Filters








2,229 Hits in 4.1 sec

GOLD: Gaussians of Local Descriptors for image representation

Giuseppe Serra, Costantino Grana, Marco Manfredi, Rita Cucchiara
2015 Computer Vision and Image Understanding  
The resulting representation, a Gaussian of local descriptors (GOLD), allows to use the dot product to closely approximate a distance between distributions without the need for expensive kernel computations  ...  We describe an image by an improved spatial pyramid, which avoids boundary effects with soft assignment: local descriptors contribute to neighboring Gaussians, forming a weighted spatial pyramid of GOLD  ...  We name our method Gaussian of Local Descriptors (GOLD) and demonstrate its effectiveness for automatic image annotation and object recognition.  ... 
doi:10.1016/j.cviu.2015.01.005 fatcat:vcgrwrh74fehhjb4rfyk2bt5ku

Orientation Adaptive Minimal Learning Machine: Application to Thiolate-Protected Gold Nanoclusters and Gold-Thiolate Rings [article]

Antti Pihlajamäki, Sami Malola, Tommi Kärkkäinen, Hannu Häkkinen
2022 arXiv   pre-print
The results demonstrate that the method is well-suited for the structural optimizations of the gold-thiolate systems, where the atomic bonding has a covalent nature in the ligand shell and at the metal-ligand  ...  The method relies only on local structural information without energy evaluations.  ...  Nieminen for numerous discussions on ML methods. J. Hämäläinen provided the basis for EMLM and RS-maximin codes. V. ASSOCIATED CONTENT A. Supplemental Material  ... 
arXiv:2203.09788v1 fatcat:md6gkm2wmngq5o2lylm3gjn2ky

Digitization and image-based structure-properties relationship evaluation of a porous gold micro-electrode

A. Baux, G. Couégnat, G.L. Vignoles, D. Lasseux, A. Kuhn, C. Carucci, N. Mano, T.D. Le
2020 Materials & design  
Then, a determination of the geometrical characteristics has been achieved through image analysis.  ...  The consequence of such defects on transport are studied through image-based simulations of mass diffusion in the actual porous medium and in similar ideal media.  ...  Then, a limited number of descriptors are selected (related to the local value of gray level and its derivatives, i.e. gradient, Laplacian, Hessian) and are convoluted with Gaussian filters of increasing  ... 
doi:10.1016/j.matdes.2020.108812 fatcat:pdvwvplowvg3zlprfcby2lpnwm

Probing enzyme-nanoparticle interactions using combinatorial gold nanoparticle libraries

Yanyan Liu, David A. Winkler, V. Chandana Epa, Bin Zhang, Bing Yan
2014 Nano Reseach  
The interaction of nanoparticles with proteins is extremely complex, important for understanding the biological properties of nanomaterials, but is very poorly understood.  ...  We employed a combinatorial library of surface modified gold nanoparticles to interrogate the relationships between the nanoparticle surface chemistry and the specific and nonspecific binding to a common  ...  Electronic Supplementary Material: Supplementary material describing synthesis of ligands, zeta potentials for the f-GNP library members, and a description of the initial poolof molecular descriptors is  ... 
doi:10.1007/s12274-014-0618-5 fatcat:qj2lmul3tbb2hidskzxbawud3a

Self-Assembled Monolayer of Monomercaptoundecahydro-closo-dodecaborate on a Polycrystalline Gold Surface

Martha L. Jiménez-González, Juan Pablo F. Rebolledo-Chávez, Marisela Cruz-Ramírez, René Antaño, Angel Mendoza, Narayan S. Hosmane, Lena Ruiz-Azuara, José Luis Hernández-López, Luis Ortiz-Frade
2022 Molecules  
From SPR experiments, the adsorption kinetics of [B12H11SH]2− were studied. The data fit for a Langmuir kinetic equation, typical for the formation of a monolayer.  ...  and the gold surface.  ...  Edith Fernández Sánchez for technical support. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/molecules27082496 pmid:35458692 pmcid:PMC9026543 fatcat:qhswarz2tzhbxmnbqilvfydhoy

Hierarchical Gaussian Descriptor for Person Re-identification

Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, Yoichi Sato
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we present a novel descriptor based on a hierarchical distribution of pixel features. A hierarchical covariance descriptor has been successfully applied for image classification.  ...  More specifically, we model the region as a set of multiple Gaussian distributions in which each Gaussian represents the appearance of a local patch.  ...  Making use of mean information to enhance the covariance descriptor is motivated by several works, such as Shape of Gaussians [10] , Global Gaussian [30] and Gaussians of Local Descriptors (GOLD) [  ... 
doi:10.1109/cvpr.2016.152 dblp:conf/cvpr/MatsukawaOSS16 fatcat:2nulrhifmvgijkioae2hc5ka54

Neonatal Pain Detection in Videos Using the iCOPEvid Dataset and an Ensemble of Descriptors Extracted from Gaussian of Local Descriptors

Sheryl Brahnam, Loris Nanni, Shannon McMurtrey, Alessandra Lumini, Rick Brattin, Melinda Slack, Tonya Barrier
2019 Applied Computing and Informatics  
An ensemble of twelve global and local descriptors with a Bag-of-Features approach is utilized to improve the performance of some new descriptors based on Gaussian of Local Descriptors (GOLD).  ...  The goals of this work are twofold: 1) to develop a new video dataset for automatic neonatal pain detection called iCOPEvid (infant Classification Of Pain Expressions videos), and 2) to present a classification  ...  We also gratefully acknowledge the support of NVIDIA Corporation with their donation of the Titan Xp GPU used in this research.  ... 
doi:10.1016/j.aci.2019.05.003 fatcat:kmnikfajhbagzahkzerkoyeg4a

Towards effective codebookless model for image classification

Qilong Wang, Peihua Li, Lei Zhang, Wangmeng Zuo
2016 Pattern Recognition  
In this paper, we present an effective CLM that represents an image with a single Gaussian for classification.  ...  The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade.  ...  Acknowledgements The work was supported by the National Natural Science Foundation of China (61471082, 61271093) and the Hong Kong RGC General Research Fund Grant (PolyU 5313/13E).  ... 
doi:10.1016/j.patcog.2016.03.004 fatcat:mx4qfz2twrcvzfdjoti3t25cuq

Hierarchical Gaussian Descriptors with Application to Person Re-Identification [article]

Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, Yoichi Sato
2017 arXiv   pre-print
More specifically, the region is modeled as a set of multiple Gaussian distributions in which each Gaussian represents the appearance of a local patch.  ...  To solve this problem, we describe a local region in an image via hierarchical Gaussian distribution in which both means and covariances are included in their parameters.  ...  CONCLUSIONS We have proposed novel hierarchical meta-descriptors for person re-id. The proposed descriptors model both the mean and covari- 4 .  ... 
arXiv:1706.04318v1 fatcat:47uokyyluzc6vlly2cyyhm2uau

Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor

Jian Chen, Jie Tian
2009 Progress in Natural Science: Materials International  
The proposed technique automatically generates a lot of highly distinctive symmetric-SIFT descriptors for two images, and the registration is performed by matching the corresponding descriptors over two  ...  However, global optimization techniques are too time-consuming, and local optimization techniques frequently fail to search the global transformation space because of the large initial misalignment of  ...  For a given image I(x, y), its scale-space representation is a family of derived signals L(x, y; r) defined by the convolution of I(x,y) with the Gaussian kernel Lðx; y; rÞ ¼ Gðx; y; rÞ Ã Iðx; yÞ and the  ... 
doi:10.1016/j.pnsc.2008.06.029 fatcat:y45y4gvlwzckdg2yjiavfy5muu

Ensemble of texture descriptors and classifiers for face recognition

Alessandra Lumini, Loris Nanni, Sheryl Brahnam
2017 Applied Computing and Informatics  
Ensemble of texture descriptors and classifiers for face recognition." Applied Computing and Informatics 13, no. 1 (2017): 79-91.  ...  Abstract Presented in this paper is a novel system for face recognition that works well in the wild and that is based on ensembles of descriptors that utilize different preprocessing techniques.  ...  Gaussian of Local Descriptors (GOLDs) GOLD [40] is a recent improvement of the well-known Bag of Word (BoW) approach [45] for extracting features from an image.  ... 
doi:10.1016/j.aci.2016.04.001 fatcat:37dupsgymbdphmjhajznccrg6i

On Factors Defining the Mechanical Behavior of Nanoporous Gold

Birthe Zandersons, Lukas Lührs, Yong Li, Jörg Weissmüller
2021 Acta Materialia  
Nanoporous gold (NPG) made by dealloying takes the form of a network of nanoscale struts or "ligaments".  ...  We confirm two recent suggestions, namely i) a modified Roberts-Garboczi-type scaling law for Young's modulus versus ϕ of the material in its as-prepared state and ii) the relevance of an apparent "load-bearing  ...  The significance of those microstructural descriptors for the mechanical behavior of the random network of NPG remains to be examined in detail.  ... 
doi:10.1016/j.actamat.2021.116979 fatcat:72qrzlmfyja5pelbjarhzq2pfm

Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context

Corina Iovan, David Picard, Nicolas Thome, Matthieu Cord
2012 2012 11th International Conference on Machine Learning and Applications  
This paper addresses the challenging problem of scene classification in street-view georeferenced images of urban environments.  ...  More precisely, the goal of this task is semantic image classification, consisting in predicting in a given image, the presence or absence of a pre-defined class (e.g. shops, vegetation, etc.).  ...  Further research of this study and theoretical understanding is an interesting direction which needs to be undertaken.  ... 
doi:10.1109/icmla.2012.171 dblp:conf/icmla/IovanPTC12 fatcat:akvs6vouqfa5fpzx3ttcs7fcn4

Learning discriminative local features from image-level labelled data for colonoscopy image classification

Siyamalan Manivannan, Emanuele Trucco
2015 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)  
Unlike existing feature learning approaches which assume that a set of additional data in the form of matching/non-matching pairs of local patches are given for learning the features, our approach only  ...  In this paper we propose a novel weakly-supervised feature learning approach, learning discriminative local features from image-level labelled data for image classification.  ...  Adrian Hood for annotations, and Dr. Ruixuan Wang for useful discussions.  ... 
doi:10.1109/isbi.2015.7163901 dblp:conf/isbi/ManivannanT15 fatcat:2ay42on2gbebbh2mnfj77p5yli

A Feature-Based Approach to Big Data Analysis of Medical Images [chapter]

Matthew Toews, Christian Wachinger, Raul San Jose Estepar, William M. Wells
2015 Lecture Notes in Computer Science  
This paper proposes an inference method well-suited to large sets of medical images.  ...  Stateof-the-art performance is achieved in predicting chronic pulmonary obstructive disorder (COPD) severity across the 5-category GOLD clinical rating, with an accuracy of 89% if both exact and one-off  ...  A variety of local feature detectors exist, we adopt a 3D generalization of the SIFT algorithm [8] , where the location and scale of distinctive image patches are detected as extrema of a difference-of-Gaussian  ... 
doi:10.1007/978-3-319-19992-4_26 fatcat:vgoan4s2ubg2njnapeqodplvde
« Previous Showing results 1 — 15 out of 2,229 results