An image processing system including at least one processor configured to receive image data captured by a mobile device image sensor. The image data includes images of an inoperative appliance. The processor is further configured to perform image recognition on the image data to identify the inoperative appliance and determine a likely cause of inoperability; retrieve a plurality of sequential instructions for enabling a user to remedy the inoperability; cause the mobile device to sequentially display the plurality of sequential instructions; detect that the inoperative appliance is outside a field of view of the image sensor, based on the image data; suspend display of additional sequential instructions when the inoperative appliance is outside of the field of view; detect when the inoperative appliance returns to the field of view; and resume display of the additional sequential instructions after the inoperative appliance returns to the field of view.