In this third application, we will go over an example where we'll develop an autoencoder model to remove certain artificially created marks on various pictures. We will use 25 images containing a black line across the picture. The code for reading the image files and carrying out the related processing is as follows:

# Reading images and image processing
setwd("~/Desktop/peoplex")
temp = list.files(pattern="*.jpeg")
mypic <- list()
for (i in 1:length(temp)) {mypic[[i]] <- readImage(temp[i])}
for (i in 1:length(temp)) {mypic[[i]] <- resize(mypic[[i]], 128, 128)}
for (i in 1:length(temp)) {dim(mypic[[i]]) <- c(128, 128,3)}

In the preceding code, we read images with .jpeg extensions from the peoplex folder and resize these images so that they have a height and width of 128 x 128. We also update the dimensions to 128 x 128 x 3 since all the images are color images.