반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

한국반도체디스플레이기술학회 (The Korean Society Of Semiconductor & Display Technology)
권호 표지

LFFCNN: 라이트 필드 카메라의 다중 초점 이미지 합성

LFFCNN: Multi-focus Image Synthesis in Light Field Camera

  • 김형식 (단국대학교 전자전기공학부) ;
  • 남가빈 (단국대학교 전자전기공학부) ;
  • 김영섭 (단국대학교 전자전기공학부)
  • Hyeong-Sik Kim (Department of Electronic and Electrical Engineering, Dankook University) ;
  • Ga-Bin Nam (Department of Electronic and Electrical Engineering, Dankook University) ;
  • Young-Seop Kim (Department of Electronic and Electrical Engineering, Dankook University)
  • 투고 : 2023.09.13
  • 심사 : 2023.09.18
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

키워드

과제정보

NRF-2020R1A2C2009717의 지원으로 이 논문을 제출합니다.

참고문헌

  1. G. Wu et al., "Light Field Image Processing: An Overview," in IEEE Journal of Selected Topics in Signal Processing, vol. 11, no. 7, pp. 926-954, Oct. (2017). https://doi.org/10.1109/JSTSP.2017.2747126
  2. Yu Liu, Lei Wang, Juan Cheng, Chang Li, Xun Chen, Multi-focus image fusion: A Survey of the state of the art, Information Fusion, vol. 64, pp. 71-91, (2020). https://doi.org/10.1016/j.inffus.2020.06.013
  3. Zhang, Xingchen. "Deep learning-based multi-focus image fusion: A survey and a comparative study." IEEE Transactions on Pattern Analysis and Machine Intelligence, (2021).
  4. Pan, Tao, et al. 'A novel multi-focus image fusion network with U-shape structure." Sensors 20, no. 3901, (2020).
  5. Zhang, Yu, et al. "IFCNN: A general image fusion framework based on convolutional neural network." Information Fusion 54, pp. 99-118, (2020). https://doi.org/10.1016/j.inffus.2019.07.011
  6. Long, Jonathan, et al. "Fully convolutional networks for semantic segmentation." 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015).
  7. He, Kaiming, et al., "Spatial pyramid pooling in deep convolutional networks for visual recognition." Computer Vision - ECCV 2014, pp. 346-361, (2014).
  8. Deng, J. et al., Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248-255, (2009).
  9. He, Kaiming, et al., "Deep residual learning for image recognition." 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016).
  10. Johnson, Justin, et al., "Perceptual losses for real-time style transfer and Super-Resolution." Computer Vision - ECCV 2016, 2016, pp. 694-711, (2016).
  11. Ruan, Lingyan, et al. "Aifnet: All-in-focus image restoration network using a light field-based dataset." IEEE Transactions on Computational Imaging 7, pp. 675-688, (2021). https://doi.org/10.1109/TCI.2021.3092891
  12. Chun, H. W., Han, M. K., & Jang, J. H. "Trends in the Technology Development of Light Field.", Electronics and Telecommunications Trends, Vol. 33, No. 2, pp. 56- 63 , (2018).