All Title Author
Keywords Abstract

Publish in OALib Journal
ISSN: 2333-9721
APC: Only $99

ViewsDownloads

Relative Articles

More...
-  2018 

Convolutional Neural Network Based on Spatial Pyramid for Image Classification
Convolutional Neural Network Based on Spatial Pyramid for Image Classification

DOI: 10.15918/j.jbit1004-0579.17140

Keywords: convolutional neural network multiscale feature extraction image classification
convolutional neural network multiscale feature extraction image classification

Full-Text   Cite this paper   Add to My Lib

Abstract:

A novel convolutional neural network based on spatial pyramid for image classification is proposed. The network exploits image features with spatial pyramid representation. First, it extracts global features from an original image, and then different layers of grids are utilized to extract feature maps from different convolutional layers. Inspired by the spatial pyramid, the new network contains two parts, one of which is just like a standard convolutional neural network, composing of alternating convolutions and subsampling layers. But those convolution layers would be averagely pooled by the grid way to obtain feature maps, and then concatenated into a feature vector individually. Finally, those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection layer. This generated feature vector derives benefits from the classic and previous convolution layer, while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the network. Experimental results demonstrate that this model improves the accuracy and applicability compared with the traditional model.
A novel convolutional neural network based on spatial pyramid for image classification is proposed. The network exploits image features with spatial pyramid representation. First, it extracts global features from an original image, and then different layers of grids are utilized to extract feature maps from different convolutional layers. Inspired by the spatial pyramid, the new network contains two parts, one of which is just like a standard convolutional neural network, composing of alternating convolutions and subsampling layers. But those convolution layers would be averagely pooled by the grid way to obtain feature maps, and then concatenated into a feature vector individually. Finally, those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection layer. This generated feature vector derives benefits from the classic and previous convolution layer, while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the network. Experimental results demonstrate that this model improves the accuracy and applicability compared with the traditional model.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133