ABSTRACT
In order to avoid the limitations of artificial feature extraction, the CNN model is adopted to extract image features by big data-driven adaptive learning, which improves the accuracy of the features. For avoiding the loss of spatial information, an improved CNN model based on up-sampling is proposed, which consists of six layers of superimposed small convolution. The multi-layer design not only expands the receptive field, but also reduces the number of training parameters, and improves the running speed. The fusion method based on improved CNN model is proposed for multi-focus images. The improved CNN model divides the input image into focus region and non-focus region, and form the decision map. According to the decision map optimized by GFF, the focus regions are intergraded by pixel-by-pixel weighted fusion strategy to obtain fusion image. Experimental results show that the fusion results of the proposed method are clear in detail, complete in structure, no distortion in contrast, and no artifacts in the picture. It effectively avoids grayscale discontinuity, artifacts and other problems, and is better than classical methods we selected.
- Gao Chen. Research on the parallel key technology of image feature extraction based on GPU[D]. Thesis for the degree of master of engineering in Nanjing University of Posts and Telecommunications. 2018.4Google Scholar
- Huang W, Jing Z. Evaluation of focus measures in multi-focus image fusion[J]. Pattern Recognition Letters, 2007, 28(4):493-500. https://doi.org/10.1016/j.patrec.2006.09.005Google ScholarDigital Library
- Tang J, Deng C, Huang G, Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine[J]. Geoscience and Remote Sensing, IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(3):1174-1185. https://doi.org/10.1109/TGRS.2014.2335751Google ScholarCross Ref
- Weng Piao, Lu Yanhui, Qi Xianbiao, Pavement crack segmentation technology based on improved fully convolutional networks[J]. Computer Engineering and Applications, 2019, 55(16):235-239. https://doi.org/10.3778/j.issn.1002-8331.1901-0068Google Scholar
- Ren S, He K, Ross G, Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031Google ScholarDigital Library
- Xue Jianming, Liu Hongzhe,Yuan Jiazheng, Facial expression recognition algorithm based on CNN and features of key regions[J]. Transducer and microsystem technologies, 2019, 10(38):146-149. https://doi.org/10.13873/J.1000-9789(2019)10-0146-04Google Scholar
- Liu Y, Chen X, Peng H, Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion, 2017, 36:191-207. https://doi.org/10.1016/j.inffus.2016.12.001Google ScholarDigital Library
- Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2):1097-1105. https://doi.org/10.1145/3065386Google ScholarDigital Library
- Zhou Feiyan, Jin Linpeng, Dong Jun. Review of convolutional neural network. Chinese Journal of Computers, 2017, 40(6): 1229-1251.https://doi.org/10.11897/SP.J.1016.2017.01229.Google Scholar
- Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 39(4):640-651. https://doi.org/10.1109/cvpr.2015.7298965.Google ScholarCross Ref
- Li W, Xie Y, Zhou H, Structure-aware image fusion[J]. Optik, 2018, 11(172):1-11. https://doi.org/10.1016/j.ijleo.2018.06.123 https://doi.org/10.1109/TPAMI.2011.109Google Scholar
- Zhang L X, Zeng G P, Wei J J. Adaptive Region-Segmentation Multi-Focus Image Fusion Based on Differential Evolution[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(3),1954010-1/1954010-23, https://doi.org/10.1142/S0218001419540107Google ScholarCross Ref
- Li S, Kang X, Hu J. Image fusion with guided filtering[J]. IEEE Transactions on Image Processing, 2013, 22(7):2864-2875. https://doi.org/10.1109/TIP.2013.2244222Google ScholarCross Ref
- Liu Z, Blasch E, Xue Z, Objective assessment of multiresolution Image fusion algorithms for context enhancement in night vision: a comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(1):94-109.Google ScholarDigital Library
Recommendations
Multi-focus image fusion through pixel-wise voting and morphology
AbstractMulti-focus image fusion (MFIf) aims to fuse two or more images into one image, so that the fused image contains more information. This paper proposes a new multi-focus image fusion based on pixel-wise voting and morphology. Firstly, we perform ...
Multi-focus Image Fusion Algorithms Research Based on Curvelet Transform
WGEC '09: Proceedings of the 2009 Third International Conference on Genetic and Evolutionary ComputingDue to the limited depth-of-focus of optical lenses, it is often difficult to get an image that contains all relevant objects in focus. Multi-focus image fusion algorithms can solve this problem effectively. Based on the analysis of the most widely used ...
A New Type of Multi-focus Image Fusion Method Based on Curvelet Transforms
ICECE '10: Proceedings of the 2010 International Conference on Electrical and Control EngineeringAs the limited depth-of-focus of optical lenses, it is usually difficult to get an image that contains all information of the objects in focus. Multi-focus image fusion method can solve this problem effectively. A new multi-focus image fusion method was ...
Comments