Multi-frame image super-resolution reconstruction via low-rank fusion combined with sparse coding
这篇文章看起来和2月初读的一篇关于图像去噪是自相矛盾的,这篇文章可以方法成立的条件是,HR和LR图片用字典表示时候的协方差系数矩阵是类似的,也就是那个 在两种情况下是一样的。在求解中也应用到了从三个方向特征提取的技巧,还有K-SVD方法。
(思考:那么在这里的特征提取是否可以接入神经网络,模型自己训练,自己提取特征呢?)这里面提取特征是在第二部,是为了提取出特征之后这些特征向量组成训练集,再用K-SVD方法提取出字典。
之前的文章中,两种情况下的 是有偏差的,之后在模型优化中,专门加入了一项,表示两个协方差的距离,接着进行一系列的估计,迭代,然后求解。
According to the number of input LR images, image SR can be divided into single -frame and multi - frame.
Single-frame SR refers to restore a HR image from a LR image, and multi-frame SR means to recover a HR image from LR image sequence.
2. Low rank fusion and sparse coding
2.1 Low rank fusion
A data matrix
contains structural information as well as noise. Then we can decompose M as
M = L + S
where L is low-rank matrix(contains the internal structure information which are linearly related.)
S is sparse (noise is sparse)
RPCA(robust principle component analysis) method model used to optimize above problem:
is a balance parameter.
(1) is a non-convex problem and it can be replaced by (2)
Augmented Lagrange Multiplier (ALM) algorithm is usually used to solve (2)
Supposing there are N frame registered images, then they are converted into a column vector and stored in a matrix by column. Now the matrix M={
} has low-rank characteristics.
Next we decompose the matrix by low-rank and sparse decomposition.
Finally the decomposed low-rank part L = {
} is average fused to get the final fusion LR image L∗ =(
)/N,
2.2 Sparse coding
After down sampling S and fuzzy B, HR image X is degenerated into LR image Y:
Where SB = L, Y = LX.
If y is an image patch taken from Y ,x is an image patch taken from X which is in the same location with y.
The sparse representation model can be represented as following:
(K>n) is a HR over-complete dictionary.
According to (3)(4), so y can be expressed as following:
Where
(K>m) is a LR over-complete dictionary.
So it can be clarified that HR and LR image patches have the same sparse representation coefficient. (
)
Based on a pair of HR and LR dictionaries {
}, we are able to rebuild the correspond- ing HR image patch as long as we acquire sparse representation coefficient of the LR image patch.
3. Multi-frame image SR via low-rank fusion combines with sparse coding
3.1 method
The Multi-frame SR using low-rank fusion combines with sparse coding includes three steps: image registration and low-rank fusion, {
} dictionary training and SR reconstruction, as shown in Fig. 3.
In image registration and low-rank fusion phase, SURF and RANSAC algorithm are used to image registration. Then registered images are decomposed into the low-rank images and the sparse images, and the low-rank images are fused into a LR image.
In {
} dictionary training phase, patch haar wavelet transform is used to get image patches characteristic vectors, and characteristic vectors constitute the joint training set. K-SVD algorithm is applied to train joint training set to obtain the {
}.
In SR reconstruction phase, after computing sparse representation coefficient
of LR patch, the HR patch can be obtained from the coefficient
multiplied by the HR dictionary
.
The END of Method of this paper.