5 Hits in 5.2 sec

Intelligent Image Retrieval Techniques: A Survey

Mussarat Yasmin, Sajjad Mohsin, Muhammad Sharif
2014 Journal of Applied Research and Technology  
In the current era of digital communication, the use of digital images has increased for expressing, sharing and interpreting information.  ...  In this research, the aim is to highlight the efforts of researchers who conducted some brilliant work and to provide a proof of concept for intelligent content-based image retrieval techniques.  ...  Acknowledgements We are grateful to Department of Computer Science, COMSATS Institute of Information Technology Pakistan for providing us a platform to conduct this research study.  ... 
doi:10.1016/s1665-6423(14)71609-8 fatcat:ce3qthtoe5bdthys3yf6vadkvy

Semi-supervised learning for scalable and robust visual search

Jun Wang
2011 ACM SIGMultimedia Records  
The graph-based approaches are used to improve accuracy, while hashing approaches are used to improve efficiency and cope with large-scale applications.  ...  a sequential learning algorithm to derive boosted hash functions, and an extension to unsupervised cases by using pseudo labels.  ...  Alternatively, the underlying features and distance metrics used in representing and matching images can be refined using relevance feedback information [117] .  ... 
doi:10.1145/2069210.2069213 fatcat:hblb5ncrprcrlgi6ugph6naucy


2006 Alcoholism: Clinical and Experimental Research  
ABMs provide a powerful analysis of the roles topological networks (geographic and social) play. 23 AGENT-BASED MODELS OF ILLEGAL DRUG MARKETS. A.  ...  Standard statistical methods using static linear mathematical techniques do not provide adequate descriptions of such systems, particularly when dynamic feedback between system components is apparent.  ...  Additionally, a rAAV-NPY vector and a control vector with the coding sequence for green fluorescent protein (rAAV-GFP) were used.  ... 
doi:10.1111/j.1530-0277.2006.00151.x fatcat:l5e4ip4jjnfnzlbgqby6cdecrm

Robot share: a framework for robot knowledge sharing

Xiuyi Fan
More discussion on techniques such as stochastic methods and neural networks on feature selection can be found in ref. [23, 27] .  ...  Extracted features are then used to query the database. Most CBIR systems belong to this group.  ... 
doi:10.26053/0h-3ga8-dzg0 fatcat:v5ebecv735bqbfmbsqplj2rz2q

Bilddaten in den Digitalen Geisteswissenschaften

(:Unkn) Unknown, Universitätsbibliothek Der FU Berlin, Canan Hastik, Philipp Hegel
In this paper, the terms Deep Learning, Deep Neural Network, and Neural Network are used as synonyms.  ...  We used convolutional neural networks to classify single object images and complex interior scenes.  ...  Zukunft Wie wir zu zeigen versucht haben, ist die Videoannotationsdatenbank ra für eine Reihe von Anwendungen durchaus gut geeignet. 23 Gleichzeitig muss man feststellen, dass ein einzelnes System  ... 
doi:10.17169/refubium-30108 fatcat:byufkavkirg4hia6nd3zfh3jna