scholarly journals Image Classification Based on Convolutional Denoising Sparse Autoencoder

2017 ◽  
Vol 2017 ◽  
pp. 1-16 ◽  
Author(s):  
Shuangshuang Chen ◽  
Huiyi Liu ◽  
Xiaoqin Zeng ◽  
Subin Qian ◽  
Jianjiang Yu ◽  
...  
Keyword(s):  
Image Classification ◽  
Saliency Detection ◽  
Feature Learning ◽  
Classification Performance ◽  
Local Contrast ◽  
Unsupervised Feature Learning ◽  
Semantic Categories ◽  
Sparse Autoencoder ◽  
Contrast Normalization ◽  
Center Bias

Image classification aims to group images into corresponding semantic categories. Due to the difficulties of interclass similarity and intraclass variability, it is a challenging issue in computer vision. In this paper, an unsupervised feature learning approach called convolutional denoising sparse autoencoder (CDSAE) is proposed based on the theory of visual attention mechanism and deep learning methods. Firstly, saliency detection method is utilized to get training samples for unsupervised feature learning. Next, these samples are sent to the denoising sparse autoencoder (DSAE), followed by convolutional layer and local contrast normalization layer. Generally, prior in a specific task is helpful for the task solution. Therefore, a new pooling strategy—spatial pyramid pooling (SPP) fused with center-bias prior—is introduced into our approach. Experimental results on the common two image datasets (STL-10 and CIFAR-10) demonstrate that our approach is effective in image classification. They also demonstrate that none of these three components: local contrast normalization, SPP fused with center-prior, and l2 vector normalization can be excluded from our proposed approach. They jointly improve image representation and classification performance.

scholarly journals Cystoscopic image classification by unsupervised feature learning and fusion of classifiers

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Seyyed Mohammad Reza Hashemi ◽  
Hamid Hassanpour ◽  
Ehsan Kozegar ◽  
Tao Tan
Keyword(s):  
Image Classification ◽  
Feature Learning ◽  
Unsupervised Feature Learning ◽  
Fusion Of Classifiers

scholarly journals Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification

2017 ◽  
Vol 14 (11) ◽  
pp. 1928-1932 ◽  
Author(s):  
Xiangrong Zhang ◽  
Yanjie Liang ◽  
Chen Li ◽  
Ning Huyan ◽  
Licheng Jiao ◽  
...  
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Feature Learning ◽  
Unsupervised Feature Learning ◽  
Hyperspectral Image Classification

scholarly journals An effective feature learning approach using genetic programming with image descriptors for image classification

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Image Classification ◽  
Learning Algorithm ◽  
Feature Learning ◽  
Classification Performance ◽  
Learning Approach ◽  
New Approach ◽  
Feature Descriptors ◽  
High Level ◽  
Almost All

© 2005-2012 IEEE. Being able to extract effective features from different images is very important for image classification, but it is challenging due to high variations across images. By integrating existing well-developed feature descriptors into learning algorithms, it is possible to automatically extract informative high-level features for image classification. As a learning algorithm with a flexible representation and good global search ability, genetic programming can achieve this. In this paper, a new genetic programming-based feature learning approach is developed to automatically select and combine five existing well-developed descriptors to extract high-level features for image classification. The new approach can automatically learn various numbers of global and/or local features from different types of images. The results show that the new approach achieves significantly better classification performance in almost all the comparisons on eight data sets of varying difficulty. Further analysis reveals the effectiveness of the new approach to finding the most effective feature descriptors or combinations of them to extract discriminative features for different classification tasks.

scholarly journals PolSAR Image Land Cover Classification Based on Hierarchical Capsule Network

2021 ◽  
Vol 13 (16) ◽  
pp. 3132
Author(s):  
Jianda Cheng ◽  
Fan Zhang ◽  
Deliang Xiang ◽  
Qiang Yin ◽  
Yongsheng Zhou ◽  
...  
Keyword(s):  
Land Cover ◽  
Image Classification ◽  
Single Neuron ◽  
Conditional Random Field ◽  
Image Interpretation ◽  
Feature Learning ◽  
Land Cover Classification ◽  
Classification Performance ◽  
Comprehensive Evaluations ◽  
Phase Amplitude

Polarimetric synthetic aperture radar (PolSAR) image classification is one of the basic methods of PolSAR image interpretation. Deep learning algorithms, especially convolutional neural networks (CNNs), have been widely used in PolSAR image classification due to their powerful feature learning capabilities. However, a single neuron in the CNN cannot represent multiple polarimetric attributes of the land cover. The capsule network (CapsNet) uses vectors instead of the single neuron to characterize the polarimetric attributes, which improves the classification performance compared with traditional CNNs. In this paper, a hierarchical capsule network (HCapsNet) is proposed for the land cover classification of PolSAR images, which can consider the deep features obtained at different network levels in the classification. Moreover, we adopt three attributes to uniformly describe the scattering mechanisms of different land covers: phase, amplitude, and polarimetric decomposition parameters, which improves the generalization performance of HCapsNet. Furthermore, conditional random field (CRF) is added to the classification framework to eliminate small isolated regions of the intra-class. Comprehensive evaluations are performed on three PolSAR datasets acquired by different sensors, which demonstrate that our proposed method outperforms other state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document