Automated Image Processing Software Development

Software experience:

OpenCV (https://opencv.org/)
Imagemagick (http://www.imagemagick.org/script/index.php)

I am looking for a merge of the two above software’s to help me automate a simple process. The software will run on a stand alone PC. It should be Windows compatible.

I wish to remove the background from images that individuals send me of their faces. Individuals send me their pictures (.jpg / .png) and I convert them into face masks. I print them on A4 using the following dimensions: 2480 x 3508 pixels. – I only want to print the face and hair (head hair/beard). I need the face and eyes automatically recognised and the background removed around the head (and also any of the body that is not the face). I assume that the background removal should be done using OpenCV software. Once the background is removed, it should automatically smooth the edges around the face.
I wish for there to be an interface similar to this:

https://clippingmagic.com/images/36472551/edit/3tpgv4m1tlsjk4gc190cjjdcfbm5jbv63hv6jt0jd5d8ii8djl5n

The user will be able to add and remove elements of the picture/background and manually change the position of the image to fit on certain eye hole templates. Certain functions such as angling the image and resizing it easily need to be accessible.

The eyes need to be recognised so the image can be automatically placed over one of 8 different options of present "eye hole" areas. The eye holes need to be a certain distance a part so when you wear the mask - you can see out of it. Here is an example of the eye hole template (please note that number 1 eye hole is where the pupils currently are):

www.worldsafar.co.uk/FMsoftwaredev/TEMPLATE_3---Copy.png

If the face does not fit into these eye hole areas automatically due to the head not fitting within the print dimensions - it needs to automatically size the face to eye hole 1 so it's the correct distance a part and prompt the user to place the image in the best position while categorising it as a “EHU” output file name (see below).

Depending on which eye hole the face matches up to, will determine the output file name given to it. For example - if it fitted to eye hole 1 - the output name would be EH1_XAMOUNT_USERNAME or eyehole 2 - EH2_X10_USERNAME - if it doesn't fit to any of the eyeholes as discussed above the name will be EHU_X200_USERNAME

I would like all files that are able to match to a file name to output in 2 file types – PNG and PDF (multiples will only be applied to PDF – see later).

Each image will also require the file name to be imposed at the bottom of the image.
There will also be a second file produced for each image - which is a backing template. There are 9 different backing templates depending on which eye hole the image matches up to. The filename should also be on this backing template also.

Here is a an example of a backing template:

www.worldsafar.co.uk/FMsoftwaredev/TEMPLATE_02.png


The software should automatically have a “hot folder” assigned to it. If you drop files into this folder, the software should automatically recognise that they’re in there and automatically load them. Once you’ve completed and verified an image, it should move onto the next one immediately. Moving the completed images into a “completed” folder. It should also have the option to reject an image and a reject folder.
The software must also have a regular expression look up to the file name that is input to it. It must be able to read the file name and output multiples of it based on a section which will have a number. Rules should be easily be created based on this. Generally they will go like this EH1_X10_USERNAME (which will mean X10 – times by 10) – these can be one file generated. So with 10 faces, and 10 backing templates. In order of – face, backing template, face, backing template etc.

The multiples of this will only be applied to the PDF’s. I will not require the PNG to be multiplied.

It is important that the development of this program is robust. This will be a stand alone project and should not require any further development once completed.


FURTHER FUCNTIONS:

Should have the option not to edit the image at all and just output / multiply.