Fuzzy image matching for posture recognition in ballet dance

Abstract

This work aims at designing a fuzzy matching algorithm that would automatically recognize an unknown ballet posture from seventeen fundamental ballet dance primitives. A novel and simple 7-stage system is proposed to achieve the desired objective. Minimized skeletons of the dance postures are generated after performing skin color segmentation on them. Straight line approximation on the minimized skeletons with the help of chain code and sampling generate their equivalent stick figure diagrams. Significant straight lines from the stick figure diagrams are considered, their fuzzy membership with respect to the 4 quadrants are evaluated. Finally with the help of the evaluated data, a fuzzy T-norm operator determines the proximity of a generated dance posture with the seventeen fundamental dance primitives.

Topomorphological approach to automatic posture recognition in ballet dance

“…In this proposed work, we modify the line integral plots by rejecting leading and trailing zeroes and thus the problem of centralising does not appear. Also the accuracy of the proposed work is better than those of [9,10]. This proposed work deals with static posture recognition and thus cannot be compared with dynamic gesture recognition techniques like [11,12].…”

“…if we do not group the postures based on the Euler number and without making any modifications on the line integral plots like discarding leading and trailing zeroes), then the line integral plots generated can also be treated as features. Moreover, these features can be used to examine the performance of the proposed work with a comparative framework which includes support vector machine (SVM) classifier [20], k-nearest neighbour (kNN) classification [21], Levenberg-Marquardt algorithm induced neural network (LMA-NN) [22], fuzzy C means clustering (FCM) [23] and ensemble decision tree (EDT) [24], algorithm in [9,10]. The parameters of all the other competing classifiers are tuned by noting the best performances after experimental trials.…”

“…Two similar approaches have been proposed in [9,10]. Here to approximate the curved lines of the skeletons by straight lines using chain codes.…”

Dance Gesture Recognition: A Survey

“…Resultant boundary of texture-based segmentation contains topological error like hole. To fill up these holes different filling operations, Sobel edge detection and many others techniques are used [22]. …”

“…Their work is carried with only eleven co-ordinates out of twenty different joints of skeleton,(iii)Bali Traditional Dance [9], which works on probabilistic grammar-based classifier, (iv) Ballet Dance [22] where multiple stage system is proposed to recognize the different dance posture, (v) Kazakh Traditional Dance [26] is basically concerned with the head gestures and many others. The details of these gesture recognition methods are described in the later part of this survey.…”