The Research of Improved Spanning Tree Kernel Algorithm for Image Classification

2015 ◽  
Vol 12 (7) ◽  
pp. 2563-2570
Author(s):  
Ming Yang
2020 ◽  
Vol 58 (12) ◽  
pp. 8583-8597
Author(s):  
Shuang Wang ◽  
Yanhe Guo ◽  
Wenqiang Hua ◽  
Xinan Liu ◽  
Guoxin Song ◽  
...  

2014 ◽  
Vol 513-517 ◽  
pp. 1387-1391
Author(s):  
Qiang Rong Jiang ◽  
Zhe Wu

Face Recognition has been recognized as a major research field in pattern recognition and computer vision. This technique is widely adopted, because of its unique convenience, economy and high accuracy compared to other biological recognition techniques. An interesting and important challenge is thus to investigate high-efficient recognition algorithm. The introduction of kernel methods in pattern recognition has been received significant attentions in the recent several years, and gray kernel and graph kernel are two popular approaches. The paper proposes maximum spanning tree kernel and region histogram intersection kernel; moreover, experiments demonstrate that higher face recognition accuracy can be achieved by multiple kernels which are the combination of them.


2009 ◽  
Vol E92-B (3) ◽  
pp. 909-921
Author(s):  
Depeng JIN ◽  
Wentao CHEN ◽  
Li SU ◽  
Yong LI ◽  
Lieguang ZENG

2020 ◽  
Vol 79 (9) ◽  
pp. 781-791
Author(s):  
V. О. Gorokhovatskyi ◽  
I. S. Tvoroshenko ◽  
N. V. Vlasenko

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.


Author(s):  
Sumit Kaur

Abstract- Deep learning is an emerging research area in machine learning and pattern recognition field which has been presented with the goal of drawing Machine Learning nearer to one of its unique objectives, Artificial Intelligence. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. Deep learning (DL) basically based on a set of supervised and unsupervised algorithms that attempt to model higher level abstractions in data and make it self-learning for hierarchical representation for classification. In the recent years, it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. This paper will present a survey on different deep learning techniques for remote sensing image classification. 


Sign in / Sign up

Export Citation Format

Share Document