AIMC Topic: Vision, Ocular

Clear Filters Showing 61 to 70 of 138 articles

Noise-trained deep neural networks effectively predict human vision and its neural responses to challenging images.

PLoS biology
Deep neural networks (DNNs) for object classification have been argued to provide the most promising model of the visual system, accompanied by claims that they have attained or even surpassed human-level performance. Here, we evaluated whether DNNs ...

Predictive Control-Based Completeness Analysis and Global Calibration of Robot Vision Features.

Computational intelligence and neuroscience
This paper provides an in-depth study and analysis of robot vision features for predictive control and a global calibration of their feature completeness. The acquisition and use of the complete macrofeature set are studied in the context of a robot ...

3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey.

Sensors (Basel, Switzerland)
3D visual recognition is a prerequisite for most autonomous robotic systems operating in the real world. It empowers robots to perform a variety of tasks, such as tracking, understanding the environment, and human-robot interaction. Autonomous robots...

Reconfigurable Micro- and Nano-Structured Camouflage Surfaces Inspired by Cephalopods.

ACS nano
Wrinkled surfaces and materials are found throughout the natural world in various plants and animals and are known to improve the performance of emerging optical and electrical technologies. Despite much progress, the reversible post-fabrication tuni...

A failure to learn object shape geometry: Implications for convolutional neural networks as plausible models of biological vision.

Vision research
Here we examine the plausibility of deep convolutional neural networks (CNNs) as a theoretical framework for understanding biological vision in the context of image classification. Recent work on object recognition in human vision has shown that both...

Optimizing Deeper Spiking Neural Networks for Dynamic Vision Sensing.

Neural networks : the official journal of the International Neural Network Society
Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks due to sparse, asynchronous, and binary event-driven processing. Most previous deep SNN optimization methods focus on static datasets (e.g., MN...

Artificial Vision Algorithms for Socially Assistive Robot Applications: A Review of the Literature.

Sensors (Basel, Switzerland)
Today, computer vision algorithms are very important for different fields and applications, such as closed-circuit television security, health status monitoring, and recognizing a specific person or object and robotics. Regarding this topic, the pres...

Uncovering structured responses of neural populations recorded from macaque monkeys with linear support vector machines.

STAR protocols
When a mammal, such as a macaque monkey, sees a complex natural image, many neurons in its visual cortex respond simultaneously. Here, we provide a protocol for studying the structure of population responses in laminar recordings with a machine learn...

Vision-Based Hybrid Controller to Release a 4-DOF Parallel Robot from a Type II Singularity.

Sensors (Basel, Switzerland)
The high accuracy and dynamic performance of parallel robots (PRs) make them suitable to ensure safe operation in human-robot interaction. However, these advantages come at the expense of a reduced workspace and the possible appearance of type II sin...

No-Reference Screen Content Image Quality Assessment With Unsupervised Domain Adaptation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
In this paper, we quest the capability of transferring the quality of natural scene images to the images that are not acquired by optical cameras (e.g., screen content images, SCIs), rooted in the widely accepted view that the human visual system has...