On differentiability of common image processing algorithms

Zhukovsky, Alexander

doi:10.1117/12.2523135

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [7], the author proposes the use of deep learning methods to implement the classical edge detector, Harris corner detector, and Niblack binarization algorithms. By using gradient descent to tune the parameters of the classical methods, neural networks allow the classical methods to adapt to different image and lighting conditions and extract more complex and informative features, which improves the quality of binarization.…”

Section: Related Workmentioning

confidence: 99%

Threshold U-Net: speed up document binarization with adaptive thresholds

Lihota,

Gayer,

Arlazarov

2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

U-Net similar architectures are widely used in the task of document image binarization. However, despite the good quality of binarization, they also have high computational complexity, which greatly limits their use on mobile and embedded devices. The performance bottleneck of U-Net architectures is the first encoder layers and the last decoder layers, which operate on high-resolution input data and contain the largest number of operations. Based on this, in this paper we propose a new Threshold U-Net model: instead of predicting the final image, Threshold U-Net predicts a low-resolution adaptive threshold map, with which the input image is binarized. The proposed architecture naturally combines the ideas of classical algorithms that calculate the binarization threshold for a specific image region with an approach based on a deep learning model with a large receptive field and context understanding. Threshold U-Net demonstrates quality of binarization of historical documents comparable to U-Net on the DIBCO-2017 dataset. At the same time, depending on the resolution of the threshold map, Threshold U-Net is up to 2 times faster, requires up to 26% less RAM and consists up to 10% fewer parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Threshold U-Net: speed up document binarization with adaptive thresholds

Lihota,

Gayer,

Arlazarov

2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

show abstract

“…Curves detection is not a new problem. It is often solved using edge detection algorithms such as Canny edge detector (original implementation [27] or maybe in the form of neural networks [28]) and others. Such an approach can be seen in the papers [29,30].…”

Section: Introductionmentioning

confidence: 99%

A method of detecting end-to-end curves of limited curvature

Panfilova¹,

Aliev²,

Kunina

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

View full text Add to dashboard Cite

In this paper we consider a method for detecting end-to-end curves of limited curvature like the k-link polylines with bending angle between adjacent segments in a given range. The approximation accuracy is achieved by maximization of the quality function in the image matrix. The method is based on a dynamic programming scheme constructed over Fast Hough Transform calculation results for image bands. The proposed method asymptotic complexity is O(h⋅(w+h/k)⋅log(h/k)), where h and w are the image size, and k is the approximating polyline links number, which is an analogue of the complexity of the fast Fourier transform or the fast Hough transform. We also show the results of the proposed method on synthetic and real data.

show abstract

On differentiability of common image processing algorithms

Cited by 2 publications

References 7 publications

Threshold U-Net: speed up document binarization with adaptive thresholds

Threshold U-Net: speed up document binarization with adaptive thresholds

A method of detecting end-to-end curves of limited curvature

Contact Info

Product

Resources

About