Guided Filter based Edge-preserving Image Non-blind Deconvolution

Yang, Hang; Zhu, Ming; Zhang, Zhongbo; Huang, Heyan

doi:10.48550/arxiv.1609.01839

Cited by 1 publication

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the investigation of several imaging parameter metrics verifies and satisfies all of the claims made by the proposed hybrid method. The suggested system improved IQI by 50 percent and has a great peakto-noise ratio, which means it has better resolution and picture quality [21]. Regarding structural resemblance, the proposed technique reaches higher accuracy with values closer to the maximum value, i.e., one.…”

Section: Discussionmentioning

confidence: 88%

“…According to the data in Table 1 suggested hybrid methodology's fusion output beats all currently used fusion procedures in theoretical and practical analyses. [41] 0.68 0.69 39.67 CNN [21] 0.97 0.94 33.65 NSCT-GIF [39] 1.00 0.99 45.68 Guided Filter [27] 1.00 1.00 45.79 Proposed System 1.00 1.00 94.36…”

Section: Experimental Analysis 51 Objective Analysis (I) Comparative ...mentioning

confidence: 99%

“…Sets Algorithm IQI mSSIM PSNR PCA [40] 0.43 0.44 28.60 DWT [41] 0.53 0.47 29.45 GIF [39] 0.61 0.55 32.56 4 PCNN [42] 0.65 0.59 35.32 NSCT [41] 0.80 0.65 39.78 CNN [21] 0.99 0.93 23.80 NSCT-GIF [39] 0.97 0.95 40.67 Guided Filter [27] Compared to techniques such as PCA, DWT, GIF, and NSCT in the Image Quality Index figure (4), the proposed system excels by raising the quality index by about 50 percent, with practical simulated values of 0.99, which is very close to 1. Similarly, in figure (5), mSSIM is used for measuring Mean Structural Similarity.…”

Section: Experimental Analysis 51 Objective Analysis (I) Comparative ...mentioning

confidence: 99%

“…Under various combinations of fusion rules, the NSCT-based methods produce fairly satisfactory fusion outcomes. Picture fusion using guided filters [20], [21], [22] has also gained popularity since it maintains good spatial consistency, reduces the curved edge, but suffers from staircase effects at image boundaries. Recent developments in neuroscience have demonstrated that deep feature representations can be studied hierarchically, beginning with simplistic ideas like oriented edges and progressing to higher-level complicated designs like segments, parts, textures, and objects.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improved Image Fusion Technique Using Convolutional Neural Networks and The Hybrid PCA-Guided Filter

Jagtap¹,

Thepade²

2023

IJCDS

View full text Add to dashboard Cite

In order to better accurately forecast the diagnostic features, medical image fusion attempts to combine multi-focus and multimodal medical data into an original image. The outcomes of deep learning-based image processing can be visually beautiful. The incomprehensibility of the outcomes in Medical Imaging is a critical topic. This paper offers a feature-level multi-focus, multi-exposure, and multimodal image fusion using a hybrid layer of Principal Component Analysis (PCA) and Guided Filter (GF) to maximize the anatomical details and eliminate significant noise and artefacts. The proposed method utilizes a Convolutional Neural Network (CNN) based network for feature extraction. The original image is initially decomposed using Principal Component Analysis (PCA). A PCA decreases its dimensionality while preserving all of the essential information in the picture in the first stage and produces a revised weight map. A Guided Filter is used at the PCA output to uphold the edges and further augment the features, reducing the ringing and blurring effects. In the third step, a pre-trained CNN network creates a new weight map by extracting critical characteristics from pictures in the input dataset. The output feature map combines the weight maps produced by the GF and CNN, which is further fused with the reference picture to create the fused image output. The contribution of developed method:• To improvise image quality features by removing noise, ringing and blurring.• Increase the quality of the image by using the hybrid mechanism for extracting more underlying critical features of images [1]. The estimation is based on three multimodal imaging datasets, including CT-MRI, MRI-PET, and MRI-SPECT. Furthermore, the proposed method excels in existing state-of-the-art techniques in terms of fusion quality. .

show abstract

Section: Discussionmentioning

confidence: 88%