Heuristic finger detection method based on depth image

A finger detection device comprising:

• a hand connected region acquisition unit configured to receive a user's depth image and acquire a hand connected region from the depth image;
• a central point determination unit configured to calculate the central point of the hand connected region;
• an extremely far point calculation unit configured to calculate a plurality of extremely far points in the hand connected region that have extremum 3D geodesic distances from the central point;
• a finger detection unit configured to detect fingertips and finger regions from the plurality of calculated extremely far points;
• and
• an output unit configured to output fingertip positions and the finger regions;
• wherein hand connected region acquisition unit further configured to:
• detect all connected regions in the user's depth image by an image growing method;
• and
• select a connected region with the smallest depth among the detected connected regions as a hand connected region.

A computer readable non-transitory storage medium, which stores computer readable instructions which, when executed by a computing device, cause the computing device to implement a finger detection method comprising the steps of:

• acquiring a hand connected region from a user's depth image;
• calculating the central point of the hand connected region;
• calculating a plurality of extremely far points in the hand connected region that have extremum 3D geodesic distances from the central point;
• detecting fingertips and finger regions from the plurality of calculated extremely far points;
• and
• outputting fingertip positions and the finger regions;
• wherein the step of acquiring a hand connected region from a user's depth image further comprises the steps of:
• detecting all connected regions in the user's depth image by an image growing method;
• and
• selecting a connected region with the smallest depth among the detected connected regions as a hand connected region.

A finger detection device comprising:

• a memory configured to store computer readable instructions and data;
• and
• a processor coupled to the memory, which is configured to execute the computer readable instructions to implement a finger detection method comprising the steps of:
• acquiring a hand connected region from a user's depth image;
• calculating the central point of the hand connected region;
• calculating a plurality of extremely far points in the hand connected region that have extremum 3D geodesic distances from the central point;
• detecting fingertips and finger regions from the plurality of calculated extremely far points;
• and
• outputting fingertip positions and the finger regions;
• wherein the step of acquiring a hand connected region from a user's depth image further comprises the steps of:
• detecting all connected regions in the user's depth image by an image growing method;
• and
• selecting a connected region with the smallest depth among the detected connected regions as a hand connected region.