Results 21 to 30 of about 5,849,321 (239)
Ventral-stream-like shape representation : from pixel intensity values to trainable object-selective COSFIRE models [PDF]
, 2014 Keywords: hierarchical representation, object recognition, shape, ventral stream, vision and scene understanding, robotics, handwriting analysisThe remarkable abilities of the primate visual system have inspired the construction of computational models ...
Azzopardi, George, Petkov, Nicolai
core +8 more sources
The Gromov–Wasserstein Distance: A Brief Overview
Axioms, 2014 We recall the construction of the Gromov–Wasserstein distance and concentrate on quantitative aspects of the definition.
Facundo Mémoli
doaj +1 more source
Transformation invariance in hand shape recognition [PDF]
, 2006 In hand shape recognition, transformation invariance is key for successful recognition. We propose a system that is invariant to small scale, translation and shape variations.
Coogan, Thomas, Sutherland, Alistair
core +1 more source
PVRNet: Point-View Relation Neural Network for 3D Shape Recognition [PDF]
AAAI Conference on Artificial Intelligence, 2018 Three-dimensional (3D) shape recognition has drawn much research attention in the field of computer vision. The advances of deep learning encourage various deep models for 3D feature representation.
Haoxuan You +5 more
semanticscholar +1 more source
Object recognition using shape-from-shading [PDF]
, 2001 This paper investigates whether surface topography information extracted from intensity images using a recently reported shape-from-shading (SFS) algorithm can be used for the purposes of 3D object recognition.
Hancock, E R, Worthington, P L
core +2 more sources
Dynamic distance-based shape features for gait recognition [PDF]
, 2014 We propose a novel skeleton-based approach to gait recognition using our Skeleton Variance Image. The core of our approach consists of employing the screened Poisson equation to construct a family of smooth distance functions associated with a given ...
Belyaev, Alexander +2 more
core +1 more source
Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition [PDF]
Computer Vision and Pattern Recognition, 2019 Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during optimization ...
Lin Xu, Han Sun, Yuai Liu
semanticscholar +1 more source
Advanced Intelligent Systems, 2023 A generative deep learning approach for shape recognition of an arbitrary object from its acoustic scattering properties is proposed and demonstrated.
Waqas W. Ahmed +4 more
doaj +1 more source
Automatic recognition of fingerspelled words in British Sign Language [PDF]
, 2009 We investigate the problem of recognizing words from video, fingerspelled using the British Sign Language (BSL) fingerspelling alphabet. This is a challenging task since the BSL alphabet involves both hands occluding each other, and contains signs ...
Everingham, M., Liwicki, S.
core +2 more sources
Planar shape recognition by shape morphing [PDF]
Pattern Recognition, 2000 Abstract A novel method based on shape morphing is proposed for 2D shape recognition. In this framework, the shape of objects is described by using their contour. Shape recognition involves a morph between the contours of the objects being compared. The morph is quantified by using a physics-based formulation.
Rahul Singh +1 more
openaire +1 more source