Perception

2018 ◽  
Author(s):  
Joel Z. Leibo ◽  
Tomaso Poggio
Keyword(s):  
Computational Neuroscience ◽  
Feature Detection ◽  
Pedestrian Detection ◽  
Detection Systems ◽  
Catching Up ◽  
Feature Detectors ◽  
Recognition Systems ◽  
Engineered Systems ◽  
Perceptual Systems ◽  
The Brain

This chapter provides an overview of biological perceptual systems and their underlying computational principles focusing on the sensory sheets of the retina and cochlea and exploring how complex feature detection emerges by combining simple feature detectors in a hierarchical fashion. We also explore how the microcircuits of the neocortex implement such schemes pointing out similarities to progress in the field of machine vision driven deep learning algorithms. We see signs that engineered systems are catching up with the brain. For example, vision-based pedestrian detection systems are now accurate enough to be installed as safety devices in (for now) human-driven vehicles and the speech recognition systems embedded in smartphones have become increasingly impressive. While not being entirely biologically based, we note that computational neuroscience, as described in this chapter, makes up a considerable portion of such systems’ intellectual pedigree.

Far Infrared Imaging Sensor for Mass Production of Night Vision and Pedestrian Detection Systems

2012 ◽  
pp. 301-312 ◽  
Author(s):  
Emmanuel Bercier ◽  
Patrick Robert ◽  
David Pochic ◽  
Jean-Luc Tissot ◽  
Agnes Arnaud ◽  
...  
Keyword(s):  
Mass Production ◽  
Infrared Imaging ◽  
Pedestrian Detection ◽  
Far Infrared ◽  
Night Vision ◽  
Detection Systems ◽  
Imaging Sensor

Explaining feature detection Mechanisms: A Survey

2021 ◽  
pp. 51-64
Author(s):  
Ahmed A. Elngar ◽  
◽  
◽  
◽  
◽  
...  
Keyword(s):  
Feature Detection ◽  
Feature Matching ◽  
Image Features ◽  
Mathematical Concepts ◽  
Detection Algorithms ◽  
Feature Detectors ◽  
Essential Components ◽  
Basic Notation ◽  
Computer Vision Applications ◽  
Detection Mechanisms

Feature detection, description and matching are essential components of various computer vision applications; thus, they have received a considerable attention in the last decades. Several feature detectors and descriptors have been proposed in the literature with a variety of definitions for what kind of points in an image is potentially interesting (i.e., a distinctive attribute). This chapter introduces basic notation and mathematical concepts for detecting and describing image features. Then, it discusses properties of perfect features and gives an overview of various existing detection and description methods. Furthermore, it explains some approaches to feature matching. Finally, the chapter discusses the most used techniques for performance evaluation of detection algorithms.

Burster Reconstruction Considering Unmeasurable Variables in the Epileptor Model

2021 ◽  
pp. 1-46
Author(s):  
João Angelo Ferres Brogin ◽  
Jean Faber ◽  
Douglas Domingues Bueno
Keyword(s):  
Computational Neuroscience ◽  
Dynamic Models ◽  
Epileptiform Activity ◽  
Convergence Speed ◽  
Brain Disorders ◽  
Feedback Controllers ◽  
Control Techniques ◽  
The Brain ◽  
Significant Effort ◽  
Theoretical Standpoint

Abstract Epilepsy is one of the most common brain disorders worldwide, affecting millions of people every year. Although significant effort has been put into better understanding it and mitigating its effects, the conventional treatments are not fully effective. Advances in computational neuroscience, using mathematical dynamic models that represent brain activities at different scales, have enabled addressing epilepsy from a more theoretical standpoint. In particular, the recently proposed Epileptor model stands out among these models, because it represents well the main features of seizures, and the results from its simulations have been consistent with experimental observations. In addition, there has been an increasing interest in designing control techniques for Epileptor that might lead to possible realistic feedback controllers in the future. However, such approaches rely on knowing all of the states of the model, which is not the case in practice. The work explored in this letter aims to develop a state observer to estimate Epileptor's unmeasurable variables, as well as reconstruct the respective so-called bursters. Furthermore, an alternative modeling is presented for enhancing the convergence speed of an observer. The results show that the proposed approach is efficient under two main conditions: when the brain is undergoing a seizure and when a transition from the healthy to the epileptiform activity occurs.

scholarly journals Is coding a relevant metaphor for the brain?

2018 ◽  
Vol 42 ◽  
Author(s):  
Romain Brette
Keyword(s):  
Brain Function ◽  
Neural Coding ◽  
Causal Structure ◽  
Linear Chain ◽  
Neural Codes ◽  
Experimental Parameters ◽  
Representational Power ◽  
Causal Structures ◽  
Perceptual Systems ◽  
The Brain

Abstract “Neural coding” is a popular metaphor in neuroscience, where objective properties of the world are communicated to the brain in the form of spikes. Here I argue that this metaphor is often inappropriate and misleading. First, when neurons are said to encode experimental parameters, the neural code depends on experimental details that are not carried by the coding variable (e.g., the spike count). Thus, the representational power of neural codes is much more limited than generally implied. Second, neural codes carry information only by reference to things with known meaning. In contrast, perceptual systems must build information from relations between sensory signals and actions, forming an internal model. Neural codes are inadequate for this purpose because they are unstructured and therefore unable to represent relations. Third, coding variables are observables tied to the temporality of experiments, whereas spikes are timed actions that mediate coupling in a distributed dynamical system. The coding metaphor tries to fit the dynamic, circular, and distributed causal structure of the brain into a linear chain of transformations between observables, but the two causal structures are incongruent. I conclude that the neural coding metaphor cannot provide a valid basis for theories of brain function, because it is incompatible with both the causal structure of the brain and the representational requirements of cognition.

scholarly journals Re-membering the body: applications of computational neuroscience to the top-down control of regeneration of limbs and other complex organs

2015 ◽  
Vol 7 (12) ◽  
pp. 1487-1517 ◽  
Author(s):  
G. Pezzulo ◽  
M. Levin
Keyword(s):  
Information Processing ◽  
Pattern Formation ◽  
Computational Neuroscience ◽  
Memory System ◽  
The Body ◽  
Signaling Networks ◽  
Control Mechanisms ◽  
Top Down ◽  
The Brain

How do regenerating bodies know when to stop remodeling? Bioelectric signaling networks guide pattern formation and may implement a somatic memory system. Deep parallels may exist between information processing in the brain and morphogenetic control mechanisms.

scholarly journals Interrelationship identification between humans from images using two class classifier

2018 ◽  
Vol 7 (2.21) ◽  
pp. 5 ◽  
Author(s):  
Amit Verma ◽  
T Meenpal ◽  
B Acharya
Keyword(s):  
Feature Extraction ◽  
Feature Detection ◽  
Confusion Matrix ◽  
Image Database ◽  
Identification Algorithm ◽  
Bag Of Words ◽  
Human Beings ◽  
Feature Detectors ◽  
Surf Features

The paper proposes an automatic interrelationship identification algorithm between human beings. The image database contains two interrelationship classes i.e. two people hugging and handshaking each other. The feature detection and feature extraction has been done using bag of words algorithm. SURF features and FAST features are used as feature detectors. Finally, the extracted features have been applied to SVM for classification. We have tested the classifier against a set of test images for both feature detectors.  Finally, the accuracy of the classifier has been calculated and confusion matrix has been plotted.  

scholarly journals A Review of ‘Brain Computation as Hierarchical Abstraction’

2016 ◽  
Vol 9 (2) ◽  
pp. 293-300
Author(s):  
Bodo Herzog
Keyword(s):  
Social Sciences ◽  
Decision Making ◽  
Computational Neuroscience ◽  
Daily Life ◽  
Book Series ◽  
Brain Functions ◽  
Interdisciplinary Dialogue ◽  
Computational Aspects ◽  
Hierarchical Abstraction ◽  
The Brain

AbstractThis article is a review of the book ‘Brain Computation As Hierarchical Abstraction’ by Dana H. Ballard published by MIT press in 2015. The book series computational neuroscience familiarizes the reader with the computational aspects of brain functions based on neuroscientific evidence. It provides an excellent introduction of the functioning, i.e. the structure, the network and the routines of the brain in our daily life. The final chapters even discuss behavioral elements such as decision-making, emotions and consciousness. These topics are of high relevance in other sciences such as economics and philosophy. Overall, Ballard’s book stimulates a scientifically well-founded debate and, more importantly, reveals the need of an interdisciplinary dialogue towards social sciences.

Systematic development and evaluation of composite methods for recognition of three-dimensional subtractive features

2005 ◽  
Vol 219 (12) ◽  
pp. 871-890 ◽  
Author(s):  
O Owodunni ◽  
S Hinduja
Keyword(s):  
Feature Detection ◽  
Three Dimensional ◽  
Detection Methods ◽  
Test Bed ◽  
The Public ◽  
Detection Systems ◽  
Composite Methods ◽  
Composite Feature ◽  
Tree Pruning ◽  
Pruning Technique

This paper describes a systematic procedure for developing composite feature detection systems from six methods for detecting three-dimensional depression features. The six methods, proposed by the authors in earlier papers, correspond to all the possible ways of grouping faces together from the simplest to the most complex grouping. All the possible ways of combining the six feature detection methods are considered and arranged in a tree structure. The possible composites are reduced to 20, using a tree pruning technique based on the criteria that the features detected should be the same (i.e. consistent), irrespective of the ordering of the faces in the B-rep model and that all faces of the component should be detected (i.e. complete coverage). A test bed for these 20 composites has been developed, implemented, and tested using carefully selected components from the public domain. The performance of these 20 composites is evaluated on the basis of suitability of the features as input to a machining application with minimal or no additional geometric reasoning, thus enabling the most promising composites to be identified.

Sign in / Sign up

Export Citation Format

Share Document