A Cognitive Architecture for Visual Memory Identification

2014 ◽  
Vol 6 (2) ◽  
pp. 63-77 ◽  
Author(s):  
Karina Jaime ◽  
Gustavo Torres ◽  
Félix Ramos ◽  
Gregorio Garcia-Aguilar
Keyword(s):  
Visual Memory ◽  
Brain Area ◽  
Cognitive Architecture ◽  
Memory System ◽  
Object Identification ◽  
Visual Object ◽  
Memory Encode ◽  
Short Term Visual Memory ◽  
Three Stages ◽  
Visual Object Identification

Memory is an important process of human behavior. In particular visual memory encode, store, and retrieve acquired knowledge about the environment. The visual memory system involves different kinds of processes, such as sensory input and short-term visual memory. The model presents a first approach for visual memory recognition that supports the three stages mentioned above. The model design is based on neuroscience results. The model consists of nodes. Each node represents a brain area that is involved in the visual memory system. The nodes run in a distributed system and send messages with visual memory information. This document presents only the memory system specifications that support a cognitive architecture for visual object identification. The authors validated the model with two case studies: known and unknown stimulus.

Brain Architecture for Visual Object Identification

2013 ◽  
Vol 7 (1) ◽  
pp. 75-97 ◽  
Author(s):  
Gustavo Torres ◽  
Karina Jaime ◽  
Félix Ramos
Keyword(s):  
Visual Memory ◽  
Cognitive Architecture ◽  
Internal Representation ◽  
Object Identification ◽  
Visual Object ◽  
Virtual Agents ◽  
Visual Elements ◽  
Memory Modules ◽  
Visual Object Identification ◽  
The One

Visual memory identification is a key cognitive process for intelligent virtual agents living on virtual environments. This process allows the virtual agents to develop an internal representation of the environment for the posterior production of intelligent responses. There are many architectures based on memory modules for environment visual elements identification, as if they were invariant, this way of processing a visual scene is different from the one that real humans use. This document presents the description of a visual memory identification model based on current neuroscience state of art. Furthermore; the proposed model considers memory as a system that treats information in three stages: to encode, store and retrieve acquired knowledge about the environment. On the other hand, the authors validate the implementation of their approach with two identification tasks: when the stimulus is known and when it is unknown. Actually, this work is part of a proposal for a cognitive architecture that will let the authors create virtual agents with more credible human behaviors.

Similar cortical correlates underlie visual object identification and orientation judgment

2005 ◽  
Vol 43 (14) ◽  
pp. 2101-2108 ◽  
Author(s):  
Christian F. Altmann ◽  
Wolfgang Grodd ◽  
Zoe Kourtzi ◽  
Heinrich H. Bülthoff ◽  
Hans-Otto Karnath
Keyword(s):  
Object Identification ◽  
Visual Object ◽  
Orientation Judgment ◽  
Visual Object Identification

Performance of 5-Year-Old Children on Seven Visual Perceptual Tasks in Relation to Neonatal Ultrasound Abnormalities

Perception ◽  
1997 ◽  
Vol 26 (1_suppl) ◽  
pp. 23-23
Author(s):  
E Vandenbussche ◽  
P Stiers ◽  
M Haers ◽  
B M van den Hout ◽  
L S de Vries ◽  
...  
Keyword(s):  
At Risk ◽  
Visual Acuity ◽  
White Matter ◽  
Intracranial Hemorrhage ◽  
Periventricular Leukomalacia ◽  
Birth Asphyxia ◽  
Object Identification ◽  
Visual Object ◽  
Normal Children ◽  
Visual Object Identification

We investigated whether neonatal brain damage can give rise to visual perceptual deficits, in addition to the well-documented impairments in visual acuity. To this end, forty-one children (age 5.02 to 5.89 years) were given four visual object identification tasks and three visuo-constructive tasks. These subjects were neonatal at risk owing to prematurity or birth asphyxia. From neonatal ultrasound scans, the occurrence of intracranial hemorrhage (ICH, N = 17), periventricular leukomalacia (PVL, N = 15), and/or white matter damage due to either of these conditions (WMD, N = 9) was determined for each subject. Scans were normal in fourteen of them. The number of subjects performing at or below Pc10 of same-age normal children was significantly above 10% for each task (range 27% – 49%). This was still true when mental instead of chronological age was used for comparison, as shown by the results of nine subjects for which intelligence data were available. This high incidence of impairment is not attributable to loss of visual acuity, since grating acuity was reduced in only four subjects (14 – 19 cycles deg−1). The frequency of scores < Pc10 correlated significantly with WMD in six tasks, with PVL in 4 tasks, but not with ICH. We conclude that neonatal at risk children are more likely to develop impaired visual perceptual skills, independent of mental disability and visual acuity loss. On ultrasound permanent white matter abnormalities are most strongly associated with visual perceptual deficit, whereas intracranial hemorrhage is unrelated.

scholarly journals Mobile visual object identification: from SIFT-BoF-RANSAC to Sketchprint

2015 ◽  
Author(s):  
Sviatoslav Voloshynovskiy ◽  
Maurits Diephuis ◽  
Taras Holotyak
Keyword(s):  
Object Identification ◽  
Visual Object ◽  
Visual Object Identification

scholarly journals Orientation, Rotary Motion, and Congruency Effects: Models of Visual Object Identification

2015 ◽  
Vol 15 (12) ◽  
pp. 1092
Author(s):  
James Ryland ◽  
Alice O'Toole ◽  
Richard Golden
Keyword(s):  
Object Identification ◽  
Rotary Motion ◽  
Visual Object ◽  
Visual Object Identification

scholarly journals Mechanisms of Feature Selectivity and Invariance in Primary Visual Cortex

2020 ◽  
Author(s):  
Ali Almasi ◽  
Hamish Meffin ◽  
Shaun L. Cloherty ◽  
Yan Wong ◽  
Molis Yunzab ◽  
...  
Keyword(s):  
Visual Cortex ◽  
Primary Visual Cortex ◽  
Visual Processing ◽  
Object Identification ◽  
Visual Object ◽  
Object Processing ◽  
Complex Cells ◽  
Feature Selectivity ◽  
Visual Object Identification ◽  
Neuronal Computation

AbstractVisual object identification requires both selectivity for specific visual features that are important to the object’s identity and invariance to feature manipulations. For example, a hand can be shifted in position, rotated, or contracted but still be recognised as a hand. How are the competing requirements of selectivity and invariance built into the early stages of visual processing? Typically, cells in the primary visual cortex are classified as either simple or complex. They both show selectivity for edge-orientation but complex cells develop invariance to edge position within the receptive field (spatial phase). Using a data-driven model that extracts the spatial structures and nonlinearities associated with neuronal computation, we show that the balance between selectivity and invariance in complex cells is more diverse than thought. Phase invariance is frequently partial, thus retaining sensitivity to brightness polarity, while invariance to orientation and spatial frequency are more extensive than expected. The invariance arises due to two independent factors: (1) the structure and number of filters and (2) the form of nonlinearities that act upon the filter outputs. Both vary more than previously considered, so primary visual cortex forms an elaborate set of generic feature sensitivities, providing the foundation for more sophisticated object processing.

scholarly journals Mechanisms of Feature Selectivity and Invariance in Primary Visual Cortex

2020 ◽  
Vol 30 (9) ◽  
pp. 5067-5087
Author(s):  
Ali Almasi ◽  
Hamish Meffin ◽  
Shaun L Cloherty ◽  
Yan Wong ◽  
Molis Yunzab ◽  
...  
Keyword(s):  
Visual Cortex ◽  
Primary Visual Cortex ◽  
Visual Processing ◽  
Object Identification ◽  
Visual Object ◽  
Object Processing ◽  
Complex Cells ◽  
Feature Selectivity ◽  
Visual Object Identification ◽  
Neuronal Computation

Abstract Visual object identification requires both selectivity for specific visual features that are important to the object’s identity and invariance to feature manipulations. For example, a hand can be shifted in position, rotated, or contracted but still be recognized as a hand. How are the competing requirements of selectivity and invariance built into the early stages of visual processing? Typically, cells in the primary visual cortex are classified as either simple or complex. They both show selectivity for edge-orientation but complex cells develop invariance to edge position within the receptive field (spatial phase). Using a data-driven model that extracts the spatial structures and nonlinearities associated with neuronal computation, we quantitatively describe the balance between selectivity and invariance in complex cells. Phase invariance is frequently partial, while invariance to orientation and spatial frequency are more extensive than expected. The invariance arises due to two independent factors: (1) the structure and number of filters and (2) the form of nonlinearities that act upon the filter outputs. Both vary more than previously considered, so primary visual cortex forms an elaborate set of generic feature sensitivities, providing the foundation for more sophisticated object processing.

Sign in / Sign up

Export Citation Format

Share Document