vision, pages 218--249, 1988.

....for different transforms. The final transform is the global maxima of the sum of the votes. A third way is to provide a mathematical formulation of the model which is invariant under geometric transforms and to recognize the model in the image, after reducing the image to the same formulation [8]. We use the predicted value of the sensor attitude to project the 3 D model into a set of 2 D points. Our recognition method suppose that approximating the deformation between the predicted 2 D appearance and the 3 3 M M A = Figure 3. View of the reconstructed building. real appearance of ....

....the reconstructed building. real appearance of the object by a similarity is sufficient to find a large number of correspondences. We then refine the 3 D sensor attitude from this set of correspondences and solve the remaining ambiguities. For recognition we use a geometric hashing formulation [8]. This method, based on the rigidity assumption, uses the fact that the coordinates of a 2 D object are invariant, up to a similarity, when expressed in a reference frame given by any pair of object points. We characterize the 2 D model in an orthonormal basis, which results from any good pair ....

Y. Lamdan and H.J. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme, in Proc. of the 2nd ICCV, 1988.

....It then adds to this mapping, employing a consistency check as nodes are added to the subgraph. A number of common methods for object recognition combine the problems of recognition and pose determination. Methods such as local feature focus [3] pose clustering [24] and geometric hashing [25], for example. These methods are able to employ additional constraints, generally involving the physical location of graph nodes, to limit potential matches. Some methods of image registration also use this type of approach [7] While these application areas are of interest, this style of ....

Y. Lamden, H. Wolfson, Geometric hashing: a general and efficient modelbased recognition scheme, Proc. 2 nd Int. Conf. On Computer Vision, Tarpon Springs, FL (Nov. 1988) 238-249.

....for dealing with clutter is to segment the scene into object and nonobject components [1] 7] naturally, this is difficult if the position of the object is unknown. An alternative to segmentation is to construct object centered coordinate systems using local features detected in the scene [9] [18]; here again there is the problem of differentiating object features from non object features. Another difficulty occurs because surface data often has missing components, i.e. occlusions. Occlusions will alter global properties of the surfaces and therefore, will complicate construction of ....

....containing clutter, occlusion and 3D surface noise. To differentiate among points, we construct 2D images associated with each point. These images are created by constructing a local basis at an oriented point (3D point with surface normal) on the surface of an object. As in geometric hashing [18], the positions with respect to the basis of other points on the surface of the object can then be described by two parameters. By accumulating these parameters in a 2D histogram, a descriptive image associated with the oriented point is created. Because the image encodes the coordinates of points ....

# Y. Lamdan and H. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc. Second Int'l Conf. Computer Vision, pp. 238-249, 1988.

....and the image and, therefore, the position of the billboard in the image. The direct exhaustive attempt to match every point of the model with every point of the image leads to unacceptable complexity. Instead, we use the original affineinvariant matching technique proposed by Lamdan and Wolfson [7]. We provide a brief description of the algorithm here. We assume the image coordinates to be affine transformed coordinates of the model coordinates. The goal of the matcher is to find an affine transform, which Fig. 5 The feature points selected by the Color based filter maps the model points ....

Y. Lamdan, H.J. Wolfson, `Geometric Hashing: A General and Efficient Model-Based Recognition Scheme', Proc. of ICCV88, pp. 238-249.

....of rotation, translation, distortion and node insert delete in the substructures of the graphs. This is an extension of the traditional substructure search in scientific and biochemical databases [3] The proposed approach is an extension of a computer vision technique, called geometric hashing [1], Work supported by NSF grants IRI 9224602 and IRI9531548. for robotics applications. In Section 2, we describe our algorithms in detail. Section 3 presents some experimental results. Section 4 compares our work with others and concludes the paper. 2 The Approach Our approach is composed of two ....

....search. The experimental results also demonstrated that the proposed approach can achieve very high precision and recall even in the presence of rotation, translation, distortion, and node insert delete in the substructures of the graphs. 4 Conclusion Geometric hashing techniques (e.g. [1, 2]) have been used in many different applications, though most of them do not consider substructure matching. The only exception is [3] in which the authors propose to use magic vectors for substructure matching. The choice of magic vectors is very much domain dependent and is based on the type of ....

Y. Lamdan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proc. Inter. Conf. on Computer Vision, pages 237--249, 1988.

....groups, uniform distribution, invariant measure, invariant distance, expected features, mean features. 1. Introduction Many algorithms in computer vision and object recognition deal with simple geometric features like points, for example the Iterative Closest Point [4, 31] the geometric hashing [18, 30, 26], and the alignment algorithm [3, 13] On the other hand, models of the real world often lead to the consideration of more complex features: lines [9] planes, oriented points [6] frames [21, 22] etc. The handling of these features raises some problems, the first one being their representation, ....

Y. Lamdan and H.J. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proc. of Second ICCV, pages 238--289, 1988.

....Recommended for acceptance by R. Szeliski. For information on obtaining reprints of this article, please send e mail to: tpami computer.org, and reference IEEECS Log Number 105207. 930 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 19, NO. 9, SEPTEMBER 1997 [61] 62] [63], 84] for various extensions and applications of the technique. Our algorithm also makes intensive use of geometric hashing, but in a somewhat different setup. 1.1 Previous Work We first briefly review the fairly extensive literature on the problem of surface or volume matching, studied mainly ....

Y. Lamdan and H.J. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc IEEE Int'l Conf. Computer Vision, pp. 238-249, 1988.

....one mutation (i.e. one node delete insert is allowed in matching a motif with a graph) then S contains one active motif shown in Fig. 3(c) To discover active motifs, we first find candidate substructures from the graphs and then evaluate their activity using the geometric hashing technique (Lamdan Wolfson 1988). To our knowledge, there are two research groups having done work that is closely related to ours: Djoko et al. Djoko, Cook, Holder 1995) studied techniques for substructure discovery in two dimensional graphs; Fischer et al. Fischer et al. 1992) searched for known motifs in 3D proteins. The ....

Lamdan, Y., and Wolfson, H. 1988. Geometric hashing: A general and efficient model-based recognition scheme. In Proceedings of International Conference on Computer Vision, 237--249.

....200 400 11 21 42 80 178 Sequence Set Size F Index Seq Figure 2: Time per query varying # sequences, for range queries 57 6. 4 Color Images Much work on ffl machine vision [BB82, DH73a] TSSM89] WSTM90] CL91, CW92, LH90, LH92] HK92] IX90, Jag91a, KKS 91, CH91, MG89, GNM92, LW88] and [BGS92, SB91, Iok89] ffl much work on fast searching; ffl little communication between DB and MV communities [ACM91, JN92, NBE 93] Except recently [HHLC92] PO93b] PO93a] FBF 94] Goal: Queries on color, shape, texture, e.g. ffl find photos with color distribution similar to ....

Yehezkel Lamdan and Haim J. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In 2nd International Conference on Computer Vision (ICCV), pages 238--249, Tampa, Florida, 1988. IEEE.

No context found.

Y. Lamdan and H. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme. Intl. Conf. on Computer Vision (ICCV), pages 238--249, 1988.

No context found.

Lamdan, Y. & Wolfson, H. (1990), Geometric hashing: A general and efficient model-based recognition scheme, in `Proceedings, 3RD International Conference on Computer Vision', Osaka, Japan, pp. 238--249.

No context found.

Y. Lamdan and H. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," in Proceedings of the International Conference of Computer Vision, 1988, pp. 238-- 249.

No context found.

Y. Lamdan and H. Wolfson. Geometric hashing: A general and efficient modelbased recognition scheme. Proceedings of the 2nd International Conference on Computer Vision, pages 238--249, 1988.

No context found.

Y. Lamdan and H. J. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," in Proce. 2nd Int. Conf. Computer Vision, Tampa, FL, June 1988, pp. 238--249.

No context found.

Y. Lamdan & H.J. Wolfson. "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc. 1998 IEEE ICCV, pp. 238-249.

No context found.

Y. Lamdan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In International Conference on Computer Vision (ICCV88), pages 238--249, 1988.

No context found.

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient modelbased recognition scheme. In Proceedings International Conference On Computer Vision, pages 238--249, 1988.

No context found.

Y. Lamden and H. Wolfson. "Geometric hashing: A general and efficient model-based recognition scheme." In Proc. Int. Conference on Computer Vision, pp. 238-249, December 1988.

No context found.

Y. Lamdan and H. Wolfson, Geometric hashing: A general and efficient model-based recognition scheme, in Proc. 2nd Inter. Conf. Computer Vision, 1988, pp. 238--249.

No context found.

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proceedings International Conference On Computer Vision, pages 238--249, 1988.

No context found.

Y. Lamdan and H. Wolfson. Geometric hashing: A general and efficient model based recognition scheme. In International Conference on Computer Vision, pages 213--29, 1998.

No context found.

Lamdan, Y. and Wolfson, H.J. 1988. Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. In Proc. IEEE Int. Conf. on Computer Vision, Tampa, FL, pp. 238--249.

No context found.

Y. Lamdan and H.J. Wolfson, "Geometric Hashing: A General and Efficient ModelBased Recognition Scheme," Proc. of the 2'nd Int. Conf. on Computer Vision, pp. 238-249, 1988.

No context found.

Y. Lamdan and H. Wolfson, "Geometric hashing: A general and efficient model-based recognition scheme," in Proc. of the IEEE Int. Conf. on Computer Vision, 1988.

No context found.

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient model based recognition scheme. In Proceedings of International Conference on Computer Vision, pages 238-- 249, 1988.

No context found.

Y. Lamdan and H.J. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc. IEEE Int. Conf. on Computer Vision, pp. 238-249, 1998.

No context found.

Y. Lambdan and H. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proc. ICCV, pages 238--249, 1988.

No context found.

Y. Lamdan and H.J. Wolfson, "Geometric Hashing: A General and Efficient ModelBased Recognition Scheme," Proc. of the 2'nd Int. Conf. on Computer Vision, pp. 238-249, 1988.

No context found.

Lamdan, Y., Wolfson, H.: Geometric hashing: A general and efficient model-based recognition scheme. Proceedings of the 2nd International Conference on Computer Vision (1988) 238--249

No context found.

Y. Laindan and H. Wolfson, Geometric hashing: A general and efficient model-based recognition scheme, Second Int. Conf. Cornput. Vis. pp. 238-249. Tampa, Florida, U.S.A. (December 1988).

No context found.

Y. Laindan and H. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme. Proc. Second Int'l Conf. Computer Vision (ICCV '88), pp. 238-249, 1988.

No context found.

Lamdan, Y. and Wolfson, H.J., Geometric Hashing: A General and Efficient Model-Based Recognition Scheme, Proc. ICCV, p.238-249, December 1988.

No context found.

Y. Lamdan and H. Wolfson, "Geometric Hashing: A General and Efficient Model-Based Recognition Scheme," Proc. Int'l Conf. Computer Vision, IEEE Computer Society, 1988, pp. 238--249.

First 50 documents  Next 50

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