Transcript GRNN.pptx
Application of GRNN neural network in non texture image inpainting and restoration
Vahid K. Aliloua, FarzinYaghmaee Pattern Recognition Letters Volume 62, 1 September 2015, Pages 24–31 Reporter : 陳彥鈞、邱麟捷 1
Outline
Introduction General regression neural network Definition GRNN-based image inpainting Parameter settings Experiments and comparisons Conclusion 2
Introduction(1/5)
Image inpainting is the technique of restoring and repairing lost parts of an image by using the information of their surrounding areas. It is a powerful technique for restoring old and scratched pictures or artworks From the mathematical point of view, inpainting is essentially an interpolation problem 3
Introduction(2/5)
Formally, the inpainting problem can be expressed in this way: given a corrupted image
I
pixel inside Ω with some missing region Ω , fill-in each with a value inferred from Ω 𝑐 .
4
Introduction(3/5)
Recently, some researchers proposed to use artificial neural networks for inpainting applications Artificial neural networks (ANNs) are one of the most powerful and popular tools for black-box modeling and are designed and inspired by real biological neural networks which have been applied in many fields, such as automotive, banking, electronics, financial, manufacturing and robotics 5
Introduction(4/5)
In this paper, we present a method to fill-in the missing or damaged areas of images by using GRNN network .
The missing regions are first separated and sorted according to their size. Then the algorithm proceeds with applying a GRNN network to each one in order to repair their damaged pixels. 6
Introduction(5/5)
7
General regression neural network (1/3) The general regression neural network (GRNN) is a variation of radial basis neural networks which is designed for function approximation and regression. It is established based on a one-pass learning algorithm and does not require to learn via the error back-propagation procedure of the training data Example : 𝑦 = 𝑓 𝑥 8
General regression neural network (2/3) 𝐷 𝑖 2 = 𝑋 − 𝑋 𝑖 𝑛 𝑖=1 𝑦 𝑖 × exp −𝐷 𝑖 2 2𝜎 2 𝑛 𝑖=1 exp 𝑇 × 𝑋 − 𝑋 𝑖 −𝐷 𝑖 2 2𝜎 2 9
General regression neural network (3/3) 10
GRNN-based image inpainting (1/3) 11
GRNN-based image inpainting (2/3) 12
GRNN-based image inpainting (3/3) 13
Parameter settings(1/3) GRNN based inpainting of images enabled us to bypass the difficulty of working with complex mathematical models of PDEs and variational formulations. The only parameter in this approach is to determine σ If there exists a strong edge or an isophote that hits the boundary of the missing area, the value of σ must be small On the other hand, if we do not have much variation over the boundary pixels, we can choose larger value of σ . 14
Parameter settings(2/3) We formulated the following equation to find the optimal spread parameter: 𝜎 = 𝑒 1− 𝜌 255 in which
ρ
is the maximum magnitude of the gradient of the boundary and is defined as: 𝜌 = 𝑚𝑎𝑥 𝐺 𝑥, 𝑦 , 𝑥, 𝑦 ∈ 𝜑 𝑖 and G is the magnitude of the gradient and can be calculated by the following equation: 𝐺 𝑥, 𝑦 = 𝐼 𝑥 𝑥, 𝑦 2 + 𝐼 𝑦 𝑥, 𝑦 2 15
Parameter settings(3/3) And G is the magnitude of the gradient and can be calculated by the following equation: 𝐺 𝑥, 𝑦 = 𝐼 𝑥 𝑥, 𝑦 2 + 𝐼 𝑦 𝑥, 𝑦 2 where 𝐼 𝑥 and 𝐼 𝑦 are the gradients in
x
and
y
directions respectively.
16
Experiments and comparisons (1/2) 17
Experiments and comparisons (2/2) 18
Conclusion GRNN networks are very fast at converging to the optimal regression surfaces using only a few number of data samples The advantages of our algorithm are: (1) it is simple in principle; (2) it is easy to implement; (3) it is qualitatively better; (4) it is computationally efficient 19