Image Dehazing Enhancement Algorithm Based on Mean Guided Filtering
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
To improve the effect of image restoration and solve the image detail loss, an image dehazing enhancementalgorithm based on mean guided filtering is proposed. The superpixel calculation method is used to pre-segmentthe original foggy image to obtain different sub-regions. The Ncut algorithm is used to segment the originalimage, and it outputs the segmented image until there is no more region merging in the image. By means of themean-guided filtering method, the minimum value is selected as the value of the current pixel point in the localsmall block of the dark image, and the dark primary color image is obtained, and its transmittance is calculatedto obtain the image edge detection result. According to the prior law of dark channel, a classic image dehazingenhancement model is established, and the model is combined with a median filter with low computationalcomplexity to denoise the image in real time and maintain the jump of the mutation area to achieve imagedehazing enhancement. The experimental results show that the image dehazing and enhancement effect of theproposed algorithm has obvious advantages, can retain a large amount of image detail information, and thevalues of information entropy, peak signal-to-noise ratio, and structural similarity are high. The researchinnovatively combines a variety of methods to achieve image dehazing and improve the quality effect. Throughsegmentation, filtering, denoising and other operations, the image quality is effectively improved, whichprovides an important reference for the improvement of image processing technology.
Abstract
To improve the effect of image restoration and solve the image detail loss, an image dehazing enhancementalgorithm based on mean guided filtering is proposed. The superpixel calculation method is used to pre-segmentthe original foggy image to obtain different sub-regions. The Ncut algorithm is used to segment the originalimage, and it outputs the segmented image until there is no more region merging in the image. By means of themean-guided filtering method, the minimum value is selected as the value of the current pixel point in the localsmall block of the dark image, and the dark primary color image is obtained, and its transmittance is calculatedto obtain the image edge detection result. According to the prior law of dark channel, a classic image dehazingenhancement model is established, and the model is combined with a median filter with low computationalcomplexity to denoise the image in real time and maintain the jump of the mutation area to achieve imagedehazing enhancement. The experimental results show that the image dehazing and enhancement effect of theproposed algorithm has obvious advantages, can retain a large amount of image detail information, and thevalues of information entropy, peak signal-to-noise ratio, and structural similarity are high. The researchinnovatively combines a variety of methods to achieve image dehazing and improve the quality effect. Throughsegmentation, filtering, denoising and other operations, the image quality is effectively improved, whichprovides an important reference for the improvement of image processing technology.
참고문헌 (20)
- V. Monga, "Algorithm unrolling: interpretable, efficient deep learning for signal and image processing", IEEE Signal Processing Magazine, 38(4), pp.18~44 (2021)
- Z. Ye, "Image defogging enhancement method based on bright region detection", Missiles and Space Vehicles, 2021(1), pp.115~120 (2021)
- J. You, "Dehazing and enhancement research of polarized image based on dark channel priori principle", Laser Infrared, 50(4), pp.493~500 (2020)
- L. He, "A haze removal algorithm based on guided coefficient weighted and adaptive image enhancement method", Microelectronics & Computer, 37(9), pp.73~77 (2020)
- Y. Fu, "Multi-level features progressive refinement and edge enhancement network for image dehazing", Optics and Precision Engineering, 30(9), pp.1091~1100 (2022)
- H. Filali, "Image segmentation using MRF model optimized by a hybrid ACO-ICM algorithm", Soft Computing, 25(15), pp.10181~10204 (2021)
- X. Zhou, "Optimization of multi threshold image segmentation using improved state transition algorithm", Computer Simulation, 39(1), pp.486~493 (2022)
- Alessia Amelio, "A new axiomatic methodology for the image similarity", Applied Soft Computing, 81, pp.105474~ (2019), Elsevier BV[DOI]
- Z. Jiang, "Image defogging algorithm based on sky region segmentation and dark channel prior", Journal of Systems Science and Information, 8(5), pp.476~486 (2020)
- Z. Chen, "An improved dark channel prior image defogging algorithm based on wavelength compensation", Earth Science Informatics, 12, pp.501~512 (2019)
- Y. Cui, "An improved dark channel defogging algorithm based on the HSI colour space", IET Image Processing, 16(3), pp.823~838 (2022)
- N. Hassan, "A cascaded approach for image defogging based on physical and enhancement models", Signal, Image and Video Processing, 14(5), pp.867~875 (2020)
- D. Fan, "An iterative defogging algorithm based on pixel-level atmospheric light map", International Journal of Modelling, Identification and Control, 35(4), pp.287~297 (2020)
- N. Sharma, "Single image defogging using deep learning techniques: past, present and future", Archives of Computational Methods in Engineering, 28, pp.4449~4469 (2021)
- S. He, "Integrated image defogging network based on improved atmospheric scattering model and attention feature fusion", Earth Science Informatics, 14, pp.2037~2048 (2021)
- G. Li, "A single image defogging algorithm for sky region recognition based on binary mask", Proceedings of SPIE 12247: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2022), pp.127~132 (2022), International Society for Optics and Photonics
- C. Kong, "Review of two typical image defogging algorithms and related improvements", Frontiers in Science and Engineering, 1(7), pp.132~134 (2021)
- N. S. Murthy, "An improved dark channel prior based defogging algorithm for video sequences", Journal of Information and Optimization Sciences, 42(1), pp.29~39 (2021)
- W. Xiao, "ASM-VoFDehaze: a real-time defogging method of zinc froth image", Connection Science, 34(1), pp.709~731 (2022)
- Wei Zhu, "RETRACTED ARTICLE: Sichuan mountainous environment and urban planning based on image dehazing algorithm", Arabian Journal of Geosciences, 14(18) (2021), Springer Science and Business Media LLC[DOI]