4.1. Image interpolation in the spatial domain

For any two images A and B in the dataset, we can generate a new image by finding a weighted average C. Specifically, the pixel at location ð Þ i; j in C can be obtained by

$$\mathcal{L}(i,j) = \min[A(i,j), B(i,j)] + k \times \{ \max[A(i,j), B(i,j)] - \min[A(i,j), B(i,j)] \},\tag{1}$$

where k is a weight ranging between 0 and 1. It can be seen that C ið Þ¼ ; j min½ � A ið Þ ; j ; B ið Þ ; j for k = 0; C ið Þ¼ ; j max½ � A ið Þ ; j ; B ið Þ ; j for k = 1. By varying the k values, for example, from 0 to 1 with a step size of 0.1, we can create 11 different images for any two input images. Assume the number of images in the dataset to be augmented is N, we can generate <sup>11</sup>N Nð Þ �<sup>1</sup> <sup>2</sup> images, which can lead to a much enlarged dataset.
