• Laser & Optoelectronics Progress
  • Vol. 58, Issue 22, 2210003 (2021)
Liang Hu1、2, Xuejuan Hu1、2、3、*, Zhenhong Huang1、2, Lu Xu1、2, and Lijin Lian2、3
Author Affiliations
  • 1Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen, Guangdong 518118, China
  • 2Key Laboratory of Advanced Optical Precision Manufacturing Technology of Guangdong Provincial Higher Education Institute, Shenzhen, Guangdong 518118, China
  • 3Guangdong Provincial Key Laboratory of Micro/Nano Optomechatronics Engineering, Shenzhen, Guangdong 518118, China
  • show less
    DOI: 10.3788/LOP202158.2210003 Cite this Article Set citation alerts
    Liang Hu, Xuejuan Hu, Zhenhong Huang, Lu Xu, Lijin Lian. Multi-Focus Image Fusion Based on Discrete Walsh-Hadamard Transform and Guided Filtering[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2210003 Copy Citation Text show less
    Sharp and blurred images and their DWHT results. (a) Sharp image; (b) blurred image; (c) DWHT of Fig.1(a); (d) DWHT of Fig.1(b)
    Fig. 1. Sharp and blurred images and their DWHT results. (a) Sharp image; (b) blurred image; (c) DWHT of Fig.1(a); (d) DWHT of Fig.1(b)
    Block diagram of proposed algorithm
    Fig. 2. Block diagram of proposed algorithm
    Focus region detection based on DWHT
    Fig. 3. Focus region detection based on DWHT
    Generation process of final decision map. (a) Initial decision map IDM (x,y); (b) small patch removing operation MD1 (x,y); (c) morphology operation MD2 (x,y); (d) final decision map FDM (x,y)
    Fig. 4. Generation process of final decision map. (a) Initial decision map IDM (x,y); (b) small patch removing operation MD1 (x,y); (c) morphology operation MD2 (x,y); (d) final decision map FDM (x,y)
    Three groups of multi-focus source images. (a) Clock; (b) book; (c) golf
    Fig. 5. Three groups of multi-focus source images. (a) Clock; (b) book; (c) golf
    Clock’s fusion images and corresponding residual images of different methods. (a)(f) GFF; (b)(g) MWGF; (c)(h) CNN; (d)(i) DCT; (e)(j) proposed method
    Fig. 6. Clock’s fusion images and corresponding residual images of different methods. (a)(f) GFF; (b)(g) MWGF; (c)(h) CNN; (d)(i) DCT; (e)(j) proposed method
    Enlarged images of labeled regions in Fig. 6
    Fig. 7. Enlarged images of labeled regions in Fig. 6
    Multi-sequence focused images. (a) Multi-sequence gravure pattern appearance images; (b) multi-sequence lithium battery pole piece images
    Fig. 8. Multi-sequence focused images. (a) Multi-sequence gravure pattern appearance images; (b) multi-sequence lithium battery pole piece images
    Multi-focus fusion results of multi-sequence gravure pattern appearance image. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Fig. 9. Multi-focus fusion results of multi-sequence gravure pattern appearance image. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Multi-focus fusion results of multi-sequence lithium battery pole piece image. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Fig. 10. Multi-focus fusion results of multi-sequence lithium battery pole piece image. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Enlarged images of labeled regions in Fig. 10. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Fig. 11. Enlarged images of labeled regions in Fig. 10. (a) GFF; (b) CNN; (c) DCT; (d) proposed method
    Quality evaluation of multi-focus sequence image fusion
    Fig. 12. Quality evaluation of multi-focus sequence image fusion
    Evaluation metricGFFMWGFCNNDCTProposed method
    QG0.69820.69580.70820.70640.7131
    QY0.74790.78060.74010.74430.7781
    QCB0.75840.77730.78210.78090.8357
    QFMI0.58620.59140.59580.59520.5980
    Table 1. Average evaluation metrics of three groups of multi-focus source images under different methods
    Liang Hu, Xuejuan Hu, Zhenhong Huang, Lu Xu, Lijin Lian. Multi-Focus Image Fusion Based on Discrete Walsh-Hadamard Transform and Guided Filtering[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2210003
    Download Citation