Title :
On an Improved FPGA Implementation of CNN-Based Gabor-Type Filters
Author :
Cesur, Evren ; Yildiz, Nerhun ; Tavsanoglu, Vedat
Author_Institution :
Dept. of Electron. & Commun. Eng., Yildiz Tech. Univ., Istanbul, Turkey
Abstract :
In this brief, the details of the architecture of a previously introduced improved field-programmable gate array implementation of the cellular neural network (CNN)-based 2-D Gabor-type filter are given, and the implementation results are discussed. The proposed architecture is suitable for real-time applications with high pixel rates. The prototype is capable of processing video streams up to a pixel rate of 373.2 megapixels per second (MP/s), including full-high-definition (HD) 1080p@60 (1080 × 1920 resolution, 60-Hz frame rate, and 124.4-MP/s visible pixel rate). This brief also contains convergence rate analysis results, along with some discussions on FIR and CNN-based implementation methods.
Keywords :
Gabor filters; cellular neural nets; convergence; field programmable gate arrays; real-time systems; video streaming; CNN-based 2D Gabor-type filter; FIR; HD; cellular neural network; convergence rate analysis; field-programmable gate array implementation; frequency 60 Hz; full-high-definition; improved FPGA implementation; pixel rate; realtime applications; video streams; Bandwidth; Computer architecture; Convergence; Equations; Field programmable gate arrays; Finite impulse response filter; Gabor filters; Cellular neural networks (CNNs); Gabor filters; field-programmable gate arrays (FPGAs); real-time systems; reconfigurable architectures;
Journal_Title :
Circuits and Systems II: Express Briefs, IEEE Transactions on
DOI :
10.1109/TCSII.2012.2218471
