DocumentCode :
1769391
Title :
FPGA implementation of feature extraction for colorectal endoscopic images with NBI magnification
Author :
Mishima, Takeshi ; Shigemi, Satoshi ; Anh-Tuan Hoang ; Koide, Tetsushi ; Tamaki, T. ; Raytchev, Bisser ; Kaneda, Kazufumi ; Kominami, Yoko ; Miyaki, Rie ; Matsuo, Takuya ; Yoshida, Sigeru ; Tanaka, Shoji
Author_Institution :
Res. Inst. for Nanodevice, Bio Syst. Hiroshima Univ., Higashi-Hiroshima, Japan
fYear :
2014
fDate :
1-5 June 2014
Firstpage :
2515
Lastpage :
2518
Abstract :
In this study, we have proposed an improvement for feature extraction in computer-aided diagnosis (CAD) system for colorectal endoscopic images with narrow-band imaging (NBI) magnification. Dense Scale-Invariant Feature Transform (D-SIFT) is used in the feature extraction. It is necessary to consider a trade-off between the precision of the feature extraction and speedup by the FPGA implementation for processing of real time full high definition image. In this paper, we reduced the number of dimensions for feature representation in hardware implementation purpose.
Keywords :
biomedical optical imaging; endoscopes; feature extraction; field programmable gate arrays; medical image processing; FPGA implementation; NBI magnification; colorectal endoscopic images; computer-aided diagnosis system; dense scale-invariant feature transform; feature extraction; feature representation; narrow-band imaging magnification; real time full high definition image processing; Accuracy; Educational institutions; Feature extraction; Hardware; Histograms; Imaging; Software algorithms; Bag-of-Features (BoF); Colorectal Endoscopic Images; Computer-Aided Diagnosis (CAD); Dense Scale-Invariant Feature Transform (DSIFT); FPGA;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems (ISCAS), 2014 IEEE International Symposium on
Conference_Location :
Melbourne VIC
Print_ISBN :
978-1-4799-3431-7
Type :
conf
DOI :
10.1109/ISCAS.2014.6865684
Filename :
6865684
Link To Document :
بازگشت