Arkin, E., Chew, P., Huttenlocher, D., Kedem, K., Mitchel, J.: An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 13 (1991) 209--215  Home/Search   Document Not in Database   Summary   Related Articles   Check

....shape is computed, and the model that is closest to the unknown shape is reported as the best match. Strong arguments from the machine vision and pattern recognition literature argue that for such applications, the function used to measure the di#erence between model and data should be a metric [3, 23]. This means that for a class of expression profiles the di#erence function d should obey the following properties, for any three profiles X, Y , and Z: d(X, Y ) 0 for all X and Y. 1) d(X, Y ) 0 if and only if X = Y (Identity) 2) d(X, Y ) d(Y, X) for all X and Y (Symmetry) 3) d(X, ....

E. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. Patt. Anal. Mach. Intell., 13(3):209--216, 1991.

....shape is computed, and the model that is closest to the unknown shape is reported as the best match. Strong arguments from the machine vision and pattern recognition literature argue that for such applications, the function used to measure the di#erence between model and data should be a metric [3, 21]. This means that for a class of expression profiles the difference function d should obey the following properties, for any three profiles X, Y , and Z: d(X, Y ) 0 for all X and Y. 1) d(X, Y ) 0 if and only if X = Y (Identity) 2) d(X, Y ) d(Y, X) for all X and Y (Symmetry) 3) ....

E. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. Patt. Anal. Mach. Intell., 13(3):209--216, 1991. 8

....methods for representing or retrieval of object based information, polygons are used to represent objects or object regions, corresponding to the boundaries of the object regions. For example, in multimedia information systems, polygons are used in pattern recognition, object based similarity [1, 14], and image processing [12] Another example application can be the representation of geographic information by the help of polygons in geographic information systems [6] In many cases, the polygons have large number of vertices, and managing these polygons is not an easy task. Thus, polygon ....

....of objects in a single video frame, an approximation for the polygons is inevitable. Since dealing with polygons having appropriate size is one of the main motivations of polygon approximation, a reasonable size for the approximated polygons is around 30 vertices. For example, Turning Angle Method [1], a famous polygonal shape comparison method, may not be feasible for polygons having more than 30 vertices. In this method, a (polygonal) object is represented by a set of vertices and shape comparison between any two objects is performed with respect to their turning angle representations. A ....

[Article contains additional citation context not shown here]

E. Arkin, P. Chew, D. Huttenlocher, K. Kedem, and J. Mitchel. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3):209--215, 1991.

.... well motivated manner [9, 10] Other object vision systems for assembly line robots require 3D models of each object, which they iteratively fit to 3D information from the scene [2, 11] A similar approach was followed in [12] where 2D contours were used to classify objects based upon [1]. 2 Polygonal Image Segmentation Formally, we describe an image by a function I (o) that assigns each possible position o i to a pixel value I (o i ) In our current implementation, we just operate on binary images, i.e. I (o) B, but the theoretical framework also applies to the multi valued ....

E. M. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchel. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Image Processing and Machine Intelligence, 13(3):209--215, 1991. 2

....queries and queries specifying spatial layout of the color regions are supported to some extent. However, query by shape is not supported as frequent as query by color. The systems that are capable of handling shape queries use various pattern matching methods (e.g. moments [45] turning angles [2], Hausdorrf distance [21] and work with only images. The general shape information of the images can be queried as well as that of objects in these systems. For object based shape queries, edge detection is applied to the image and then the polygonal object boundaries are compared. Besides, the ....

....other methods su#er from. Since the method gathers information from the pixels, the length and shape of the boundary as well as the presence of holes in the interior have no influence on the method. Besides, there is no polynomial restriction on the object boundaries as in turning angle method [2]. Thus, the method is successful for processing noisy objects. 5.1 Related Work 5.1.1 Query by Color Approaches Color is the most frequent feature that is used in multimedia data querying and retrieval systems. The existing CBR systems are enriched with an easy to index data structure in order ....

[Article contains additional citation context not shown here]

E. Arkin, P. Chew, D. Huttenlocher, K. Kedem, J. Mitchel. An E#ciently Computable Metric for Comparing Polygonal Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3), 209--215, 1991.

.... is to parameterize the boundary by arc length # x#t# y#t# # , for 0 # t # L, with x#t# 2 y#t# 2 = 1, and use the tangent direction #:#0;L# #0; 2## as the function that characterizes the curve: # x#t# y#t# # = # cos ##t# sin ##t# # ; This approach has for example been taken by Arkin et al. #1990#, who considered the L 1 and L 2 norms of the resulting funtion ##t#. Other distances, including the well known Hausdor# distance, have been investigated in this context, see Atallah #1983# and Cox et al. #1989#. Quality control. In the production of arti#cial fabric, one aspect of quality is ....

E. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell: An e#ciently computable metric for comparing polygonal shapes, in: SODA'90, Proc. 1st ACM-SIAM Symp. Discrete Algorithms, San Francisco, January 1990, Society for Industrial and Applied Mathematics, Philadelphia 1990, pp. 129#137.

....The behavior based mobile robot acts in the environments using given behaviors, and obtains sequences of executed actions (called action sequences) for each of them. The action sequences (lists of symbols) are transformed into the real valued vectors (called environment vectors) using chain coding [1]. The environment vectors are stored as cases, and the training phase finishes. Next, in the test phase (Fig.1(b) a robot is placed in a test environment : one of the training environments. The robot tries to identify the test environment with one of training environments, and we call this task ....

....vector be [a 1 , a 2 , an ] a 0 = 0, a i # A1, A2, A3, A4 ) and V = v 1 , v 2 , vm ) respectively. The vector values of V are determined by the following rules. They change the vector value when the direction of movement changes. These rules are considered a kind of chain coding [1]. For example, an action sequence [ A2, A2, A3, A3, A3, A4, A1 ] is transformed into an environment vector ( 1, 2, 1, 0, 1, 1, 1 ) 1. If a i = A1 then v i = v i 1 . 2. If a i = A2 then v i = v i 1 1. 3. If a i = A3 then v i = v i 1 1. 4. If a i = A4 then v i = v i 1 . As ....

[Article contains additional citation context not shown here]

E. M. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Transaction on Pattern Analysis and Machine Intelligence, 13(3):209--216, 1991.

....vector be [a 0 , a 1 , a 2 , an ] a i # A1 , A2 , A3 , A4 , a 0 = 0) and V = v 1 , v 2 , vm ) m # n) respectively. The vector values of V are determined by the following rules. They change the vector value when the direction of movement changes in the similar way to chain coding[1]. An example of an environment vector is shown in Fig.4. If a i = A1 then v i = v i 1 . If a i = A2 then v i = v i 1 1. If a i = A3 then v i = v i 1 1. If a i = A4 then v i = v i 1 . 4 Applying GA to acquire behaviors A behavior is mapping from each state to one of ....

....does not have such advantage. The termination is evaluated with g = No. of E trials) No. of H trials) 2 (Total No. of trials) where E trials and H trials means trials in which a robot escaped from the neighborhood of the start point and trials in which it succeeded in homing. Its range is [0, 1], and it returns 1 when a robot succeeded in homing in all the environments. Accuracy of recognition Another important criterion is accuracy of identifying test environments. The accuracy is evaluated by the following formula. h = No. of successful test env. Total No. of test env. Its range ....

[Article contains additional citation context not shown here]

E. M. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Transaction on Pattern Analysis and Machine Intelligence, 13(3):209--216, 1991.

No context found.

Arkin, E., Chew, P., Huttenlocher, D., Kedem, K., Mitchel, J.: An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 13 (1991) 209--215

No context found.

E.M. Arkin, L.P. Chew, D.P. Huttenlocher, K. Kedem, and J.S.B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Recognition and Machine Intelligence, 13:209--216, 1991.

No context found.

M. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. PAMI, 13:209--206, 1991.

No context found.

E. M. Arkin, L. P. Chew, D. P. Huttenlocher, K. Kedem, and J. S. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3):209--216, March 1991.

No context found.

Arkin, E., Chew, P., Huttenlocher, D., Kedem, K., Mitchel, J.: An e#ciently computable metric for comparing polygonal shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 13 (1991) 209--215

No context found.

E.M. Arkin, L.P. Chew, D.P. Huttenlocher, K. Kedem, J.S.B. Mitchell: An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence13ll

No context found.

E. Arkin, P. Chew, D. Huttenlocher, K. Kedem, and J. Mitchel. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3):209--215, 1991.

No context found.

E.M. Arkin, L.P.Chew, D.P.Huttenlocher, K.Kedem, and J.S.B. Mitchell. An e#ciently computable metric for comparing polygonal shapes. IEEE Transactions on PAMI, 13#3#, March 1991.

No context found.

Esther Arkin, Paul Chew, Daniel Huttenlocher, Klara Kedem, and Joseph Mitchel. An eÆciently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3):209-215, 1991.

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