Approach for Object Recognition Based on a Computational Model of Feature Binding

2010 ◽  
Vol 21 (3) ◽  
pp. 452-460
Author(s):  
Xi LIU ◽  
Zhong-Zhi SHI ◽  
Zhi-Wei SHI ◽  
Zhi-Ping SHI
Keyword(s):  
Object Recognition ◽  
Computational Model ◽  
Feature Binding

Learning to Segment Images Using Dynamic Feature Binding

1992 ◽  
Vol 4 (5) ◽  
pp. 650-665 ◽  
Author(s):  
Michael C. Mozer ◽  
Richard S. Zemel ◽  
Marlene Behrmann ◽  
Christopher K. I. Williams
Keyword(s):  
Object Recognition ◽  
Phase Locking ◽  
Signal Amplitude ◽  
Feature Binding ◽  
Dynamic Feature ◽  
Training Procedure ◽  
Segmentation Process ◽  
Visual Scenes ◽  
Computational Systems ◽  
Complex Valued

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object they belong. Current computational systems that perform this operation are based on predefined grouping heuristics. We describe a system called MAGIC that learns how to group features based on a set of presegmented examples. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of finding nonintuitive structural regularities in images. Grouping is performed by a relaxation network that attempts to dynamically bind related features. Features transmit a complex-valued signal (amplitude and phase) to one another; binding can thus be represented by phase locking related features. MAGIC's training procedure is a generalization of recurrent backpropagation to complex-valued units.

COMBINED MODEL-BASED 3D OBJECT RECOGNITION

2005 ◽  
Vol 19 (07) ◽  
pp. 839-852 ◽  
Author(s):  
SUNGHO KIM ◽  
GIJEONG JANG ◽  
WANG-HEON LEE ◽  
IN SO KWEON
Keyword(s):  
Object Recognition ◽  
Object Identification ◽  
Feature Binding ◽  
Human Vision ◽  
3D Object Recognition ◽  
Top Down ◽  
Combined Model ◽  
Bottom Up ◽  
3D Object ◽  
Model Based

This paper presents a combined model-based 3D object recognition method motivated by the robust properties of human vision. The human visual system (HVS) is very efficient and robust in identifying and grabbing objects, in part because of its properties of visual attention, contrast mechanism, feature binding, multiresolution and part-based representation. In addition, the HVS combines bottom-up and top-down information effectively using combined model representation. We propose a method for integrating these aspects under a Monte Carlo method. In this scheme, object recognition is regarded as a parameter optimization problem. The bottom-up process initializes parameters, and the top-down process optimizes them. Experimental results show that the proposed recognition model is feasible for 3D object identification and pose estimation.

A feature binding computational model for multi-class object categorization and recognition

2011 ◽  
Vol 21 (6) ◽  
pp. 1297-1305 ◽  
Author(s):  
Xishun Wang ◽  
Xi Liu ◽  
Zhongzhi Shi ◽  
Hongjian Sui
Keyword(s):  
Computational Model ◽  
Feature Binding ◽  
Object Categorization

scholarly journals Crowding and Binding: Not All Feature Dimensions Behave in the Same Way

2019 ◽  
Vol 30 (10) ◽  
pp. 1533-1546
Author(s):  
Amit Yashar ◽  
Xiuyun Wu ◽  
Jiageng Chen ◽  
Marisa Carrasco
Keyword(s):  
Computational Model ◽  
Feature Binding ◽  
Common Mechanism ◽  
Spatial Frequencies ◽  
Dual Estimation ◽  
Feature Dimension ◽  
Joint Coding

Humans often fail to identify a target because of nearby flankers. The nature and stages at which this crowding occurs are unclear, and whether crowding operates via a common mechanism across visual dimensions is unknown. Using a dual-estimation report ( N = 42), we quantitatively assessed the processing of features alone and in conjunction with another feature both within and between dimensions. Under crowding, observers misreported colors and orientations (i.e., reported a flanker value instead of the target’s value) but averaged the target’s and flankers’ spatial frequencies (SFs). Interestingly, whereas orientation and color errors were independent, orientation and SF errors were interdependent. These qualitative differences of errors across dimensions revealed a tight link between crowding and feature binding, which is contingent on the type of feature dimension. These results and a computational model suggest that crowding and misbinding are due to pooling across a joint coding of orientations and SFs but not of colors.

A computational model for feature binding

2008 ◽  
Vol 51 (5) ◽  
pp. 470-478 ◽  
Author(s):  
ZhiWei Shi ◽  
ZhongZhi Shi ◽  
Xi Liu ◽  
ZhiPing Shi
Keyword(s):  
Computational Model ◽  
Feature Binding
Sign in / Sign up

Export Citation Format

Share Document