Indian Classical Dance Mudra Classification Using HOG Features and SVM Classifier
نویسنده
چکیده
Received Dec 9, 2016 Revised Jun 17, 2017 Accepted Sep 17, 2017 Digital understanding of Indian classical dance is least studied work, though it has been a part of Indian Culture from around 200BC. This work explores the possibilities of recognizing classical dance mudras in various dance forms in India. The images of hand mudras of various classical dances are collected form the internet and a database is created for this job. Histogram of oriented (HOG) features of hand mudras input the classifier. Support vector machine (SVM) classifies the HOG features into mudras as text messages. The mudra recognition frequency (MRF) is calculated for each mudra using graphical user interface (GUI) developed from the model. Popular feature vectors such as SIFT, SURF, LBP and HAAR are tested against HOG for precision and swiftness. This work helps new learners and dance enthusiastic people to learn and understand dance forms and related information on their mobile devices. Keyword:
منابع مشابه
Classification of Indian Classical Dance Steps using HOG Features
In this paper Histogram Oriented Gradient (HOG) features are extracted to classify the postures in a Indian classical dance video dataset. The aim is to design an automated system that can recognize the steps of Indian classical dance in a video. As a video consists of frames of different actions, so features representing shapes can be used to interpret the dance steps. HOG based features are c...
متن کاملتحلیل ممیز غیرپارامتریک بهبودیافته برای دستهبندی تصاویر ابرطیفی با نمونه آموزشی محدود
Feature extraction performs an important role in improving hyperspectral image classification. Compared with parametric methods, nonparametric feature extraction methods have better performance when classes have no normal distribution. Besides, these methods can extract more features than what parametric feature extraction methods do. Nonparametric feature extraction methods use nonparametric s...
متن کاملMCS HOG Features and SVM Based Handwritten Digit Recognition System
Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of Oriented Gradient (HOG) features and a Support Vector Machine (SVM) based classifier for efficient classification of Handwritten Digits. The HOG based technique is sensitive to the...
متن کاملEpileptic Seizure Detection in EEG signals Using TQWT and SVM-GOA Classifier
Background: Epilepsy is a Brain disorder disease that affects people's quality of life. If it is diagnosed at an early stage, it will not be spread. Electroencephalography (EEG) signals are used to diagnose epileptic seizures. However, this screening system cannot diagnose epileptic seizure states precisely. Nevertheless, with the help of computer-aided diagnosis systems (CADS), neurologists ca...
متن کاملPlant Leaf Recognition and Classification using Zernike Moments (ZM) and Histogram of Oriented Gradients (HOG)
A method using Zernike Moments (ZM) and Histogram of Oriented Gradients (HOG) for classification and recognition of plant leaf images is proposed in this paper. After preprocessing, we compute the shape features of a leaf using Zernike Moments (ZM) and texture features using Histogram of Oriented Gradients (HOG) and then Support Vector Machine (SVM) classifier is used for plant leaf image class...
متن کامل