scispace - formally typeset
Search or ask a question
Topic

Human visual system model

About: Human visual system model is a research topic. Over the lifetime, 8697 publications have been published within this topic receiving 259440 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: The results suggest that adaptation affects at least two neural representations of expression: one specific to the individual (not the image), and one that represents expression across different facial identities.

208 citations

Journal ArticleDOI
TL;DR: VIVA is a proposed visual language for image processing that serves as an effective teaching tool for students of image processing and takes account of several secondary goals, including the completion of a software platform for research in human/image interaction and the establishment of a presentation medium for image-processing algorithms.
Abstract: Visual languages have been developed to help new programmers express algorithms easily. They also help to make experienced programmers more productive by simplifying the organization of a program through the use of visual representations. However, visual languages have not reached their full potential because of several problems including the following: difficulty of producing visual representations for the more abstract computing constructs; the lack of adequate computing power to update the visual representations in response to user actions; the immaturity of the subfield of visual programming and need for additional breakthroughs and standardization of existing mechanisms. Visualization of Vision Algorithms (VIVA) is a proposed visual language for image processing. Its main purpose is to serve as an effective teaching tool for students of image processing. Its design also takes account of several secondary goals, including the completion of a software platform for research in human/image interaction, the creation of a vehicle for studying algorithms and architectures for parallel image processing, and the establishment of a presentation medium for image-processing algorithms.

208 citations

Journal ArticleDOI
26 Jul 2013
TL;DR: The principles and methods of modern algorithms for automatically predicting the quality of visual signals are discussed and divided into understandable modeling subproblems by casting the problem as analogous to assessing the efficacy of a visual communication system.
Abstract: Finding ways to monitor and control the perceptual quality of digital visual media has become a pressing concern as the volume being transported and viewed continues to increase exponentially. This paper discusses the principles and methods of modern algorithms for automatically predicting the quality of visual signals. By casting the problem as analogous to assessing the efficacy of a visual communication system, it is possible to divide the quality assessment problem into understandable modeling subproblems. Along the way, we will visit models of natural images and videos, of visual perception, and a broad spectrum of applications.

206 citations

Posted Content
TL;DR: The human visual system is found to be more robust to image manipulations like contrast reduction, additive noise or novel eidolon-distortions than deep neural networks, indicating that there may still be marked differences in the way humans and current DNNs perform visual object recognition.
Abstract: Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algorithms called deep neural networks (DNNs) that achieve human-level classification performance on object recognition tasks. Furthermore, a growing number of studies report similarities in the way DNNs and the human visual system process objects, suggesting that current DNNs may be good models of human visual object recognition. Yet there clearly exist important architectural and processing differences between state-of-the-art DNNs and the primate visual system. The potential behavioural consequences of these differences are not well understood. We aim to address this issue by comparing human and DNN generalisation abilities towards image degradations. We find the human visual system to be more robust to image manipulations like contrast reduction, additive noise or novel eidolon-distortions. In addition, we find progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker, indicating that there may still be marked differences in the way humans and current DNNs perform visual object recognition. We envision that our findings as well as our carefully measured and freely available behavioural datasets provide a new useful benchmark for the computer vision community to improve the robustness of DNNs and a motivation for neuroscientists to search for mechanisms in the brain that could facilitate this robustness.

206 citations

Journal ArticleDOI
TL;DR: The implementation of a theory for the detection of intensity changes, proposed by Marr and Hildreth, where the image is first processed independently through a set of different size operators, whose shape is the Laplacian of a Gaussian, ▿2G(x, y).
Abstract: This article describes the implementation of a theory for the detection of intensity changes, proposed by Marr and Hildreth (Proc. R. Soc. London, Ser. B 207, 1980, 187–217). According to this theory, the image is first processed independently through a set of different size operators, whose shape is the Laplacian of a Gaussian, ▿2G(x, y). The loci, along which the convolution outputs cross zero mark the positions of intensity changes at different resolutions. These zero-crossings can be described by their position, slope of the convolution output across zero, and two-dimensional orientation. The set of descriptions from different operator sizes forms the input for later visual processes, such as stereopsis and motion analysis. There are close parallels between this theory and the early processing of information by the human visual system.

204 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
89% related
Feature extraction
111.8K papers, 2.1M citations
86% related
Image segmentation
79.6K papers, 1.8M citations
86% related
Image processing
229.9K papers, 3.5M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
84% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202349
202294
2021279
2020311
2019351
2018348