원문정보
보안공학연구지원센터(IJMUE)
International Journal of Multimedia and Ubiquitous Engineering
Vol.11 No.1
2016.01
pp.87-96
피인용수 : 0건 (자료제공 : 네이버학술정보)
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
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
저자정보
참고문헌
자료제공 : 네이버학술정보