The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
Method of scene image classification based on Gist descriptor and CNN
Author(s): 
Pages: 7-11
Year: Issue:  11
Journal: Video Engineering

Keyword:  Gist descriptorfeature extractionconvolutional neural networkscene classification;
Abstract: 针对大多数场景分类方法只能学习浅层特征,忽略图像之间的相关结构信息,提出一种基于Gist特征与卷积神经网络结合的场景图像分类方法.其中Gist特征用于提取场景图像的全局特征,并将其作为深度学习模型的输入,通过逐层训练卷积神经网络,提取更高层次的特征,并用训练好的卷积神经网络进行分类.实验在O&T室外场景图像数据集和MNIST手写体数据集上考察了batchsize、卷积核对分类结果的影响,并与DBN,NN,SVM和CART作为分类器的分类结果进行比较,充分说明了本文方法的有效性.
Related Articles
No related articles found