Pubblicazione scientifica

Fish recognition using convolutional neural network

FILONE TECNOLOGICO	TEMA
produzione e raccolta

RIASSUNTO

Studying fish recognition has important realistic and theoretical significance to aquaculture and marine biology. Fish recognition is challenging problem because of distortion, overlap and occlusion of digital images. Previous researchers have done a lot of work on fish recognition, but the classification accuracy may be not high enough. Classification and recognition methods based on convolutional neural network (CNN) develop fast in recent years because of its higher accuracy and the support of GPU. In this paper, we design several architectures for convolutional neural network for the fish recognition. After performing a series of experiments, we can get the CNN architecture which has best performance and robustness.

DATA

Data di pubblicazione: 01/09/2017

AUTORI

GUOQING DING
YAN SONG
JIA GUO
CHEN FENG
GUANGLIANG LI
BO HE
TIANHONG YAN

ENTE DI AFFERENZA

COLL OF INF SCI & ENG OCEAN UNIV CHINA QINGDAO CHINA
DEPT MECH & ELEC ENG CHINA JILIANG UNIV HANGZHOU CHINA

RIVISTA

OCEANS 2017 - Anchorage (Page(s): 1-4)

indietro