Earticle

초록

영어

According to the local and global feature of image, matching the image from a lot image library, this is the image retrieval task; however, the image retrieval need to search the information in the database, we need to find a method for efficient information retrieval. Deep belief network according to the characteristic of the initiative, through the method of training a multilayer neural network to process large amounts of data, and it is very efficient, in this article, as to the characteristics of image local features and global features, it gives a deep belief network image retrieval algorithm, the experiment verify the effectiveness of the algorithm.

목차

Abstract
 1. Introduction
 2. Related Works
  2.1 The Research Status of Deep Neural Network
  2.2 The Research Status of Image Retrieval
 3. The Proposed Scheme
  3.1 The Input of Deep Belief Network
  3.2 The Determination of Learning Network Layer
  3.3 Setting Hidden Nodes
  3.4 Adaptive Learning Method
 4. Experiment Results and Analysis
 5. Conclusion
 References

키워드

저자

• Sun Ting [ School of computer science and technology, Zhoukou Normal University, Zhoukou, Henan,466001, China ]
• Qi Yingchun [ School of computer science and technology, Zhoukou Normal University, Zhoukou, Henan,466001, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Multimedia and Ubiquitous Engineering

• 간기

  월간

• pISSN

  1975-0080

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605