Filters








31,459 Hits in 5.0 sec

A two-step face hallucination approach for video surveillance applications

Zhen Jia, Jianwei Zhao, Hongcheng Wang, Ziyou Xiong, Alan Finn
2013 Multimedia tools and applications  
Our proposed algorithm uses the Approximate Nearest Neighbors (ANN) search method to find a number of nearest neighbors for a stack of queries, instead of finding the exact match for each low frequency  ...  Our proposed algorithm uses a sparse representation and the ANN method to enhance both global face shape and local high frequency information while greatly improving the processing speed, as confirmed  ...  Therefore, in order to conduct example-based super-resolution for visual surveillance applications, we still need to improve the search speed while maintaining good super resolution results.  ... 
doi:10.1007/s11042-013-1721-4 fatcat:tpbk5x5vxjesdnxb472ltndst4

Fast face hallucination with sparse representation for video surveillance

Zhen Jia, Hongcheng Wang, Ziyou Xiong, Alan Finn
2011 The First Asian Conference on Pattern Recognition  
Our proposed algorithm uses the Approximate Nearest Neighbors (ANN) search method to find a number of nearest neighbors for a stack of queries, instead of finding the exact match for each low frequency  ...  Our proposed algorithm uses sparse representation and the ANN method to enhance both global face shape and local high frequency information while greatly improving the processing speed, as confirmed empirically  ...  Therefore, in order to conduct examplebased super-resolution for visual surveillance applications, we still need to improve the searching speed while maintaining good super resolution results.  ... 
doi:10.1109/acpr.2011.6166702 dblp:conf/acpr/JiaWXF11 fatcat:oxx4yfyfwjfhnkbbxitkudamr4

Multidimensional particle swarm optimization and applications in data clustering and image retrieval

Moncef Gabbouj
2010 2010 2nd International Conference on Image Processing Theory, Tools and Applications  
The natural behavior of a bird flock when searching for food is simulated through the movements of the individuals (particles or living organisms) in the flock.  ...  PSO is conceptually related to other evolutionary algorithms such as Genetic Algorithms, Genetic Programming, Evolution Strategies, and Evolutionary Programming.  ...  In order to extract perceptually important colors and to further improve the discrimination factor for a better clustering performance, an efficient color distance metric, which uses a fuzzy model for  ... 
doi:10.1109/ipta.2010.5586831 fatcat:euade5p6lfbyxlkg4eddswmo5m

Scaling Cross-Domain Content-Based Image Retrieval for E-commerce Snap and Search Application [article]

Isaac Kwan Yin Chung, Minh Tran, Eran Nussinovitch
2022 arXiv   pre-print
search and classification capabilities.  ...  Specifically, we present a system that is able to handle the scale of the data for e-commerce usage and the cross-domain nature of the query and gallery image pools.  ...  Visual search recommendations in their mobile and web applications, illustrated in Figure 1 , improve customer experience by reducing the time and effort needed for product searches.  ... 
arXiv:2204.11593v1 fatcat:t5xdysa5wfeq5ekgpl5lfs3qu4

Review of Meta-Heuristic Optimization based Artificial Neural Networks and its Applications

D. Devikanniga, K. Vetrivel, N. Badrinath
2019 Journal of Physics, Conference Series  
The efficiency of classification and prediction is improved by optimizing artificial neural network using the metaheuristic optimization algorithms.  ...  Upcoming sections cover the current trending research topics dealing with optimized artificial neural network concepts and provide some interesting insights for researchers to use in their respective applications  ...  The application of ANN hybrids for specific real-world applications The hybrid classifiers are modeled and developed particularly for specialized applications.  ... 
doi:10.1088/1742-6596/1362/1/012074 fatcat:wvimk7u265f7hay3si2uypbuni

Artificial Neural Networks Based Optimization Techniques: A Review

Maher G. M. Abdolrasol, S. M. Suhail Hussain, Taha Selim Ustun, Mahidur R. Sarker, Mahammad A. Hannan, Ramizi Mohamed, Jamal Abd Ali, Saad Mekhilef, Abdalrhman Milad
2021 Electronics  
This paper includes some results for improving the ANN performance by PSO, GA, ABC, and BSA optimization techniques, respectively, to search for optimal parameters, e.g., the number of neurons in the hidden  ...  In this paper, we present an extensive review of artificial neural networks (ANNs) based optimization algorithm techniques with some of the famous optimization techniques, e.g., genetic algorithm (GA),  ...  An example of improving the ANN is an efficient model based on the ABC optimization algorithm with neural networks [154] .  ... 
doi:10.3390/electronics10212689 fatcat:oupnikhxdbhedfz5yeatmtj4xa

Query-driven iterated neighborhood graph search for large scale indexing

Jingdong Wang, Shipeng Li
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
In this paper, we address the approximate nearest neighbor (ANN) search problem over large scale visual descriptors.  ...  We propose a query-driven iterated neighborhood graph search approach to improve the performance.  ...  cases and hence not proper for ANN search over high-dimensional visual descriptors.  ... 
doi:10.1145/2393347.2393378 dblp:conf/mm/WangL12 fatcat:s4eyt7upzfgthgbvsxvif2q5lu

A Review of Research on Pulsar Candidate Recognition Based on Machine Learning

Cheng Jun Zhang, Zhen Hong Shang, Wan Min Chen, Liu Xie, Xiang Hua Miao
2020 Procedia Computer Science  
At present, a large number of pulsar searches have produced millions of pulsar candidates.  ...  In the face of these large-scale data, if only relying on manual visual classification by experts in related fields, it will be a huge project.  ...  improved algorithms.  ... 
doi:10.1016/j.procs.2020.02.050 fatcat:vsqad27akzdgzpkapct7e4wu5m

Video Inpainting

Ankita Bagul, Asha Bhalerao, Vaishali Dhage
2014 International Journal of Computer Applications  
Masking algorithm is used for detection of scratches or damaged portions in video frames.  ...  The given algorithm offers performance improvement, because of that anyone can use it in interactive editing tools.  ...  Thus using NNF algorithm can improve efficiency by performing searches for adjacent pixels in an interdependent manner.  ... 
doi:10.5120/15851-4749 fatcat:zkn65sufy5eczlmf3fhyl2zt3e

Organizational Climate for Successful Aging

Hannes Zacher, Jie Yang
2016 Frontiers in Psychology  
This paper presents several improvements to linear search that allows it to outperform existing methods and recommends two approaches to exact matching.  ...  The second method improves query speed further by presorting the data using a data structure called d-D sort.  ...  Improved Linear Search The objective of visual descriptor extraction is usually to capture some structure.  ... 
doi:10.3389/fpsyg.2016.01007 pmid:27458405 pmcid:PMC4930930 fatcat:jgbrx62aqjfqvns7lj53cd4ypy

Fast Exact Nearest Neighbour Matching in High Dimensions Using d-D Sort

Ruan Lakemond, Clinton Fookes, Sridha Sridharan
2013 ISRN Machine Vision  
This paper presents several improvements to linear search that allows it to outperform existing methods and recommends two approaches to exact matching.  ...  The second method improves query speed further by presorting the data using a data structure called d-D sort.  ...  Improved Linear Search The objective of visual descriptor extraction is usually to capture some structure.  ... 
doi:10.1155/2013/405680 fatcat:3tic5gkfmfedlozbqckx4arjsu

Using a Visual Attention Model to Improve Gaze Tracking Systems in Interactive 3D Applications

S. Hillaire, G. Breton, N. Ouarti, R. Cozot, A. Lécuyer
2010 Computer graphics forum (Print)  
Our algorithm uses an uncertainty window, defined by the gaze tracker accuracy, and located around the gaze point given by the tracker.  ...  Then, using a visual attention model, it searches for the most salient points, or objects, located inside this uncertainty window, and determines a novel, and hopefully, better gaze point.  ...  We have proposed an algorithm using a saliency map which is meant to improve the accuracy of any gaze tracking system such as the ANN-based gaze tracking system described here.  ... 
doi:10.1111/j.1467-8659.2010.01651.x fatcat:dfi2ilj3gnhfnhjcgd4rvm3akq

Intelligent Training Algorithm for Artificial Neural Network EEG Classifications

Hanan A. R. Akkar, Faris B. Ali Jasim
2018 International Journal of Intelligent Systems and Applications  
The aim of this paper is to implement recently evolutionary algorithms for optimizing neural weights such as Grass Root Optimization (GRO), Artificial Bee Colony (ABC), Cuckoo Search Optimization (CSA)  ...  Artificial neural networks (ANN) have been widely used in classification. They are complicated networks due to the training algorithm used to fix their weights.  ...  [13] have proposed a novel PSO-OSD algorithm to improve the RBF learning algorithm in real time applications for EEG classification. III.  ... 
doi:10.5815/ijisa.2018.05.04 fatcat:be47wuywnbholansfqyq3rmcuy

Feature Selection on Thermal-stress Dataset [article]

Xuyang Shen, Jo Plested, Tom Gedeon
2021 arXiv   pre-print
Our result indicates that the genetic algorithm combined with ANNs can improve the prediction accuracy by 19.1% compared to the baseline.  ...  Support Vector Machine (SVM) and Artificial Neural Network (ANN) models were involved in measuring these three algorithms.  ...  Acknowledgements We thank Alasdair Tran for his invaluable feedback on the draft of this paper.  ... 
arXiv:2109.03755v1 fatcat:nr4w35eufbdgpfr5v4hzgr3e5m

A Hybrid Method for Searching Near-Optimal Artificial Neural Networks

Leandro Almeida, Teresa Ludermir
2006 2006 Sixth International Conference on Hybrid Intelligent Systems (HIS'06)  
This paper describes a method for searching nearoptimal neural networks using Genetic Algorithms.  ...  The method uses an evolutionary search with the simultaneous selection of initial weights, transfer functions, architectures and learning rules.  ...  Acknowledgments The authors would like to thank CNPq (Brazilian Research Council) for their financial support.  ... 
doi:10.1109/his.2006.264919 fatcat:wppmwnelgbh53etoq7utylvdcy
« Previous Showing results 1 — 15 out of 31,459 results