支持向量机
计算机科学
机器视觉
模式识别(心理学)
机器学习
自动化
线性判别分析
算法
软件
目视检查
作者
Liangzhong Fan,Ying Liu
出处
期刊:Aquaculture
[Elsevier]
日期:2013-03-04
卷期号:380: 91-98
被引量:13
标识
DOI:10.1016/j.aquaculture.2012.10.016
摘要
In this paper, an approach based on geometric features to count overlapping fry fish is presented. Back propagation neural network (BPNN) and least squares support vector machine (LS-SVM) were used to construct classification models. 19 video clips with fish numbers varying from 10 to 100 were captured by a computer vision system. A total of 600 sub-images with overlapping fish were randomly selected, 300 images were used as a training set to create a calibration model, and remaining images were used to verify the model. 7 geometric features (area, perimeter, convex area, bounding box width, bounding box height, skeleton length, endpoint number) were obtained from the overlapping fish images. Results indicate that the best performance with about 98.73% of the average counting accuracy rate is achieved by LS-SVM model, which is better than the performance of BPNN model. The combined multiple geometric features coupled with an LS-SVM classifier is a highly accurate way for fry fish counting. (C) 2012 Published by Elsevier B.V.
科研通智能强力驱动
Strongly Powered by AbleSci AI