全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

微距摄影的多聚焦图像拍摄和融合

DOI: 10.11834/jig.20150411

Keywords: 微距摄影,多聚焦图像,图像对齐,图像融合

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的对于微距摄影来说,由于微距镜头的景深有限,往往很难通过单幅照片获得拍摄对象全幅清晰的图像.因此要想获取全幅清晰的照片,就需要拍摄多幅具有不同焦点的微距照片,并对其进行融合.方法传统的微距照片融合方法一般都假定需要融合的图像是已经配准好的,也并没有考虑微距图像的自动采集.因此提出了一种用于微距摄影的多聚焦图像采集和融合系统,该系统由3个部分组成.第1部分是一种微距图像拍摄装置,该硬件能够以高精度的方式拍摄物体在不同焦距下的微距照片.第2部分是一个基于不变特征的图像配准组件,它可以对在多个焦点下拍摄的微距图像进行自动配准和对齐.第3部分是一个基于图像金字塔的多聚焦图像融合组件,这个组件能够对已经对齐的微距照片进行融合,使得合成的图像具有更大的景深.该组件对基于图像金字塔的融合方法进行了扩展,提出了一种基于滤波的权重计算策略.通过将该权重计算与图像金字塔相结合,得到了一种基于多分辨率的多聚焦图像融合方法.结果论文使用设计的拍摄装置采集了多组实验数据,用以验证系统硬件设计和软件设计的正确性,并使用主观和客观的方法对提出的系统进行评价.从主观评价来看,系统合成的微距图像不仅具有足够的景深,而且在高分辨率下也能够清晰地呈现物体微小的细节.从客观评价来看,通过将系统合成的微距图像与其他方法合成的微距图像进行量化比较,在标准差、信息熵和平均梯度3种评价标准中都是最优的.结论实验结果表明,该系统是灵活和高效的,不仅能够对多幅具有不同焦点的微距图像进行自动采集、配准和融合,并且在图像融合的质量方面也能和其他方法相媲美.

References

[1]  Wilson T, Rogers S, Meyers L. Perceptual based hyper spectral image fusion using multiresolution analysis[J]. Optical Engineering, 1995, 34(11): 3154-3164.
[2]  Antonio M. Digital macro photography of cactus and succulent plants[J]. Cactus and Succulent Journal, 2013, 85(3):101-106.
[3]  Burt P, Kolczynski R. Enhanced image capture through fusion[C]//Proceedings of the 4th International Conference on Computer Vision. Berlin: Springer, 1993: 173-182.
[4]  Wang H, Jin Z, Li J. Research and development of multi-resolution image fusion [J]. Control Theory and Applications, 2004, 21(4): 145-149.
[5]  Jin H, Yang X, Jiao L, et al. Image enhancement via fusion based on Laplacian pyramid directional filter banks [C]//Proceedings of International Conference on Image Analysis and Recognition. Berlin: Springer, 2005: 239-246.
[6]  Haghighat M, Aghagolzadeh A, Seyedarabi H. Multi-focus image fusion for visual sensor networks in DCT domain[J]. Computers and Electrical Engineering, 2011, 37(2): 789-797.
[7]  Haghighat M, Aghagolzadeh A, Seyedarabi H. Real-time fusion of multi-focus images for visual sensor networks[J]. Iranian Machine Vision and Image Processing, 2010, 21: 1-6.
[8]  Pu T, Ni G. Contrast-based image fusion using the discrete wavelet transform[J]. Optical Engineering, 2000, 39(6): 2075-2082.
[9]  Wen Y, Li Y, Luo Y. The image fusion method based on wavelet transform in auto-analysis of pashm[J]. Journal of Sichuan University, 2000, 37(6): 36-40.
[10]  Wang H H, Peng J X, Wu W. Remote sensing image fusion using wavelet packet transform[J]. Journal of Image and Graphics,2002, 7(9): 922-937.[王海晖,彭嘉雄,吴巍.基于小波包变换的遥感图像融合[J].中国图象图形学报,2002,7(9):932-937.][DOI:10.11834/jig.200209297]
[11]  Wang H, Jing Z, Li J. Image fusion using non-separable wavelet frame[J]. Chinese Optics Letters, 2003, 1(9): 523-526.
[12]  Long G, Xiao L, Chen X Q. Overview of the applications of Curvelet transform in image processing[J]. Journal of Computer Research and Development, 2005, 2(8): 1331-1337.[隆刚,肖磊,陈学?. Curvelet变换在图像处理中的应用综述[J]. 计算机研究与发展,2005, 2(8): 1331-1337.]
[13]  Hassan M, Shah S. Block level multi-focus image fusion using wavelet transform [C]//Proceedings of International Conference on Signal Acquisition and Processing. Berlin: Springer, 2009: 213-216.
[14]  Brown M, Szeliski R, Winder S. Multi-image matching using multi-scale oriented patches [C]//Proceedings of International Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE Computer Society, 2005: 510-517.
[15]  David G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[16]  Fischler M, Bolles R. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communication of the ACM, 1981, 24(2): 381-395.
[17]  Burt P, Adelson H. A multiresolution spline with application to image mosaics[J]. ACM Transactions on Graphics, 1983, 2(4): 217-236.
[18]  Wekenm D, Nachtegael M, Kerre E. Using similarity measures and homogeneity for the comparison of images[J]. Image and Visual Computing, 2004, 22(3): 695-702.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133