Adaptive iterative guided filtering for suppressing background noise in ptychographical imaging

Qiao, Ziling; Xiu, Wen; Zhou, Xuyang; Feng, Qinglai; Liu, Shutian; Gao, Bin; Liu, Wei; Chi, Dazhao; Liu, Zhengjun

doi:10.1016/j.optlaseng.2022.107233

Cited by 7 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The image capture process is prone to noise due to factors such as exposure time, electronic interference, or variations in photosensitive components, necessitating the introduction of an image preprocessing phase. Guided filtering [13][14][15] excellently maintains edges and enhances details while smoothing image noise, avoiding the common issue of edge blurring seen with traditional filters. This process can be expressed as follows: where I is the guidance image, P is the input image to be filtered, Q is the filtered output image, and W is the weight determined by the guidance image I; µ k represents the mean of pixel values within the window, σ k represents the variance of pixel values within the window, I i and I j are the values of two adjacent pixels, and ε is a regularization term.…”

Section: D Image Processingmentioning

confidence: 99%

Gap measurement method based on projection lines and convex analysis of 3D points cloud

Pan,

Jiang,

Tang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate measurement of the gap between the lower surface of the relay and the ground is critical for ensuring the quality of the finished product. Traditional gap measurement methods have some shortcomings, such as low accuracy, poor robustness, and loss of depth clues in obscured areas. In this study, a novel gap measurement method based on computer vision is proposed, which includes a projection line model based on guided filtering and a 3D surface point cloud model based on a three dimensional plane reference.- The relay gap was measured by calculating the projection lines of the upper and lower surfaces of the gap with an error of ±0.016 mm. A 3D point cloud model captures the key features of the underside of the relay through image processing techniques, and combines convex hull and centroid estimation to construct a three-dimensional reference plane for the gap, which could achieve high-precision, real-time measurement of the gap (with an error less than ±0.0087 mm). The experimental measurement results show that the proposed method is better than the SelfConvNet method, which has a high measurement accuracy and strong anti-interference ability, and an accuracy rate of up to 99.5% in factory relay quality inspection experiments.

show abstract

Section: D Image Processingmentioning

confidence: 99%

Gap measurement method based on projection lines and convex analysis of 3D points cloud

Pan,

Jiang,

Tang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…This hybrid method takes full advantage of the two combined models. Recently, more image de-noising model have been proposed in litterature as [12][13][14].…”

Section: Related Work 21 Related Work On the Restoration Of Noisy Imagesmentioning

confidence: 99%

Exploitation of second-and fourth-order PDEs to improve Lossy compression of noisy images

Welba¹,

THIERRY²,

Noura³

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

This paper presents a lossy compression method for noisy images. The main contributions in this paper are : improve the performance of noisy image compression algorithms by using partial differential equations (PDEs) as an image preprocessing filter and show that it is more advantageous to apply a restoration filter before compressing noise images.Method :The preprocessing filter is applied to the noisy image first. A comparing of the obtained outcomes with those in the scientific literature devoted to the restoration of noisy images is performed. The filtered image is then submitted to a compression algorithm. The compression algorithm employed is a hybrid of the following : DWT+SPIHT+HUFFMAN. Results:The simulation results demonstrate that the suggested technique is as efficient as approaches described in the scientific literature for picture compression and/or image restoration.

show abstract

“…In fact, the ART methods are based on Kaczmarz' method [19], [20]. Modern approaches for the low-dose computed tomography problem and denoising includes what is known today as ''the machine learning for image reconstruction'' [21], [22], [23], [24], such as batch gradient descent, stochastic gradient descent, and many others.…”

Section: Introductionmentioning

confidence: 99%

“…The problem of recovering a function f (x, y) from a limited set of Radon projections has been dealt with in the mathematical and engineering literatures, for instance, [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41]. Examples of different approaches include interpolating the missing views such as [25], spectrum analysis [24], statistical iterative methods [27]. A common approach is the theory of using different moments to recover the function, [28], [29], [30].…”

Section: Introductionmentioning

confidence: 99%

“…To better constrain the solution, compressive sensing techniques [32], [33] have been applied to promote sparsity in reconstructions. As said, the Machine learning for image reconstruction [21], [22], [23], [24], [34], [35], [36], [37] provide an alternative. These studies are essentially focused on image processing with pre-trained deep networks, either to in-paint sinogram images [34], [35], or to correct artifacts in reconstructed images [36], [37].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computed Tomography Reconstruction Using Only One Projection Angle

Hjouj

Jouini

2023

IEEE Access

View full text Add to dashboard Cite

Let F represent a digitized version of an image f (x, y). Assume that the image fits inside a rectangular region and this region is subdivided into M × N squares. We call these squares the shifted box functions. Thus f (x, y) is approximated by M × N matrix F. This paper proofs that F can be recovered exactly and uniquely from the Radon transform of f using only one selected view angle with a well selected family of MN lines. The paper also proposes a precise method for computing the Radon transform of an image. The approach can be categorized as an algebraic reconstruction, but it is merely a theoretical contribution for the field of limited data tomography.

show abstract

Adaptive iterative guided filtering for suppressing background noise in ptychographical imaging

Cited by 7 publications

References 50 publications

Gap measurement method based on projection lines and convex analysis of 3D points cloud

Gap measurement method based on projection lines and convex analysis of 3D points cloud

Exploitation of second-and fourth-order PDEs to improve Lossy compression of noisy images

Computed Tomography Reconstruction Using Only One Projection Angle

Contact Info

Product

Resources

About