Bare-hand human-computer interaction

Abstract

In this paper, we describe techniques for barehanded interaction between human and computer. Barehanded means that no device and no wires are attached to the user, who controls the computer directly with the movements of his/her hand.Our approach is centered on the needs of the user. We therefore define requirements for real-time barehanded interaction, derived from application scenarios and usability considerations. Based on those requirements a finger-finding and hand-posture recognition algorithm is developed and evaluated.To demonstrate the strength of the algorithm, we build three sample applications. Finger tracking and hand posture recognition are used to paint virtually onto the wall, to control a presentation with hand postures, and to move virtual items on the wall during a brainstorming session. We conclude the paper with user tests, which were conducted to prove the usability of bare-hand human computer interaction.

Template-Based Hand Pose Recognition Using Multiple Cues

“…Hand locations and scale are hypothesized efficiently using cumulative likelihood maps, and the hand pose is estimated by normalized template matching. The system lifts several restrictions which are often present in real-time systems: In contrast to other methods, the system in this paper uses neither background subtraction [6] nor does it rely on binary colour segmentation [17,2,3] or gesturing at a fixed distance to the camera [23]. Finally, the method is efficient enough to detect the hand in each frame independently.…”

Gestures for Interaction between the Software CATIA and the Human via Microsoft Kinect

“…Finding a series of gestures to define an action or task is difficult because in the world exist several ways to say or do a thing, depending on the language and the culture of the people. We can have an infinite number of gestures to interact, but many of them may not be identified or remembered [5][6] [7].…”

“…One important task is to find the bridge in communication between the humans to perform gestures and then, translate these gestures to a Human-Computer communication, so that they can be expressed naturally and can be remembered easily [2][3] [5]. Also these gestures can't confuse the computer or do something that has not referred to do in the development of the tasks.…”

VisHap: augmented reality combining haptics and vision

“…A standard PC, with a stereo camera system and a haptic device, is the minimum requirement. Some of the software implementations are recent research topics [1,3,6,8] and even free to download [2].…”

“…An efficient way to detect the fingertip is to exploit the geometrical property of the finger [3,8]. We use a cylinder with a hemispherical cap to approximate the shape of the finger.…”