Techniques for determining sign language gesture partially shown in image(s)

Abstract

In one aspect, a device may include a processor and storage accessible to the processor. The storage may include instructions executable by the processor to receive at least one image that indicates a first gesture being made by a person using a hand-based sign language, with at least part of the first gesture extending out of the image frame of the image. The instructions may then be executable to provide the image to a gesture classifier and to receive plural candidate first text words for the first gesture from the gesture classifier. The instructions may then be executable to use at least a second text word correlated to a second gesture to select one of the candidate first text words, combine the second text word with the selected first text word to establish a text string, and provide the text string to an apparatus different from the device.