Architecture of the parallel hierarchical network for fast image recognition
Fragment książki (Materiały konferencyjne)
MNiSW
15
WOS
| Status: | |
| Autorzy: | Timchenko Leonid I., Wójcik Waldemar, Kokriatskaya Nataliya I., Kutaev Yuriy F., Ivasyuk Igor D., Kotyra Andrzej, Smailova Saule |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Arkusze wydawnicze: | 0,5 |
| Język: | angielski |
| Strony: | 1452 - 1459 |
| Web of Science® Times Cited: | 1 |
| Scopus® Cytowania: | 2 |
| Bazy: | Web of Science | Scopus |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | TAK |
| Nazwa konferencji: | Conference on Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments |
| Skrócona nazwa konferencji: | SPIE-IEEE-PSP 2016 |
| URL serii konferencji: | LINK |
| Termin konferencji: | 29 maja 2016 do 6 czerwca 2016 |
| Miasto konferencji: | Wilga |
| Państwo konferencji: | POLSKA |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| Multistage integration of visual information in the brain allows humans to respond quickly to most significant stimuli while maintaining their ability to recognize small details in the image. Implementation of this principle in technical systems can lead to more efficient processing procedures. The multistage approach to image processing includes main types of cortical multistage convergence. The input images are mapped into a flexible hierarchy that reflects complexity of image data. Procedures of the temporal image decomposition and hierarchy formation are described in mathematical expressions. The multistage system highlights spatial regularities, which are passed through a number of transformational levels to generate a coded representation of the image that encapsulates a structure on different hierarchical levels in the image. At each processing stage a single output result is computed to allow a quick response of the system. The result is presented as an activity pattern, which can be compared with previously computed patterns on the basis of the closest match. With regard to the forecasting method, its idea lies in the following. In the results synchronization block, network-processed data arrive to the database where a sample of most correlated data is drawn using service parameters of the parallel-hierarchical network. |
