Hand gesture recognition using a dedicated geometric descriptor

Abstract

A high proportion of hospital-acquired diseases are transmitted nowadays during surgery despite existing asepsis preservation measures. These are quite drastic, prohibiting surgeons from interacting directly with non-sterile equipment. Indirect control is presently achieved through an assistant or a nurse. Gesture-based Human-Computer Interfaces constitue a promising approach for giving direct control over such equipment to surgeons. This paper introduces a novel hand descriptor based on measurements extracted from hand contour convex and concave extrema. Using a 9750-picture database created especially for this purpose, it is compared with three state-ofthe-art description methods, namely Hu moments, and both SIFT and HOG features. Effects of large amounts of hand rotation are also studied on each rotation axis independently. Obtained results give HOG features as best in recognizing hands from our database, closely followed by the proposed descriptor. Performance comparison when facing rotated hands shows our descriptor as the most robust to rotations, outperforming the other descriptors by a wide margin.

A 3D Fingertips Detecting and Tracking Algorithm based on the Sliding Window

“…Since the background and shapes of hand are diverse, it is difficult to differentiate hands from the complicated environments. Thus it is not effective to use the template matching [9] or geometric methods [10]. As the human skin has the unique characteristic in special color space, we make use of the ellipse color model [11] to detect the hands in the YC r C b color space.…”

Design Process of a New Lighting Robotic Arm for Operating Room

“…As depicted in Fig. 1 (left part), that mechanisms are mainly composed by a cradle (1), a hoisting arm (2) and a horizontal arm (3), respectively. In particular, the cradle is composed of two parts allowing to orientate the dome.…”

“…Cost, ergonomic and acceptability of technical solutions are criteria provided by the industrial partner and are considered in the design process. The gestures recognition has been developed in PRISME laboratory [1][2][3]. In this paper we present the design process followed to obtain the final robotic solution that complies with the medical and industrial specifications.…”