Results 301 to 310 of about 2,841,987 (371)

Unsupervised Deep Shape Descriptor With Point Distribution Learning

Computer Vision and Pattern Recognition, 2020
Deep learning models have achieved great success in supervised shape descriptor learning for 3D shape retrieval, classification, and correspondence. However, the unsupervised shape descriptor calculated via deep learning is less studied than that of ...
Yi Shi, Mengchen Xu, Shuaihang Yuan, Yi Fang   +3 more
semanticscholar   +1 more source

Unique Shape Descriptor Algorithm for Medicinal Plant Identification (SDAMPI) With Abridged Image Database

IEEE Sensors Journal, 2020
In image processing, leaf shape recognition requires a huge database of similar images. Normal leaf image database construction requires more time and space.
Jibi G. Thanikkal, Ashwani Kumar Dubey, M. T. Thomas   +2 more
semanticscholar   +1 more source

CONNECTIVITY-BASED SHAPE DESCRIPTORS

International Journal of Computers and Applications, 2010
AbstractIn this paper, we propose a method for indexing and retrieval of images based on shapes of objects. The concept of connectivity is introduced. 3D models are used to represent 2D images. 2D images are decomposed a priori using connectivity which is followed by 3D model construction.
A. Sajjanhar, G. Lu, D.S. Zhang, W. Zhou
openaire   +1 more source

Descriptors of Corneal Shape

Optometry and Vision Science, 1998
With the advent of videokeratoscopy and similar technology, we are now provided with more information about corneal contour than ever before. One of the common problems in this area is which parameters should be used to quantify the corneal shape.
Lindsay, Richard, Smith, George, Atchison, David A.   +2 more
openaire   +2 more sources

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Computer graphics forum (Print), 2019
We present a novel deep learning approach to extract point‐wise descriptors directly on 3D shapes by introducing Siamese Point Networks, which contain a global shape constraint module and a feature transformation operator.
Jun Zhou, M. J. Wang, W. Mao, Minglun Gong, Xiuping Liu   +4 more
semanticscholar   +1 more source

Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field

Optical Engineering: The Journal of SPIE, 2018
. This paper proposes a hierarchical feature-matching model for the typical faults detection, which is a big challenge in the trouble of a moving freight car detection system (TFDS) due to the constant color and complex background of images. The proposed
Guodong Sun, Yang Zhang, Hanbing Tang, Huiming Zhang, Moyun Liu, Daxing Zhao   +5 more
semanticscholar   +1 more source

Integral Contour Angle: An Invariant Shape Descriptor for Classification and Retrieval of Leaf Images

International Conference on Information Photonics, 2018
Leaf identification is a significant and challenging task for computer vision community due to the large intra-class variations and small inter-class differences of leaf image patterns.
Feng Ni, Bin Wang
semanticscholar   +1 more source

Evaluation of MPEG-7 shape descriptors against other shape descriptors

Multimedia Systems, 2003
Shape is an important image feature-it is one of the primary low level image features exploited in content-based image retrieval (CBIR). There are generally two types of shape descriptors in the literature: contour-based and region-based. In MPEG-7, the curvature scale space descriptor (CSSD) and Zernike moment descriptor (ZMD) have been adopted as the
Dengsheng Zhang, Guojun Lu
openaire   +1 more source

Gradient-based shape descriptors

Machine Vision and Applications, 2008
This paper presents two shape descriptors which could be applied to both binary and grayscale images. The proposed algorithm utilizes gradient based features which are extracted along the object boundaries. We use two-dimensional steerable G-Filters (IEEE Trans Pattern Anal Mach Intell 19(6):545–563, 1997) to obtain gradient information at different ...
Abdulkerim Çapar, Binnur Kurt, Muhittin Gökmen   +2 more
openaire   +2 more sources

Shape Discrimination Using Fourier Descriptors

IEEE Transactions on Systems, Man, and Cybernetics, 1977
Description or discrimination of boundary curves (shapes) is an important problem in picture processing and pattern recognition Fourier descriptors (FD's) have interesting properties in this respect. First, a critical review is given of two kinds of FD's.
E, Persoon, K S, Fu
openaire   +2 more sources