scholarly journals Human Object Recognition Using Colour and Depth Information from an RGB-D Kinect Sensor

10.5772/55717 ◽  
2013 ◽  
Vol 10 (3) ◽  
pp. 171 ◽  
Author(s):  
Benjamin John Southwell ◽  
Gu Fang
Keyword(s):  
Object Recognition ◽  
Depth Information ◽  
Kinect Sensor ◽  
Human Object

A solution to the tag-assignment problem for neural networks

1989 ◽  
Vol 12 (3) ◽  
pp. 381-397 ◽  
Author(s):  
Gary W. Strong ◽  
Bruce A. Whitehead
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Assignment Problem ◽  
Model Object ◽  
Parallel Processes ◽  
Illusory Conjunctions ◽  
Feature Processing ◽  
Human Object ◽  
Processing Activity ◽  
Normal Perception

AbstractPurely parallel neural networks can model object recognition in brief displays – the same conditions under which illusory conjunctions (the incorrect combination of features into perceived objects in a stimulus array) have been demonstrated empirically (Treisman 1986; Treisman & Gelade 1980). Correcting errors of illusory conjunction is the “tag-assignment” problem for a purely parallel processor: the problem of assigning a spatial tag to nonspatial features, feature combinations, and objects. This problem must be solved to model human object recognition over a longer time scale. Our model simulates both the parallel processes that may underlie illusory conjunctions and the serial processes that may solve the tag-assignment problem in normal perception. One component of the model extracts pooled features and another provides attentional tags that correct illusory conjunctions. Our approach addresses two questions: (i) How can objects be identified from simultaneously attended features in a parallel, distributed representation? (ii) How can the spatial selectional requirements of such an attentional process be met by a separation of pathways for spatial and nonspatial processing? Our analysis of these questions yields a neurally plausible simulation of tag assignment based on synchronizing feature processing activity in a spatial focus of attention.

Temporal Correlations in Presentation Order during Learning Affects Human Object Recognition

Perception ◽  
1997 ◽  
Vol 26 (1_suppl) ◽  
pp. 33-33
Author(s):  
G M Wallis ◽  
H H Bülthoff
Keyword(s):  
Neural Network ◽  
Object Recognition ◽  
Recognition Performance ◽  
Presentation Order ◽  
Temporal Association ◽  
Spatial Correlations ◽  
Temporal Correlations ◽  
Human Object ◽  
Network Simulations ◽  
Recognition Learning

The view-based approach to object recognition supposes that objects are stored as a series of associated views. Although representation of these views as combinations of 2-D features allows generalisation to similar views, it remains unclear how very different views might be associated together to allow recognition from any viewpoint. One cue present in the real world other than spatial similarity, is that we usually experience different objects in temporally constrained, coherent order, and not as randomly ordered snapshots. In a series of recent neural-network simulations, Wallis and Baddeley (1997 Neural Computation9 883 – 894) describe how the association of views on the basis of temporal as well as spatial correlations is both theoretically advantageous and biologically plausible. We describe an experiment aimed at testing their hypothesis in human object-recognition learning. We investigated recognition performance of faces previously presented in sequences. These sequences consisted of five views of five different people's faces, presented in orderly sequence from left to right profile in 45° steps. According to the temporal-association hypothesis, the visual system should associate the images together and represent them as different views of the same person's face, although in truth they are images of different people's faces. In a same/different task, subjects were asked to say whether two faces seen from different viewpoints were views of the same person or not. In accordance with theory, discrimination errors increased for those faces seen earlier in the same sequence as compared with those faces which were not ( p<0.05).

Multiple Classifiers-Based Feature Fusion for RGB-D Object Recognition

2017 ◽  
Vol 31 (05) ◽  
pp. 1750014 ◽  
Author(s):  
Yan Wu ◽  
Jiqian Li ◽  
Jing Bai
Keyword(s):  
Object Recognition ◽  
Feature Fusion ◽  
Classification Performance ◽  
Depth Image ◽  
Depth Information ◽  
The Past ◽  
Depth Images ◽  
Comparable Performance ◽  
Accuracy Difference ◽  
Rgb Image

RGB-D-based object recognition has been enthusiastically investigated in the past few years. RGB and depth images provide useful and complementary information. Fusing RGB and depth features can significantly increase the accuracy of object recognition. However, previous works just simply take the depth image as the fourth channel of the RGB image and concatenate the RGB and depth features, ignoring the different power of RGB and depth information for different objects. In this paper, a new method which contains three different classifiers is proposed to fuse features extracted from RGB image and depth image for RGB-D-based object recognition. Firstly, a RGB classifier and a depth classifier are trained by cross-validation to get the accuracy difference between RGB and depth features for each object. Then a variant RGB-D classifier is trained with different initialization parameters for each class according to the accuracy difference. The variant RGB-D-classifier can result in a more robust classification performance. The proposed method is evaluated on two benchmark RGB-D datasets. Compared with previous methods, ours achieves comparable performance with the state-of-the-art method.

scholarly journals Resolving human object recognition in space and time

2014 ◽  
Vol 17 (3) ◽  
pp. 455-462 ◽  
Author(s):  
Radoslaw Martin Cichy ◽  
Dimitrios Pantazis ◽  
Aude Oliva
Keyword(s):  
Object Recognition ◽  
Space And Time ◽  
Human Object

The Role of Attention on Viewpoint-Invariant Object Recognition

Perception ◽  
1996 ◽  
Vol 25 (1_suppl) ◽  
pp. 148-148
Author(s):  
B J Stankiewicz ◽  
J E Hummel
Keyword(s):  
Object Recognition ◽  
Shape Representation ◽  
Invariant Representation ◽  
Shape Constancy ◽  
Priming Paradigm ◽  
Human Object ◽  
Invariant Object Recognition ◽  
Series Of Experiments ◽  
Invariant Representations

Researchers in the field of visual perception have dedicated a great deal of effort to understanding how humans recognise known objects from novel viewpoints (often referred to as shape constancy). This research has produced a variety of theories—some that emphasise the use of invariant representations, others that emphasise alignment processes used in conjunction with viewpoint-specific representations. Although researchers disagree on the specifics of the representations and processes used during human object recognition, most agree that achieving shape constancy is computationally expensive—that is, it requires work. If it is assumed that attention provides the necessary resources for these computations, these theories suggest that recognition with attention should be qualitatively different from recognition without attention. Specifically, recognition with attention should be more invariant with viewpoint than recognition without attention. We recently reported a series of experiments, in which we used a response-time priming paradigm in which attention and viewpoint were manipulated, that showed attention is necessary for generating a representation of shape that is invariant with left-right reflection. We are now reporting new experiments showing that shape representation activated without attention is not completely view-specific. These experiments demonstrate that the automatic shape representation is invariant with the size and location of an image in the visual field. The results are reported in the context of a recent model proposed by Hummel and Stankiewicz ( Attention and Performance16 in press), as well as in the context of other models of human object recognition that make explicit predictions about the role of attention in generating a viewpoint-invariant representation of object shape.

Invariant Features Detected with Computer Vision Allow Better Human Object Recognition in Photographs

2007 ◽  
Author(s):  
Trevor Wolff ◽  
Jeremiah D. Still ◽  
Derrick J. Parkhurst ◽  
Veronica J. Dark
Keyword(s):  
Computer Vision ◽  
Object Recognition ◽  
Invariant Features ◽  
Human Object
Sign in / Sign up

Export Citation Format

Share Document