Filters








4,431 Hits in 2.3 sec

Local vs Global Descriptors of Hippocampus Shape Evolution for Alzheimer's Longitudinal Population Analysis [chapter]

Jean-Baptiste Fiot, Laurent Risser, Laurent D. Cohen, Jurgen Fripp, François-Xavier Vialard
2012 Lecture Notes in Computer Science  
algorithm, density transport and integration on a hippocampus subregion, which is able to outperform global descriptors.  ...  this template do not directly perform as well as global descriptors (e.g. volume difference), we propose a novel strategy combining the use of initial momentum from geodesic shooting, extended Kärcher  ...  is computed, (3) all local shape deformation descriptors are transported towards this template, (4) SVM classification is performed for local descriptors on the whole domain and on a subregion, and local  ... 
doi:10.1007/978-3-642-33555-6_2 fatcat:kb2hgt6lsvbm3l7o44elcuxn2y

Adaptive Tuboid Shapes for Action Recognition [chapter]

Roman Filipovych, Eraldo Ribeiro
2009 Lecture Notes in Computer Science  
These features are based on the information content inside subregions extracted at locations of interest in a video.  ...  We suggest that the local shape of spatio-temporal subregions defined by changes in local information content can be used as a descriptor of the underlying motion.  ...  Rather than using information inside video-subregions, our features are based on the shapes of tuboid regions designed to follow the local information flow.  ... 
doi:10.1007/978-3-642-10520-3_34 fatcat:653ss2qxvvasvigvgywbvdxanq

Scale Invariant Gabor Descriptor-Based Noncooperative Iris Recognition

Yingzi Du, Craig Belcher, Zhi Zhou
2010 EURASIP Journal on Advances in Signal Processing  
Two feature region maps were designed to locally and globally register the feature points and each subregion in the map is locally adjusted to the dilation/contraction/deformation.  ...  In this method, the iris features are extracted using a Gabor descriptor. The feature extraction and comparison are scale, deformation, rotation, and contrast-invariant.  ...  Brief Review of SIFT-Based Methods Local descriptor-based methods are widely used.  ... 
doi:10.1155/2010/936512 fatcat:ljxigpfgvneexcmvyrbq5qmjra

OSRI: A Rotationally Invariant Binary Descriptor

Xianwei Xu, Lu Tian, Jianjiang Feng, Jie Zhou
2014 IEEE Transactions on Image Processing  
from local image patches.  ...  Index Terms-Binary descriptor, rotation invariant, local order pattern, real-time matching, feature matching.  ...  INTRODUCTION E STABLISHING visual correspondences based on feature point descriptors is an essential component of many computer vision applications, such as image localization [1] , 3D reconstruction  ... 
doi:10.1109/tip.2014.2324824 pmid:24846607 fatcat:okhp3hif2ndk3hgk2wfhvpisye

A New Local Descriptor Based on Strings for Face Recognition

Hicham Zaaraoui, Abderrahim Saaidi, Rachid El Alami, Mustapha Abarkan
2020 Journal of Electrical and Computer Engineering  
This paper proposes the use of strings as a new local descriptor for face recognition.  ...  Therefore, the information of the local and global properties of an object is obtained.  ...  New Local Descriptor Based on Strings. e intervention of a local descriptor in the feature extraction step is primary.  ... 
doi:10.1155/2020/3451808 fatcat:j3mfrzwlfjdgpimjwguq6o3t7a

Determining the scale of interest regions in videos

Roman Filipovych, Eraldo Ribeiro
2009 2009 16th IEEE International Conference on Image Processing (ICIP)  
Improved information quality has been achieved from recently developed entropy-based spatio-temporal feature descriptors.  ...  These features often consist of local spatio-temporal descriptors centered at locations provided by an interest point detector.  ...  Also, the circular region indicates the idealized scale of a local descriptor.  ... 
doi:10.1109/icip.2009.5413805 dblp:conf/icip/FilipovychR09 fatcat:2aqcwz74kje67giw6z5xh46r3m

A dissimilarity kernel with local features for robust facial recognition

Weilin Huang, Hujun Yin
2010 2010 IEEE International Conference on Image Processing  
In this paper, a novel framework for robust face recognition is presented that considers both local and global features by using multi-resolution LBP descriptors.  ...  Index Terms-Local binary pattern, local feature, dissimilarity measure, robustness, conditionally positive semi-definite kernel  ...  In [6] , facial spatial information was enhanced by splitting image into many subregions and an LBP descriptor was applied to each subregion.  ... 
doi:10.1109/icip.2010.5653495 dblp:conf/icip/HuangY10 fatcat:i4whell2enbyzmcz7ff47jmsgu

Gauge-SURF descriptors

Pablo F. Alcantarilla, Luis M. Bergasa, Andrew J. Davison
2013 Image and Vision Computing  
based descriptors such as: SURF, Modified-SURF (M-SURF) 14 and SIFT, in both standard and upright forms.  ...  Our family 4 of descriptors, called Gauge-SURF (G-SURF), are based on second-order 5 multiscale gauge derivatives.  ...  When comparing gauge-derivatives 616 based descriptors and first-order local derivatives ones, without any subregion 617 overlap nor any Gaussian weighting step, we can observe that GU-SURF (64) 618 obtained  ... 
doi:10.1016/j.imavis.2012.11.001 fatcat:7l7u3ogwknbi7on62nq3slpf5i

Learning moment-based fast local binary descriptor

Abdelkader Bellarbi, Nadia Zenati, Samir Otmane, Hayet Belghit
2017 Journal of Electronic Imaging (JEI)  
when compared with state-of-the-art real-time local descriptors.  ...  Recently, binary descriptors have attracted significant attention due to their speed and low memory consumption; however, using intensity differences to calculate the binary descriptive vector is not efficient  ...  Inspired by Weber's law, Chen et al. 21 proposed a local descriptor called the Weber local descriptor.  ... 
doi:10.1117/1.jei.26.2.023006 fatcat:lsmwkcpolvhypapcgkadi4lcq4

Scale- and Affine-Invariant Fan Feature

Chunhui Cui, King Ngi Ngan
2011 IEEE Transactions on Image Processing  
The Fan features are then described by Fan-SIFT, which is an extension of the famous scale-invariant feature transform (SIFT) descriptor.  ...  Specifically, the image neighborhood of a keypoint is depicted by multiple fan subregions, namely Fan features, to provide robustness to surface discontinuity and background change.  ...  The semi-local filter [37] is based on the consensus of nearby local affine transforms.  ... 
doi:10.1109/tip.2010.2103948 pmid:21224174 fatcat:6ewnowo3e5c2vmwrvyj5q3k7vq

Edgel templates for fast planar object detection and pose estimation

Taehee Lee, Stefano Soatto
2011 2011 10th IEEE International Symposium on Mixed and Augmented Reality  
We describe a method to select edgels and to calculate gradient orientation-based template descriptors for edgel features.  ...  An edgel is selected within a grid block based on gradient magnitude; its position and orientation are used to determine a canonical frame where the descriptor is computed based on quantized orientation  ...  METHODOLOGY We introduce a template based on edge segments ("edge elements", or "edgels") that describes the local appearance around a collection of edgels.  ... 
doi:10.1109/ismar.2011.6162905 fatcat:uwvt4laxpjeabpzxbykh55t2bi

Edgel templates for fast planar object detection and pose estimation

Taehee Lee, Stefano Soatto
2011 2011 10th IEEE International Symposium on Mixed and Augmented Reality  
We describe a method to select edgels and to calculate gradient orientation-based template descriptors for edgel features.  ...  An edgel is selected within a grid block based on gradient magnitude; its position and orientation are used to determine a canonical frame where the descriptor is computed based on quantized orientation  ...  METHODOLOGY We introduce a template based on edge segments ("edge elements", or "edgels") that describes the local appearance around a collection of edgels.  ... 
doi:10.1109/ismar.2011.6143486 dblp:conf/ismar/LeeS11 fatcat:bjarnis6h5clroa3fkur2fqiuu

SAR target classification using sparse representations and spatial pyramids

Peter Knee, Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Andreas Spanias
2011 2011 IEEE RadarCon (RADAR)  
Results using a linear SVM for classification along with SIFT, FFT-magnitude and DCT-based local feature descriptors indicate that the use of a single element from the dictionary to describe the local  ...  These feature descriptors are generated by identifying those dictionary elements, created via -means clustering, that best approximate the local features for each sub-region.  ...  CODE GENERATION The D-dimensional local descriptors for each subregion are encoded into an M-dimensional code using one of two coding schemes.  ... 
doi:10.1109/radar.2011.5960546 fatcat:ckd7sxhzubf7hpier6veihqy6e

SUSurE: Speeded Up Surround Extrema feature detector and descriptor for realtime applications

Mosalam Ebrahimi, Walterio W. Mayol-Cuevas
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this paper we present modified detectors and descriptors based on the recently introduced CenSurE [1] , and show experimental results that aim to highlight the computational savings that can be made  ...  There has been significant research into the development of visual feature detectors and descriptors that are robust to a number of image deformations.  ...  The descriptor used in CenSurE is based on Upright SURF descriptor, and is called Modified Upright SURF (MU-SURF).  ... 
doi:10.1109/cvprw.2009.5204313 dblp:conf/cvpr/EbrahimiM09 fatcat:vqlt7towirf4lccf46lzhl63wi

SUSurE: Speeded Up Surround Extrema feature detector and descriptor for realtime applications

M. Ebrahimi, W.W. Mayol-Cuevas
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this paper we present modified detectors and descriptors based on the recently introduced CenSurE [1] , and show experimental results that aim to highlight the computational savings that can be made  ...  There has been significant research into the development of visual feature detectors and descriptors that are robust to a number of image deformations.  ...  The descriptor used in CenSurE is based on Upright SURF descriptor, and is called Modified Upright SURF (MU-SURF).  ... 
doi:10.1109/cvpr.2009.5204313 fatcat:r223synypvavbjsnmaad276qta
« Previous Showing results 1 — 15 out of 4,431 results