scholarly journals Developing a Modified HMAX Model Based on Combined with the Visual Featured Model

2017 ◽  
Vol 7 (3) ◽  
pp. 773
Author(s):  
Yaghoub Pourasad
Keyword(s):  
Visual Cortex ◽  
Object Recognition ◽  
Visual System ◽  
Human Visual System ◽  
Hierarchical Models ◽  
Recognition Rate ◽  
Basic Operation ◽  
High Complexity ◽  
Proposed Model ◽  
Computational Speed

<p>Identify objects based on modeling the human visual system, as an effective method in intelligent identification, has attracted the attention of many researchers. Although the machines have high computational speed but are very weak as compared to humans in terms of diagnosis. Experience has shown that in many areas of image processing, algorithms that have biological backing had more simplicity and better performance. The human visual system, first select the main parts of the image which is provided by the visual featured model, then pays to object recognition which is a hierarchical operations according to this, HMAX model is also provided. HMAX object recognition model from the group of hierarchical models without feedback that its structure and parameters selected based on biological characteristics of the visual cortex. This model is a hierarchical model neural network with four layers, is composed of alternating layers that are simple and complex. Due to the high complexity of the human visual system is virtually impossible to replicate it. For each of the above, separate models have been proposed but in the human visual system, this operation is performed seamlessly, thus, by combining the principles of these models is expected to be closer to the human visual system and obtain a higher recognition rate. In this paper, we introduce an architecture to classify images based on a combination of previous work is based on the basic operation of the visual cortex. According to the results presented, the proposed model compared with the main HMAX model has a much higher recognition rate. Simulations was performed on the database of Caltech101.</p>

scholarly journals Blindsight and Unconscious Vision: What They Teach Us about the Human Visual System

2016 ◽  
Vol 23 (5) ◽  
pp. 529-541 ◽  
Author(s):  
Sara Ajina ◽  
Holly Bridge
Keyword(s):  
Visual Cortex ◽  
Visual System ◽  
Primary Visual Cortex ◽  
Neural Activity ◽  
Human Visual System ◽  
Visual Information ◽  
Visual Loss ◽  
Physiological Conditions ◽  
The World ◽  
The Brain

Damage to the primary visual cortex removes the major input from the eyes to the brain, causing significant visual loss as patients are unable to perceive the side of the world contralateral to the damage. Some patients, however, retain the ability to detect visual information within this blind region; this is known as blindsight. By studying the visual pathways that underlie this residual vision in patients, we can uncover additional aspects of the human visual system that likely contribute to normal visual function but cannot be revealed under physiological conditions. In this review, we discuss the residual abilities and neural activity that have been described in blindsight and the implications of these findings for understanding the intact system.

scholarly journals The human visual system preserves the hierarchy of 2-dimensional pattern regularity

2021 ◽  
Author(s):  
Peter J. Kohler ◽  
Alasdair D. F. Clarke
Keyword(s):  
Visual Cortex ◽  
Visual System ◽  
Human Visual System ◽  
Posterior Probability ◽  
Brain Activity ◽  
Large Body ◽  
Natural Scenes ◽  
Brain Response ◽  
Lower Amplitude ◽  
Wallpaper Groups

AbstractSymmetries are present at many scales in images of natural scenes. A large body of literature has demonstrated contributions of symmetry to numerous domains of visual perception. The four fundamental symmetries, reflection, rotation, translation and glide reflection, can be combined in exactly 17 distinct ways. These wallpaper groups represent the complete set of symmetries in 2D images and have recently found use in the vision science community as an ideal stimulus set for studying the perception of symmetries in textures. The goal of the current study is to provide a more comprehensive description of responses to symmetry in the human visual system, by collecting both brain imaging (Steady-State Visual Evoked Potentials measured using high-density EEG) and behavioral (symmetry detection thresholds) data using the entire set of wallpaper groups. This allows us to probe the hierarchy of complexity among wallpaper groups, in which simpler groups are subgroups of more complex ones. We find that this hierarchy is preserved almost perfectly in both behavior and brain activity: A multi-level Bayesian GLM indicates that for most of the 63 subgroup relationships, subgroups produce lower amplitude responses in visual cortex (posterior probability: > 0.95 for 56 of 63) and require longer presentation durations to be reliably detected (posterior probability: > 0.95 for 49 of 63). This systematic pattern is seen only in visual cortex and only in components of the brain response known to be symmetric-specific. Our results show that representations of symmetries in the human brain are precise and rich in detail, and that this precision is reflected in behavior. These findings expand our understanding of symmetry perception, and open up new avenues for research on how fine-grained representations of regular textures contribute to natural vision.

scholarly journals Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems

Algorithms ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 167 ◽  
Author(s):  
Dan Malowany ◽  
Hugo Guterman
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Object Recognition ◽  
Visual System ◽  
Human Visual System ◽  
State Of The Art ◽  
Top Down ◽  
Feed Forward ◽  
Recognition Process ◽  
The World

Computer vision is currently one of the most exciting and rapidly evolving fields of science, which affects numerous industries. Research and development breakthroughs, mainly in the field of convolutional neural networks (CNNs), opened the way to unprecedented sensitivity and precision in object detection and recognition tasks. Nevertheless, the findings in recent years on the sensitivity of neural networks to additive noise, light conditions, and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the autonomous robotic industry. In an attempt to bring computer vision algorithms closer to the capabilities of a human operator, the mechanisms of the human visual system was analyzed in this work. Recent studies show that the mechanisms behind the recognition process in the human brain include continuous generation of predictions based on prior knowledge of the world. These predictions enable rapid generation of contextual hypotheses that bias the outcome of the recognition process. This mechanism is especially advantageous in situations of uncertainty, when visual input is ambiguous. In addition, the human visual system continuously updates its knowledge about the world based on the gaps between its prediction and the visual feedback. CNNs are feed forward in nature and lack such top-down contextual attenuation mechanisms. As a result, although they process massive amounts of visual information during their operation, the information is not transformed into knowledge that can be used to generate contextual predictions and improve their performance. In this work, an architecture was designed that aims to integrate the concepts behind the top-down prediction and learning processes of the human visual system with the state-of-the-art bottom-up object recognition models, e.g., deep CNNs. The work focuses on two mechanisms of the human visual system: anticipation-driven perception and reinforcement-driven learning. Imitating these top-down mechanisms, together with the state-of-the-art bottom-up feed-forward algorithms, resulted in an accurate, robust, and continuously improving target recognition model.

scholarly journals Object Recognition Inspiring HVS

2018 ◽  
Vol 12 (2) ◽  
pp. 783
Author(s):  
Mohammadesmaeil Akbarpour ◽  
Nasser Mehrshad ◽  
Seyyed-Mohammad Razavi
Keyword(s):  
Object Recognition ◽  
Visual System ◽  
Computational Modeling ◽  
Hierarchical Model ◽  
Human Visual System ◽  
Visual Pathway ◽  
Natural Images ◽  
Significant Performance

<p><span>Human recognize objects in complex natural images very fast within a fraction of a second. Many computational object recognition models inspired from this powerful ability of human. The Human Visual System (HVS) recognizes object in several processing layers which we know them as hierarchically model. Due to amazing complexity of HVS and the connections in visual pathway, computational modeling of HVS directly from its physiology is not possible. So it considered as a some blocks and each block modeled separately. One models inspiring of HVS is HMAX which its main problem is selecting patches in random way. As HMAX is a hierarchical model, HMAX can enhanced with enhancing each layer separately. In this paper instead of random patch extraction, Desirable Patches for HMAX (DPHMAX) will extracted.  HVS for extracting patch first selected patches with more information. For simulating this block patches with more variance will be selected. Then HVS will chose patches with more similarity in a class. For simulating this block one algorithm is used. For evaluating proposed method, Caltech 5 and Caltech101 datasets are used. Results show that the proposed method (DPMAX) provides a significant performance over HMAX and other models with the same framework.</span></p>

Parts of visual shape as primitives for categorization

1998 ◽  
Vol 21 (1) ◽  
pp. 36-37 ◽  
Author(s):  
Manish Singh ◽  
Barbara Landau
Keyword(s):  
Object Recognition ◽  
Visual System ◽  
Recent Work ◽  
Human Visual System ◽  
Human Vision ◽  
Visual Shape

Converging psychophysical evidence suggests that the human visual system parses shapes into component parts for the purposes of object recognition. We examine the Schyns et al. claim of “creation” of features in light of recent work on part-based representations of visual shape, particularly the perceptual rules that human vision uses to parse shapes.

Spatiotemporal Isosensitivity Fields in the Human Visual System

Perception ◽  
1986 ◽  
Vol 15 (4) ◽  
pp. 467-472 ◽  
Author(s):  
Bill Jenkins
Keyword(s):  
Visual Cortex ◽  
Visual System ◽  
Human Visual System ◽  
Spatial Domain ◽  
Area 17 ◽  
Dynamic Textures ◽  
Neural Basis ◽  
Global Pattern

The human visual system is capable of detecting correlations, manifested perceptually as global pattern, in mathematically constrained dynamic textures. This ability has given rise to speculation that correlative mechanisms in the human visual system exist and that they have a neural basis similar to the orientationally selective structures discovered in area 17 of the mammalian visual cortex. The limits to the detection of correlation were mapped, spatially and temporally, by means of a psychophysical technique. Evidence is presented that, at least in the spatial domain, the correlation mechanism may be served by a population of such neural units.

scholarly journals ‘Proto-rivalry’: how the binocular brain identifies gloss

2016 ◽  
Vol 283 (1830) ◽  
pp. 20160383 ◽  
Author(s):  
Alexander A. Muryy ◽  
Roland W. Fleming ◽  
Andrew E. Welchman
Keyword(s):  
Visual Cortex ◽  
Machine Vision ◽  
Visual System ◽  
Human Visual System ◽  
Binocular Fusion ◽  
Low Level ◽  
Material Appearance

Visually identifying glossy surfaces can be crucial for survival (e.g. ice patches on a road), yet estimating gloss is computationally challenging for both human and machine vision. Here, we demonstrate that human gloss perception exploits some surprisingly simple binocular fusion signals, which are likely available early in the visual cortex. In particular, we show that the unusual disparity gradients and vertical offsets produced by reflections create distinctive ‘proto-rivalrous’ (barely fusible) image regions that are a critical indicator of gloss. We find that manipulating the gradients and vertical components of binocular disparities yields predictable changes in material appearance. Removing or occluding proto-rivalrous signals makes surfaces look matte, while artificially adding such signals to images makes them appear glossy. This suggests that the human visual system has internalized the idiosyncratic binocular fusion characteristics of glossy surfaces, providing a straightforward means of estimating surface attributes using low-level image signals.

Sign in / Sign up

Export Citation Format

Share Document