基于卷积神经网络的图像识别算法设计与实现
Design and Implementation of Image Recognition Algorithm Based on Convolutional Neural Networks
王振 1高茂庭1
作者信息
- 1. 上海海事大学信息工程学院，上海 201306
- 折叠
摘要
卷积神经网络在图像识别领域取得很好的效果，但其网络结构对图像识别的效果和效率有较大的影响，为改善识别性能，通过重复使用较小卷积核，设计并实现一种新的卷积神经网络结构，有效地减少训练参数的数量，并能够提高识别的准确率。与图像识别领域当前具有世界先进水平的ILSVRC挑战赛中取得较好成绩的算法对比实验，验证这种结构的有效性。
Abstract
Convolutional neural networks has achieved a great success in image recognition. The structure of the network has a great impact on the performance and accuracy in image recognition. To improve the performance of this algorithm, designs and implements a new architecture of the convolutional neural network by using convolutional layers with small kernel size repeatedly, which will reduce the number of training parameters effectively and increase the recognition accuracy. Compared with the state-of-art results in ILSVRC, experiments demonstrate the effectiveness of the new network architecture.
关键词
卷积神经网络/深度学习/图像识别/机器学习/神经网络Key words
Convolutional Neural Networks/Deep Learning/Image Recognition/Machine Learning/Neural Network引用本文复制引用
基金项目
国家自然科学基金(61202022)
上海海事大学科研项目()
出版年
2015
NETL
NSTL
维普
万方数据