Semantic Analysis of Natural Images Using Hidden Markov Models
碩士 === 國立中正大學 === 電機工程研究所 === 91 === The tremendous growth in digital multimedia data is driving the need for more sophisticated methods for automatic image analysis, cataloging, searching. Semantic analysis based on content-based image retrieval is the focus of current research and it indeed has ob...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2003
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/78932846414545617558 |
| Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 91 === The tremendous growth in digital multimedia data is driving the need for more sophisticated methods for automatic image analysis, cataloging, searching. Semantic analysis based on content-based image retrieval is the focus of current research and it indeed has obtained a great achievement. But we want to extract semantic information of image directly without the retrieval for image database. This technique is insufficient in current research.
In this thesis, we employ Hidden Markov Model (HMM) to analyze semantic of natural image. HMM is a powerful probabilistic tool on modeling sequential data. We present some model structure building policy for HMM to deal with semantic extraction problem. The experiment results of semantic analysis are proved with satisfaction.
|
|---|