Research of Diver Sonar Image Recognition Based on Support Vector Machine
2013 ◽
Vol 785-786
◽
pp. 1437-1440
◽
Keyword(s):
To recognize small diver target from the dim special diver sonar images accurately, the Support Vector Machine method is used as classifier. According to the main characteristics of diver, five feature parameters, including Average-scale, Velocity, Shape, Direction, Included angle, are chosen as the input of characteristics vectors to train the net. And then the testing images are classified and identified. The experimental results show that accuracy rate of recognition reaches 94.5% for as many as 200 testing images. The experiment indicates that small object recognition from complex sonar images based on the right selection of feature parameters is of good performance by using the SVM method as well as good engineering foreground.
Keyword(s):
2021 ◽
Vol 275
◽
pp. 122140
2017 ◽
Vol 9
(1)
◽
pp. 168781401668596
◽
Keyword(s):
2019 ◽
Vol 351
◽
pp. 012028
Keyword(s):