Journal ArticleDOI
An HVS-Directed Neural-Network-Based Image Resolution Enhancement Scheme for Image Resizing
TLDR
Simulation results demonstrate that the proposed new resolution enhancement algorithm can produce a higher visual quality for the interpolated image than the conventional interpolation methods.Abstract:Â
In this paper, a novel human visual system (HVS)-directed neural-network-based adaptive interpolation scheme for natural image is proposed. A fuzzy decision system built from the characteristics of the HVS is proposed to classify pixels of the input image into human perception nonsensitive class and sensitive class. Bilinear interpolation is used to interpolate the nonsensitive regions and a neural network is proposed to interpolate the sensitive regions along edge directions. High-resolution digital images along with supervised learning algorithms are used to automatically train the proposed neural network. Simulation results demonstrate that the proposed new resolution enhancement algorithm can produce a higher visual quality for the interpolated image than the conventional interpolation methods.read more
Citations
More filters
Patent
Electronic apparatus and control method thereof
Young-Jun Ryu,Dong-Wan Kim,Jae-Hyun Bae,Ki-Hoon Shin,Namgook Cho,Byeong-seob Ko,Ki-Beom Kim,Hee-seob Ryu +7 more
TL;DR: In this article, a display apparatus and a method of controlling the display apparatus is presented. But the display is not shown in this paper, since it is in a standby mode and the user cannot control it when the received sound is a reserved word candidate.
Journal ArticleDOI
VLSI Implementation of an Adaptive Edge-Enhanced Image Scalar for Real-Time Multimedia Applications
TL;DR: Compared with previous low-complexity techniques, this paper performs with better quality, higher performance, less memory requirements, and lower hardware cost than other image scaling methods.
Journal ArticleDOI
Geometric Regularized Hopfield Neural Network for Medical Image Enhancement.
Fayadh Alenezi,K. C. Santosh +1 more
TL;DR: In this article, a continuous modified Hopfield neural network (MHNN) was proposed to enhance the geometric correlation of features within various image hyperplanes via pixel gradient vectors, which is achieved by regularizing proposed MHNNs under cohomology.
Proceedings ArticleDOI
Adaptive and Non-adaptive Image Interpolation Techniques
TL;DR: From the various interpolation techniques, adaptive edge enhanced technique gives better PSNR of 38.95dB than standard interpolation technique, i.e PSNR (Peak Signal-to-Noise Ratio).
Patent
Visual-experience-optimized super-resolution frame generator
TL;DR: In this article, a Human Visual Preference Model (HVPM) is used to detect random texture regions, where visual artifacts and errors are tolerated to allow for more image details, and immaculate regions having flat areas, corners, or regular structures, where details may be sacrificed to prevent annoying visual artifacts that seem to stand out more.
References
More filters
Journal ArticleDOI
A new, fast, and efficient image codec based on set partitioning in hierarchical trees
Amir Said,William A. Pearlman +1 more
TL;DR: The image coding results, calculated from actual file sizes and images reconstructed by the decoding algorithm, are either comparable to or surpass previous results obtained through much more sophisticated and computationally complex methods.
Journal ArticleDOI
New edge-directed interpolation
Xin Li,Michael T. Orchard +1 more
TL;DR: Simulation results demonstrate that the new interpolation algorithm substantially improves the subjective quality of the interpolated images over conventional linear interpolation.
Book
Neural fuzzy systems: a neuro-fuzzy synergism to intelligent systems
Chin-Teng Lin,C. S. George Lee +1 more
TL;DR: Neural Fuzzy Systems provides a comprehensive, up-to-date introduction to the basic theories of fuzzy systems and neural networks, as well as an exploration of how these two fields can be integrated to create Neural-Fuzzy systems.
Journal ArticleDOI
Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields
Haluk Derin,H. Elliott +1 more
TL;DR: This paper presents random field models for noisy and textured image data based upon a hierarchy of Gibbs distributions, and presents dynamic programming based segmentation algorithms for chaotic images, considering a statistical maximum a posteriori (MAP) criterion.
Journal ArticleDOI
Image-adaptive watermarking using visual models
C.I. Podilchuk,Wenjun Zeng +1 more
TL;DR: This work proposes perceptually based watermarking schemes in two frameworks: the block-based discrete cosine transform and multiresolution wavelet framework and discusses the merits of each one, which are shown to provide very good results both in terms of image transparency and robustness.