When you encounter an image, you'll likely hear something like this: 120922ah86btvi4hb8577w.jpg image, which doesn't help you much. then you press VO-l, then you get something like this: an illustration of ice cream cones and text, Detected Document, Possible Text, JULES DESTROOPER. •q LGlVla. BELGIAN BUTTER WAFFLEs, now that's helpful.
so how do we make the computer read the image description automatically, instead of going through every senseless image name and press VO-l each and every time? there are pages contain mostly images, and it would be very useful if we could just get the description simply by navigating through each of them.