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: A visual attention index descriptor based on a visual attention model bridges the semantic gap between low-level descriptors used by computers and high-level concepts perceived by humans.
Abstract: A visual attention index descriptor based on a visual attention model bridges the semantic gap between low-level descriptors used by computers and high-level concepts perceived by humans.

84 citations

Posted Content
TL;DR: A new learning-based method that is the first to predict perceptual image error like human observers, and significantly outperforms existing algorithms, beating the state-of-the-art by almost 3× on the authors' test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning- based methods.
Abstract: The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual differences like humans. Some previous approaches used hand-coded models, but they fail to model the complexity of the human visual system. Others used machine learning to train models on human-labeled datasets, but creating large, high-quality datasets is difficult because people are unable to assign consistent error labels to distorted images. In this paper, we present a new learning-based method that is the first to predict perceptual image error like human observers. Since it is much easier for people to compare two given images and identify the one more similar to a reference than to assign quality scores to each, we propose a new, large-scale dataset labeled with the probability that humans will prefer one image over another. We then train a deep-learning model using a novel, pairwise-learning framework to predict the preference of one distorted image over the other. Our key observation is that our trained network can then be used separately with only one distorted image and a reference to predict its perceptual error, without ever being trained on explicit human perceptual-error labels. The perceptual error estimated by our new metric, PieAPP, is well-correlated with human opinion. Furthermore, it significantly outperforms existing algorithms, beating the state-of-the-art by almost 3x on our test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning-based methods.

84 citations

Journal ArticleDOI
TL;DR: It is shown that the periphery can indeed perceive biological motion, but it suffers from an inability to detect biological motion signals when they are embedded in dynamic visual noise, and suggests that this peripheral deficit is not due to biological motion perception per se, but to signal/noise segregation.
Abstract: Biological motion perception, having both evolutionary and social importance, is performed by the human visual system with a high degree of sensitivity. It is unclear whether peripheral vision has access to the specialized neural systems underlying biological motion perception; however, given the motion component, one would expect peripheral vision to be, if not specialized, at least highly accurate in perceiving biological motion. Here we show that the periphery can indeed perceive biological motion. However, the periphery suffers from an inability to detect biological motion signals when they are embedded in dynamic visual noise. We suggest that this peripheral deficit is not due to biological motion perception per se, but to signal/noise segregation.

84 citations

Journal ArticleDOI
TL;DR: The main contribution is to theoretically prove that the basis matrices of (k,n)-OVCS can be used in (k-n)-XVCS, which uses XOR operation for decoding, and to enhance the contrast.
Abstract: A (k,n) visual cryptographic scheme (VCS) encodes a secret image into n shadow images (printed on transparencies) distributed among n participants. When any k participants superimpose their transparencies on an overhead projector (OR operation), the secret image can be visually revealed by a human visual system without computation. However, the monotone property of OR operation degrades the visual quality of reconstructed image for OR-based VCS (OVCS). Accordingly, XOR-based VCS (XVCS), which uses XOR operation for decoding, was proposed to enhance the contrast. In this paper, we investigate the relation between OVCS and XVCS. Our main contribution is to theoretically prove that the basis matrices of (k,n)-OVCS can be used in (k,n)-XVCS. Meantime, the contrast is enhanced 2(k-1) times.

84 citations

Journal ArticleDOI
06 Aug 2013
TL;DR: A short history of advances in perceptual visual signal compression is presented, and perceptual models and how they are embedded into systems for compression and transmission are described, both with and without current compression standards.
Abstract: One- and two-way communication with digital compressed visual signals is now an integral part of the daily life of millions. Such commonplace use has been realized by decades of advances in visual signal compression. The design of effective, efficient compression and transmission strategies for visual signals may benefit from proper incorporation of human visual system (HVS) characteristics. This paper overviews psychophysics and engineering associated with the communication of visual signals. It presents a short history of advances in perceptual visual signal compression, and describes perceptual models and how they are embedded into systems for compression and transmission, both with and without current compression standards.

83 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