1,461 Hits in 9.1 sec

Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgments

Brian M. Scassellati, Sophoclis Alexopoulos, Myron D. Flickner, Carlton W. Niblack, Ramesh C. Jain
1994 Storage and Retrieval for Image and Video Databases II  
In content based image retrieval, systems allow users to ask for objects similar in shape to a query object.  ...  However, there is no clear understanding of how computational shape similarity corresponds to human shape similarity.  ...  The available method for evaluating a shape matching technique is comparison against human perceptual judgments.  ... 
doi:10.1117/12.171777 dblp:conf/spieSR/ScassellatiAF94 fatcat:qnewjjjo4naqblizsxglvddrqu

Shape skeletons and shape similarity

E. Briscoe, M. Singh, J. Feldman
2010 Journal of Vision  
Shepard (1957 Shepard ( , 1987 was first to recognize the importance of similarity in human judgments with his proposal of a universal law of perceptual generalization, which explained human similarity  ...  To this end, computational models of vision are created to mechanize human visual and cognitive capabilities, and as a result, models of 2D shape are of critical value.  ... 
doi:10.1167/8.6.718 fatcat:o4shcn7vhbeqnhcgif4ol3ijcm

Structure-oriented contour representation and matching for engineering shapes

Suyu Hou, Karthik Ramani
2008 Computer-Aided Design  
They are also compared with the existing methods.  ...  This paper presents a strategy of an integrated shape matching for contours of engineering drawings inspired by the divide and conquer paradigm.  ...  Acknowledgements This material is partly based upon work supported by the National Science Foundation under Grant IIS No. 0535156.  ... 
doi:10.1016/j.cad.2007.08.007 fatcat:ru5hs45m6zhydbqb5qi3qxjyjy

Visceral Signals Shape Brain Dynamics and Cognition

Damiano Azzalini, Ignacio Rebollo, Catherine Tallon-Baudry
2019 Trends in Cognitive Sciences  
This active field of research offers a unique opportunity to draw new theories blurring the border between cognition, emotion, and consciousness, as well as between mind and body.  ...  These ongoing ascending signals actively shape brain dynamics at rest, complementing canonical resting-state networks (RSNs).  ...  In contrast, consider the kind of learning that allows a human being to recognize an image with high accuracy that was previously only seen once as part of a sequence of 10'000 images, each shown once  ... 
doi:10.1016/j.tics.2019.03.007 pmid:31047813 fatcat:srlek2k63nagnmstxtvzwi6nmu

A histogram-based approach for object-based query-by-shape-and-color in image and video databases

Ediz Şaykol, Uğur Güdükbay, Özgür Ulusoy
2005 Image and Vision Computing  
Considering the fact that querying by low-level object features is essential in image and video data, an efficient approach for querying and retrieval by shape and color is proposed.  ...  The objects can be extracted from images or video frames. The proposed histogram-based approach is used as a component in the query-by-feature subsystem of a video database management system.  ...  Acknowledgements This work was supported by Scientific and Technical Research Council of Turkey (TÜ BİTAK) under the grant  ... 
doi:10.1016/j.imavis.2005.07.015 fatcat:rgwp6fncnras3cu7g2nqpua2ku

Semi-Supervised Co-Analysis of 3D Shape Styles from Projected Lines

Fenggen Yu, Yan Zhang*, Kai Xu, Ali Mahdavi-Amiri, Hao Zhang
2018 ACM Transactions on Graphics  
We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines, achieving style patch localization with only weak supervision.  ...  Given a collection of 3D shapes spanning multiple object categories and styles, we perform style co-analysis over projected feature lines of each 3D shape and then backproject the learned style features  ...  This work was supported in part by NSFC (61572507, 61532003, 61622212) for Kai Xu, NSERC (611370) and a gift grant from Adobe Research for Hao Zhang, and NSERC PDF for Ali Mahdavi-Amiri.  ... 
doi:10.1145/3182158 fatcat:gopfmqhstzairau3reccsm7qze

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style [article]

Chaitanya Patel, Zhouyingcheng Liao, Gerard Pons-Moll
2020 arXiv   pre-print
The weights of the mixture are computed with a narrow bandwidth kernel to guarantee that only predictions with similar high-frequency patterns are combined.  ...  The style variation is obtained by computing, in a canonical pose, a subspace of deformation, which satisfies physical constraints such as inter-penetration, and draping on the body.  ...  This work is partly funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) -409792180 (Emmy Noether Programme, project: Real Virtual Humans) and Google Faculty Research Award.  ... 
arXiv:2003.04583v2 fatcat:fyis7zmzhzdfff2qfiyr3gp4xq

Softness and weight from shape: Material properties inferred from local shape features

Filipp Schmidt, Roland W. Fleming, Matteo Valsecchi
2020 Journal of Vision  
For this, we created a large number of novel stimuli with varying surface shape features.  ...  Here, we set out to test the role of such shape features on judgments of material properties softness and weight.  ...  and local shape features on material property judgments for real-world images of different textiles.  ... 
doi:10.1167/jov.20.6.2 pmid:32492099 pmcid:PMC7416911 fatcat:quqknhwzbnao3jhv34qsrnxhfi

On the Perceptual Organization of Image Databases Using Cognitive Discriminative Biplots

Christos Theoharatos, Nikolaos A. Laskaris, George Economou, Spiros Fotopoulos
2006 EURASIP Journal on Advances in Signal Processing  
A human-centered approach to image database organization is presented in this study.  ...  The management of a generic image database is pursued using a standard psychophysical experimental procedure followed by a well-suited data analysis methodology that is based on simple geometrical concepts  ...  This work was financed by the European Social Fund (ESF), Operational Program for Educational and Vocational Training II (EPEAEK II), and particularly the Program "New Graduate Programs of University of  ... 
doi:10.1155/2007/68165 fatcat:dsd4xu2yf5aoni67iu5piyokmm

Perceptual image similarity experiments

Bernice E. Rogowitz, Thomas Frese, John R. Smith, Charles A. Bouman, Edward B. Kalin, Bernice E. Rogowitz, Thrasyvoulos N. Pappas
1998 Human Vision and Electronic Imaging III  
This paper also describes and validates a new technique for collecting similarity judgments which can provide meaningful results with a factor of four fewer judgments, as compared with the paired comparisons  ...  We then used the two perceptual and the two algorithmic methods to measure the similarity of each image to every other image in the data set, producing four similarity matrices.  ...  Often, these features are thought to contribute to human judgments of image similarity (e.g. color, texture, and shape), but with few exceptions, 7,6 the characteristics of human similarity perception  ... 
doi:10.1117/12.320148 dblp:conf/hvei/RogowitzFSBK98 fatcat:bqq2rupfbfbr3lfafwrcgvkfy4

Visual interference can help and hinder memory: Measuring memory fidelity using a novel circular shape space: Supplemental Material [article]

Aedan Y. Li, Jackson Liang, Andy C. H. Lee, Morgan D. Barense
2019 bioRxiv   pre-print
on a 2D circle.  ...  In a first experiment, we created the Validated Circular Shape Space (VCS space), the first perceptually uniform 'Shape Wheel' whereby subjective similarity was empirically quantified by angular distance  ...  AYL is supported by a NSERC grant. This work is supported by a Scholar Award  ... 
doi:10.1101/535922 fatcat:qrnqixapgbcgfeuwztvloss2li

Transfer of View-manifold Learning to Similarity Perception of Novel Objects [article]

Xingyu Lin, Hao Wang, Zhihao Li, Yimeng Zhang, Alan Yuille, Tai Sing Lee
2017 arXiv   pre-print
We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object  ...  Interestingly, the resulting transformation of feature representation in the deep networks is found to significantly better match human perceptual similarity judgment than AlexNet, suggesting that object  ...  In this paper, we explored computational models for understanding the neural basis of human perceptual similarity judgment.  ... 
arXiv:1704.00033v1 fatcat:km5kdd34lvhqtfsvxt4pceg2xy

Exploring the veridicality of shape-from-shading for real 3D objects

Jenny Bartov, Martin Giesel, Qasim Zaidi
2015 Journal of Vision  
to retrieve the object's proper shape?  ...  As our experiment shows: unlike algorithms, humans are not rigid in their interpretations -each observer does not perform the same perceptual computation when confronted with the same stimulus.  ... 
doi:10.1167/15.12.964 fatcat:767fizqssvdftdcflqxcfx7ozy

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style

Chaitanya Patel, Zhouyingcheng Liao, Gerard Pons-Moll
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1: We present TailorNet, a model to estimate the clothing deformations with fine details from input body shape, body pose and garment style.  ...  From the left: the first two avatars show two different styles on the same shape, the following two show the same two styles on another shape, and the last two avatars illustrate that our method works  ...  This work is partly funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) -409792180 (Emmy Noether Programme, project: Real Virtual Humans) and Google Faculty Research Award.  ... 
doi:10.1109/cvpr42600.2020.00739 dblp:conf/cvpr/PatelLP20 fatcat:tafhrzep75hhddxu7wv4vjpf7a

An Evolutionary Perspective on the Design of Neuromorphic Shape Filters

Ernest Greene
2020 IEEE Access  
The present article provides a brief overview of retinal and cortical mechanisms for registering shape information, with the hope that it might contribute to the design of shape-encoding circuits that  ...  Most of that work has been inspired by theories advanced by neuroscientists and behaviorists for how cortical systems store stimulus information.  ...  This method for identifying 2D shapes first creates a 1D summary histogram of each shape to be evaluated. A.  ... 
doi:10.1109/access.2020.3004412 fatcat:xxvuszbsgffqlm2dkbc56cbgwm
« Previous Showing results 1 — 15 out of 1,461 results