Font Size: a A A

Research On The Algorithms Of Multi-focus Image Fusion

Posted on:2007-06-21Degree:MasterType:Thesis
Country:ChinaCandidate:H YuFull Text:PDF
GTID:2178360182472216Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
Multi-focus image fusion is to give birth to a completely clear image by fusing the registered images of the same scene with different focus points, which are under the same imaging conditions.For visible light imaging system, optical lenses, particularly those with long focal lengths, suffer from the problem of limited depth of field. Consequently, it is often difficult to obtain good focus for all objects in the picture. But it can be solved by multi-focus image fusion. This technology is propitious to boost the using efficiency of the image information.It can also improve the reliability of the system detecting and recognizing the objects.Because of these merits ,multi-focus image fusion is widely used in these areas such as machine vision,digital camera and object recognition and so on.There are many multi-focus image fusion algorithms, mainly consisted of the spatial area based and the frequency area based algorithms.In this paper,the algorithms based on the definition index are studied,on the wavelet transform based algorithms basis. When discussing the single image definition index based image fusion algorithms, it proposed an algorithm based on the image blocks' wavelet energy.This algorithm not only has the predominant local spatial and frequency characteristics,but also has small calculation complexity,because it doesn't need wavelet inverse transform.And the outputs of it are better than the wavelet transform based algorithms and the image blocks' energy based algorithms. When discussing the multi-index of the image definition based image fusion algorithms, a multi-focus image fusion using BP neural networks based on sub-block uniformity and energy indexes is proposed.In this part,we emulated it ?nd compared it with the routine algorithms.The following main points are included:① Discussed the basic theory, actuality and the existing questions of the image fusiontechnology. ② Classified and summarized the multi-focus image fusion algorithms and the quantitativeevaluation of it.③ Studied the wavelet transform based multi-focus image fusion algorithms. Analyzed materially the multi-resolution wavelet transform based image fusion algorithms ,wavelet packet transform based image fusion algorithms,and emulated these algorithms.Especially discussed the choice of the wavelet transform coefficients.④ According to the multi-focus image fusion algorithms, discussed deeply the image definition based image fusion algorithms.And it proceeded from the single index and multi-index of the image definition respectively.And two new algorithms are proposed:multi-focus image fusion using image blocks' wavelet energy and multifocus image fusion using BP neural networks based on sub-block uniformity and energy indexes.⑤ The last is the summary of my work and the prospect of future work.
Keywords/Search Tags:Multi-focus Image Fusion, Wavelet Transform, Block Segmentation, Wavelet Energy, BP Neural Network
PDF Full Text Request
Related items