Reduced-Dimensional Capture of High-Dynamic Range Images with Compressive Sensing

Figure 2

The flowchart of the K-SVD algorithm: I_m, (m) = 1, 2, …, (M), is an image in image sequence. All images in image sequence are divided into blocks and pixels in each block are rearranged into a column vector y_i, i = 1, 2, …, N. (N) is the number of vectors generated from the image sequence and (n) is the length of y_i. is a matrix of column vectors y_i. The dictionary is made up of atom vector d_k, where K is the total number of atoms in D^(J) and the superscript (J) is the number of iterations. is the sparse representation of (Y) under dictionary (D) and is made up of row vectors , where the subscript T of indicates that is a row vector and superscript T indicates matrix transpose. The matrix E_k is the error for all the input signal when the (k)th atom is removed. The detail of and SVD decomposition of can be found in [9].