I was not able to extract the raw pixel information from the PNG images directly using binary pattern matching.

However, I found this library which solved the problem and gave me the pixel information from the PNG image.

I resized and converted the image to monochrome using Image Magick and I was then able to load the image in the required MNIST format by doing the following…

defmodule ImageParser do

  # Load pixel values from a png image
  # Uses the Pixels library to read pixel data from PNG image
  def load_img(path) do
    {:ok, %Pixels{data: data}} = Pixels.read_file(path)
    data
  end

  # Use ImageMagick to resize the image to 28 * 28
  # Also, converts image to monochrome(black and white)
  def resize(input_file_path) do
    System.cmd("convert", [
      input_file_path,
      "-resize",
      "28x28!",
      "-monochrome",
      "/tmp/output.png"
    ])
  end

  # Take image pixel data and read it as dx3-ubyte which is the MNIST data set format
  # Return a tensor created from the image data
  def parse_and_make_tensor(image_data) do
    image_data
    |> :binary.bin_to_list()                     # Convert Image binray to list
    |> Enum.chunk_every(4)                       # Chunk every 4 values to get a singal RGBA pixel
    |> Enum.map(fn                               # Since we are processing a back and white image there
      [0, 0, 0, 255] -> 0                        # can be only two pixels values rgba(0, 0, 0, 255) -> Black and rgba(255,255, 255, 255) -> White
      [255, 255, 255, 255] -> 255                # We map Black pixels to a single value 0 and white pixels to a single value 255
    end)
    |> :binary.list_to_bin()                     # Convert list back to binary
    |> Nx.from_binary({:u, 8})                   # Create a Nx tensor
  end
end