Proceedings ArticleDOI
Quantum mechanics in computer vision: Automatic object extraction
Caglar Aytekin,Serkan Kiranyaz,Moncef Gabbouj +2 more
- pp 2489-2493
TLDR
The results of the proposed automatic object extraction method exhibit such a promising accuracy that pushes the frontier in this field to the borders of the input-driven processing only - without the use of “object knowledge” aided by long-term human memory and intelligence.Abstract:
An automatic object extraction method is proposed exploiting the rich mathematical structure of quantum mechanics. First, a novel segmentation method based on the solutions of Schrodinger's equation is proposed. This powerful segmentation method allows us to model complex objects and inherent structures of edge, shape, and texture information along with the grey-level intensity uniformity, all in a single equation. Due to the large amount of segments extracted with the proposed method, the selection of the object segment is performed by maximizing a regularization energy function based on a recently proposed sub-segment analysis indicating the object boundaries. The results of the proposed automatic object extraction method exhibit such a promising accuracy that pushes the frontier in this field to the borders of the input-driven processing only - without the use of “object knowledge” aided by long-term human memory and intelligence.read more
Citations
More filters
Proceedings ArticleDOI
Automatic Object Segmentation by Quantum Cuts
TL;DR: In this study, the link between quantum mechanics and graph-cuts is exploited and a novel saliency map generation and salient object segmentation method is proposed based on the ground state solution of a modified Hamiltonian, which outperforms many existing state-of-the-art algorithms.
Journal ArticleDOI
New quantum inspired meta-heuristic techniques for multi-level colour image thresholding
TL;DR: Three efficient meta-heuristic techniques, called ant colony optimization, differential evolution and particle swarm optimization, inspired by the fundamental features of quantum systems, are presented in this paper, which find optimal threshold values at different levels of thresholding for colour images.
Journal ArticleDOI
Binary image denoising using a quantum multilayer self organizing neural network
TL;DR: The QMLSONN outperforms the MLSONN and the Hopfield network in terms of the computation time and application results are demonstrated on a synthetic and a real life binary image with varying degrees of Gaussian and uniform noise.
Journal ArticleDOI
Efficient quantum inspired meta-heuristics for multi-level true colour image thresholding
TL;DR: The features of quantum computing are exploited to introduce four different quantum inspired meta-heuristic techniques to accelerate the execution of multi-level thresholding and affirm that the proposed quantum inspired particle swarm optimization technique outperforms other techniques.
Proceedings ArticleDOI
Visual saliency by extended quantum cuts
TL;DR: This study proposes an unsupervised, state-of-the-art saliency map generation algorithm which is based on a recently proposed link between quantum mechanics and spectral graph clustering, Quantum Cuts and introduces a novel approach to propose several saliency maps.
References
More filters
Journal ArticleDOI
Efficient Graph-Based Image Segmentation
TL;DR: An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.
Journal ArticleDOI
Learning to Detect a Salient Object
TL;DR: A set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, are proposed to describe a salient object locally, regionally, and globally.
Journal ArticleDOI
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
TL;DR: A universal statistical model for texture images in the context of an overcomplete complex wavelet transform is presented, demonstrating the necessity of subgroups of the parameter set by showing examples of texture synthesis that fail when those parameters are removed from the set.
Journal ArticleDOI
Unsupervised segmentation of color-texture regions in images and video
Y. Deng,B.S. Manjunath +1 more
TL;DR: The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed and applying the criterion to local windows in theclass-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions.