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: This work proposes a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions, and uses it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system.
Abstract: Existing object recognition techniques often rely on human labeled data conducting to severe limitations to design a fully autonomous machine vision system. In this work, we present an intelligent machine vision system able to learn autonomously individual objects present in real environment. This system relies on salient object detection. In its design, we were inspired by early processing stages of human visual system. In this context we suggest a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions. Then we use it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system. We provide results of our salient object detection algorithm on MSRA Salient Object Database benchmark comparing its quality with other state-of-the-art approaches. The proposed system has been implemented on a humanoid robot, increasing its autonomy in learning and interaction with humans. We report and discuss the obtained results, validating the proposed concepts.

86 citations

Proceedings ArticleDOI
04 Oct 1989
TL;DR: Various methods of handling video data on the MediaBENCH are introduced and discussed to show how video data can be manipulated on visual database systems which deal with spatial and temporal factors.
Abstract: The importance of content-oriented visual user interfaces using video icons for visual database systems is clarified. The effectiveness of both still and live video images, especially for user's browsing and interaction, is shown by means of the MediaBENCH (hypermedia basic environment for computer and human interactions), which is a basic prototype multimedia database system. Various methods of handling video data on the MediaBENCH are introduced and discussed to show how video data can be manipulated on visual database systems which deal with spatial and temporal factors. A visual interface using video icons is quite suitable to video editing, presentation support or other electronic video document systems. >

86 citations

Posted Content
TL;DR: A novel CNN architecture named as ISGAN is proposed to conceal a secret gray image into a color cover image on the sender side and exactly extract the secret image out on the receiver side and can achieve start-of-art performances on LFW, PASCAL-VOC12 and ImageNet datasets.
Abstract: Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information hiding domain. There are also several works based on deep learning to do image steganography, but these works still have problems in capacity, invisibility and security. In this paper, we propose a novel CNN architecture named as \isgan to conceal a secret gray image into a color cover image on the sender side and exactly extract the secret image out on the receiver side. There are three contributions in our work: (i) we improve the invisibility by hiding the secret image only in the Y channel of the cover image; (ii) We introduce the generative adversarial networks to strengthen the security by minimizing the divergence between the empirical probability distributions of stego images and natural images. (iii) In order to associate with the human visual system better, we construct a mixed loss function which is more appropriate for steganography to generate more realistic stego images and reveal out more better secret images. Experiment results show that ISGAN can achieve start-of-art performances on LFW, Pascal VOC2012 and ImageNet datasets.

86 citations

Journal ArticleDOI
TL;DR: This paper analyzes different ways of compounding one-dimensional motion estimates (image gradients, spatiotemporal frequency triplets, local correlation estimates) into two-dimensional velocity estimates, including linear and nonlinear methods.

85 citations

Journal ArticleDOI
TL;DR: A novel high capacity data hiding method based on JPEG that can achieve an impressively high embedding capacity of around 20% of the compressed image size with little noticeable degradation of image quality is proposed.
Abstract: The JPEG image is the most popular file format in relation to digital images. However, up to the present time, there seems to have been very few data hiding techniques taking the JPEG image into account. In this paper, we shall propose a novel high capacity data hiding method based on JPEG. The proposed method employs a capacity table to estimate the number of bits that can be hidden in each DCT component so that significant distortions in the stego-image can be avoided. The capacity table is derived from the JPEG default quantization table and the Human Visual System (HVS). Then, the adaptive least-significant bit (LSB) substitution technique is employed to process each quantized DCT coefficient. The proposed data hiding method enables us to control the level of embedding capacity by using a capacity factor. According to our experimental results, our new scheme can achieve an impressively high embedding capacity of around 20% of the compressed image size with little noticeable degradation of image quality.

85 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