FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1571966209> ?p ?o ?g. }

• W1571966209 abstract "Fast pattern detection and identification is a fundamental problem for many applications of real-time systems (Bruce & Veloso 2003). Its reliability and performance have a major influence in a whole pattern recognition system. Nowadays, neural networks have shown very good results for detecting a certain pattern in a given image (Rowley et al. 1998; Feraud et al. 2000; Anifantis et al. 1999; Lang et al. 1988; El-Bakry 2001). Among other techniques (Schneiderman & Kanade 1998; Zhu et al. 2000; Srisuk & Kurutach 2002; Bao et al. 2006), neural networks are efficient pattern detectors (Rowley et al. 1998; Feraud et al. 2000; ElBakry 2002,a; El-bakry 2002,b; Essannouni and Ibn Elhaj 2006; Roth et al. 2006; Ramasubramanian & Kannan 2006). But the problem with neural networks is that the computational complexity is very high because the networks have to process many small local windows in the images (Zhu et al. 2000; Srisuk & Kurutach 2002; Yang et al. 2002). The main objective of this paper is to reduce the detection time using neural networks. The idea is to accelerate the operation of neural networks by performing the testing process in the frequency domain instead of spatial domain. Then, cross-correlation between the input image and the weights of neural networks is performed in the frequency domain. This model is called fast neural networks. Compared to conventional neural networks, fast neural networks show a significant reduction in the number of computation steps required to detect a certain pattern in a given image under test. Furthermore, another idea to increase the speed of these fast neural networks through image decomposition is presented. Moreover, the problem of sub-image (local) normalization in the Fourier space which presented in (Feraud et al. 2000) is solved.. The number of computation steps required for weight normalization is proved to be less than that needed for image normalization. Also, the effect of weight normalization on the speed up ratio is theoretically and practically discussed. Mathematical calculations prove that the new idea of weight normalization, instead of image normalization, provides good results and increases the speed up ratio. This is because weight normalization requires fewer computation steps than sub-image normalization. Moreover, for neural networks, normalization of weights can be easily done off line before starting the search process. In section 2, high speed neural networks for pattern detection are described. The details of conventional neural networks, high speed neural networks, and the speed up ratio of" @default.
• W1571966209 created "2016-06-24" @default.
• W1571966209 creator A5042916753 @default.
• W1571966209 date "2011-04-11" @default.
• W1571966209 modified "2023-10-03" @default.
• W1571966209 title "Design of High Speed Neural Networks for Fast Pattern Detection by using Cross Correlation and Matrix Decomposition" @default.
• W1571966209 cites W1523658021 @default.
• W1571966209 cites W1554570365 @default.
• W1571966209 cites W1587003203 @default.
• W1571966209 cites W1598732512 @default.
• W1571966209 cites W1616186945 @default.
• W1571966209 cites W1941208090 @default.
• W1571966209 cites W2000921048 @default.
• W1571966209 cites W2024149974 @default.
• W1571966209 cites W2061171222 @default.
• W1571966209 cites W2087205724 @default.
• W1571966209 cites W2089364633 @default.
• W1571966209 cites W2105188811 @default.
• W1571966209 cites W2113672589 @default.
• W1571966209 cites W2116577452 @default.
• W1571966209 cites W2121135674 @default.
• W1571966209 cites W2121601095 @default.
• W1571966209 cites W2125120037 @default.
• W1571966209 cites W2130752433 @default.
• W1571966209 cites W216012752 @default.
• W1571966209 cites W2166713160 @default.
• W1571966209 cites W2217896605 @default.
• W1571966209 cites W335401109 @default.
• W1571966209 cites W651054606 @default.
• W1571966209 doi "https://doi.org/10.5772/16099" @default.
• W1571966209 hasPublicationYear "2011" @default.
• W1571966209 type Work @default.
• W1571966209 sameAs 1571966209 @default.
• W1571966209 citedByCount "1" @default.
• W1571966209 countsByYear W15719662092017 @default.
• W1571966209 crossrefType "book-chapter" @default.
• W1571966209 hasAuthorship W1571966209A5042916753 @default.
• W1571966209 hasBestOaLocation W15719662091 @default.
• W1571966209 hasConcept C106487976 @default.
• W1571966209 hasConcept C117220453 @default.
• W1571966209 hasConcept C124681953 @default.
• W1571966209 hasConcept C153180895 @default.
• W1571966209 hasConcept C154945302 @default.
• W1571966209 hasConcept C159985019 @default.
• W1571966209 hasConcept C178790620 @default.
• W1571966209 hasConcept C185592680 @default.
• W1571966209 hasConcept C192562407 @default.
• W1571966209 hasConcept C2524010 @default.
• W1571966209 hasConcept C33923547 @default.
• W1571966209 hasConcept C41008148 @default.
• W1571966209 hasConcept C50644808 @default.
• W1571966209 hasConceptScore W1571966209C106487976 @default.
• W1571966209 hasConceptScore W1571966209C117220453 @default.
• W1571966209 hasConceptScore W1571966209C124681953 @default.
• W1571966209 hasConceptScore W1571966209C153180895 @default.
• W1571966209 hasConceptScore W1571966209C154945302 @default.
• W1571966209 hasConceptScore W1571966209C159985019 @default.
• W1571966209 hasConceptScore W1571966209C178790620 @default.
• W1571966209 hasConceptScore W1571966209C185592680 @default.
• W1571966209 hasConceptScore W1571966209C192562407 @default.
• W1571966209 hasConceptScore W1571966209C2524010 @default.
• W1571966209 hasConceptScore W1571966209C33923547 @default.
• W1571966209 hasConceptScore W1571966209C41008148 @default.
• W1571966209 hasConceptScore W1571966209C50644808 @default.
• W1571966209 hasLocation W15719662091 @default.
• W1571966209 hasLocation W15719662092 @default.
• W1571966209 hasOpenAccess W1571966209 @default.
• W1571966209 hasPrimaryLocation W15719662091 @default.
• W1571966209 hasRelatedWork W2033914206 @default.
• W1571966209 hasRelatedWork W2042327336 @default.
• W1571966209 hasRelatedWork W2046077695 @default.
• W1571966209 hasRelatedWork W2146076056 @default.
• W1571966209 hasRelatedWork W2163831990 @default.
• W1571966209 hasRelatedWork W2378160586 @default.
• W1571966209 hasRelatedWork W2386387936 @default.
• W1571966209 hasRelatedWork W2996038082 @default.
• W1571966209 hasRelatedWork W3003836766 @default.
• W1571966209 hasRelatedWork W3047965787 @default.
• W1571966209 isParatext "false" @default.
• W1571966209 isRetracted "false" @default.
• W1571966209 magId "1571966209" @default.
• W1571966209 workType "book-chapter" @default.