Premium
Pseudo‐color enhancement and its segmentation for femtosecond laser spot image
Author(s) -
Wang FuBin,
Wu Chen,
Liu Yang,
Feng Ding,
Tu Paul
Publication year - 2018
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/mop.31062
Subject(s) - artificial intelligence , computer vision , image segmentation , particle swarm optimization , computer science , pixel , image processing , optics , segmentation , physics , image (mathematics) , algorithm
When using femtosecond laser processing silicon wafer, arises laser spot along with the plasma diffraction. Comparatively studied the spot images of silicon wafer which was in three processing movement states as follows: towards the left, stop, towards the right, found that the three dimensional Gauss mean ablation energy of spot image almost kept the same, this provides experimental support for femtosecond laser feedback processing based on Gauss energy of spot image. Then the following image enhancement strategies are proposed: pseudo color transformation for spot image, color decomposition in RGB space and image superposition of G component, and the quality of the spot image is improved. In addition, adopted the method of Particle Swarm Optimization (PSO) or K ‐means respectively, analyzed the segmentation effect for spot image: through traversal compares the gray value of image pixel and fitness function, realized the spot image segmentation with PSO, and the clustering and segmentation for data cluster of image pixel was realized by K ‐means. Finally, overcome the shortcomings of PSO and K ‐means, the ideal segmentation for spot target image is realized by combining the two methods.