Image database for tiny hand gesture recognition

Description

The dataset is composed by RGB videos containing 7 different hand gestures collected from 40 people. Every instantiation of one gesture is composed by about 1400 color frames, and the gestures are performed in different locations in the image. For each image, human face and human body are the main parts of the image, while the hand gesture to be classified only occupies the 10% of pixels the whole image.

Gestures

Fist

Pointer

Fist

Pointer

Fist

Pointer

Palm

Example of users and backgrouds

Data

[Link]

Contact

Ana I. Maqueda: http://gti.ssr.upm.es/ana-maqueda

Carlos R. del Blanco Adán: http://gti.ssr.upm.es/carlos-r-del-blanco