Single-Channel Grayscale Processing Algorithm for Transmission Tissue Images Based on Heterogeneity Detection
- 14 Downloads
Aiming at the problem of low contrast and unclear edge of gray image in hyperspectral transmission imaging, the single-channel grayscale processing algorithm was applied to the simulated image based on the simulation experiment. The experiment shows that this algorithm improves the contrast to a certain extent and enhances the image edge and grayscale image quality. While improving the quality of grayscale images, this algorithm also triples the number of original images, providing a data enhancement method for heterogeneity detection using deep learning. Therefore, this experiment verifies the feasibility of the single-channel processing algorithm and may provide a method for multispectral transmission biological tissue images, it may be a data enhancement method that can be applied to deep learning for tissue image detection.
KeywordsMultispectral tissue image processing Image graying Grayscale image quality Target detection
The authors would love to acknowledge funding from NYSFC and TSF. This work was partially supported by the Natural Youth Science Foundation of China (NYSFC-61401310) and the Tianjin Science Foundation (TSF-18JCYBJC86400).
- 1.Yang X, Li G, Lin L (2016) Assessment of spatial information for hyperspectral imaging of lesion. In: SPIE, vol 10024, p 100242OGoogle Scholar
- 3.Rousset F, Ducros N et al (2018) Time-resolved multispectral imaging based on an adaptive single-pixel camera. Opt Express 26(8):10550–10558Google Scholar
- 5.Yang X, Hu Y, Li G, Lin L (2018) Optimized lighting method of applying shaped-function signal for increasing the dynamic range of LED-multispectral imaging system. Rev Sci Instrum. https://doi.org/10.1063/1.5022700
- 6.Li H, Li G, An WJ, He GQ, Lin L (2019) “Synergy effect” and its application in LED-multispectral imaging for improving image quality. https://doi.org/10.1016/j.optcom.2018.12.091
- 7.Li WS, Du J, Zhao ZM, Long JY (2019) Fusion of medical sensors using adaptive cloud model in local Laplacian pyramid domain. IEEE Trans Biomed Eng 66(4):1172–1183Google Scholar
- 8.Wang WQ, Liu H, Liang LL, Liu Q, Xie G (2019) A regularised model-based pan-sharpening method for remote sensing images with local dissimilarities. Int J Remote Sens 40(8):3029–3054 Google Scholar
- 9.Yann LC, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444 Google Scholar
- 10.Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE conference on computer vision and pattern recognition, pp 580–587Google Scholar