Zobrazeno 1 - 10
of 38
pro vyhledávání: '"John J. Weng"'
Autor:
John J. Weng, Y. Cui
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 21:798-804
We present a prediction-and-verification segmentation scheme using attention images from multiple fixations. A major advantage of this scheme is that it can handle a large number of different deformable objects presented in complex backgrounds. The s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fcea88279872207e42731a740ad42a47
https://doi.org/10.1109/34.784311
https://doi.org/10.1109/34.784311
Publikováno v:
Multimedia Tools and Applications. 7:181-212
Large image databases are commonly employed in applications like criminal records, customs, plant root databases, and voters‘ registration databases. Efficient and convenient mechanisms for database organization and retrieval are essential. A quick
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b203d4887a476d8926397a99fb6ace2
https://doi.org/10.1023/a:1009618917283
https://doi.org/10.1023/a:1009618917283
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 19:451-464
A transitory image sequence is one in which no scene element is visible through the entire sequence. This article deals with some major theoretical and algorithmic issues associated with the task of estimating structure and motion from transitory ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd3312066b357a08c0e5316add936140
https://doi.org/10.1109/34.589205
https://doi.org/10.1109/34.589205
Publikováno v:
International Journal of Computer Vision. 25:109-143
This paper presents a framework called Cresceptron for view-based learning, recognition and segmentation. Specifically, it recognizes and segments image patterns that are similar to those learned, using a stochastic distortion model and view-based in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a0a5ba5731a6bcc209ef6ccf5ac0031
https://doi.org/10.1023/a:1007967800668
https://doi.org/10.1023/a:1007967800668
Publikováno v:
Pattern Recognition Letters. 17:309-316
In this paper, we propose an unbiased minimum variance estimator to estimate the parameters of an ellipse. A space decomposition scheme is presented to direct the search of the optimal parameters. Experimental results have shown the dramatic improvem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24efef7889400170ea1f50e422284ee3
https://doi.org/10.1016/0167-8655(95)00114-x
https://doi.org/10.1016/0167-8655(95)00114-x
Autor:
John J. Weng
Publikováno v:
International Journal of Computer Vision. 11:211-236
A theoretical framework is presented in which windowed Fourier phase (WFP) is introduced as the primary matching primitive. Zero-crossings and peaks correspond to special values of the phase. The WFP is quasi-linear and dense; and its spatial period
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2b80432f3a2ee6e054ac585a62b50cd
https://doi.org/10.1007/bf01469343
https://doi.org/10.1007/bf01469343
Autor:
John J. Weng, Daniel L. Swets
Publikováno v:
Biometrics ISBN: 9780387285399
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0114d3810452bfaedfa98da45f7df41
https://doi.org/10.1007/0-306-47044-6_3
https://doi.org/10.1007/0-306-47044-6_3
Publikováno v:
Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL'99).
Fisher's discriminant analysis is very powerful for classification but it does not perform well when the number of classes is large but the number of samples in each class is small. We propose to resolve this problem by dynamically grouping classes a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bae47bb466ce05e84ec6f6153001854a
https://doi.org/10.1109/ivl.1999.781115
https://doi.org/10.1109/ivl.1999.781115
Autor:
John J. Weng, Wey-Shiuan Hwang
Publikováno v:
ICPR
Our goal is to enable machines to learn directly from sensory input streams. The learning machine does not require human teacher to specify any content-level rule. Such a capability requires a fundamentally new way of addressing the learning problem,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::054cf58acd556287da9f75afca6f577c
https://doi.org/10.1109/icpr.1998.711128
https://doi.org/10.1109/icpr.1998.711128
Publikováno v:
SPIE Proceedings.
A sensory mapping method, called Staggered Hierarchical Mapping (SHM), and its developmental algorithm are described in this paper. SHM is a model motivated by human early visual pathways including processing performed by the retina, Lateral Genicula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d3ed9c3d76b6a6238afbc22dca905254
https://doi.org/10.1117/12.457457
https://doi.org/10.1117/12.457457