Classical Dance Form Research Articles

MCM-Vb\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_b$$\\end{document}F: dance hand gestures recognition with vision based features

To digitize and preserve the cultural heritage in the form of Indian classical dance become apparent area of research. Sattriya classical dance of North-East India (Assam) is one of the eight Indian classical dance forms that requires immediate preservation. Sattriya classical dance consists of 29 Asamyukta hastas (single-hand gestures) and 14 Samyukta hastas (double-hand gestures). Moreover, the foundation of Samyukta hasta depends on understanding Asamyukta hasta. Therefore, the paper aims to classify single-hand gestures of Sattriya classical dance only. Although, a solution based on two level classification method to classify the Sattriya classical dance is available in recent literature, but it requires a trial and error method to select the optimized features. Since, Asamyukta hastas can appear closely similar to each other and therefore misclassification chances are very high. Thus, accuracy rate obtained for the two level classification method was only 75.45%. So, to address this issues in this paper, a Multilevel Classification Model with Vision based Features (MCM-Vb\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_b$$\\end{document}F) has been proposed to classify the Asamyukta hastas of Sattriya classical dance. This model uses two types of feature matching, viz., high-level feature matching and low-level feature matching. To extract the high-level features and low-level features different algorithm has been proposed. In this model, features are automatically selected. This proposed MCM-Vb\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_b$$\\end{document}F model is also tested on Asamyukta hasta mudras of Bharatanatyam classical dance of South India (Tamil Nadu). This model obtain an accuracy 94.12%, 87.14% for Sattriya classical dance Single-Hand Gestures (SSHG) dataset and Bharatnatyam classical dance Single-Hand Gestures (BHSG) dataset respectively. This paper also provides the comparative study of the proposed model MCM-Vb\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$V_b$$\\end{document}F with traditional bench-mark classifier model such as Naive Bayes, Decision Tree and Support Vector Classifier (SVM) etc.

Comparison of anthropometric measurements related to the medial longitudinal arch of feet between non-dancers and Bharatnatyam dancers- an observational study

BackgroundBharatnatyam is an Indian classical dance form that involves rhythmic barefoot tapping at varying speeds. The intense impact forces generated during this dance can result in biochemical alterations in the feet, potentially causing injuries to ligaments, tendons, and fascia. This can lead to changes in the structure of the foot over time. Therefore, this study was conducted to compare anthropometric measurements related to the medial longitudinal arch of the foot in non-dancer, mid-stage, and last stage Bharatnatyam dancers. MethodsThe study was conducted on 192 participants. They were divided into three groups: 1) Non dancers 2) Mid-stage Bharatnatyam dancers, and 3) Last-stage Bharatnatyam dancers. Each group consisted of 64 participants each. Various measurements were taken on both the right and left foot using a wooden platform, foot image, and footprint. Later the results were analyzed statistically. ResultsOn comparing the parameters in non-dancers and mid-stage Bharatnatyam dancers it was found that all the parameters were found to be significant except right and left arch index. On comparing the parameters of mid-stage and last-stage Bharatnatyam dancers, it was found that none of the parameters showed significant value. On comparing the non-dancers and last-stage Bharatnatyam dancers, it was found that except right and left arch index all the parameters were found to be significant. ConclusionFrom the results of the present study, it can be concluded that there were significant changes in the arches of the foot between the non-dancers and mid-stage and last-stage Bharatnatyam dancers.

Understanding similarities and exploring possibilities of using somatic dance/movement aspects of Odissi dance for social, cognitive and emotional development in population with autism spectrum disorder

Dance allows for expressions of various emotions and interactions. It can be used for entertainment and exercising, as well as for movement therapy, improving health and wellness, and promoting relaxation. It has been known to enhance mindfulness, well-being, healing of body and mind, etc. The key contributions of this work are as follows: (1) present an overview of Odissi dance elements; (2) aggregate certain studies that explore the relevance of somatic dance/movement therapy for neurodegenerative disorders such as autism spectrum disorders (ASDs); (3) exploring the many similarities between Odissi dance, an Indian classical dance (ICD) form, and somatic dance/movements; and (4) study the implication of using the Odissi dance form as a dance/movement therapy as an alternative rehabilitation tool for a population with neurocognitive disorders such as ASD. ICDs such as Odissi dance practices and somatic dance/movements have been found to have numerous similarities. There are many characteristics of the Odissi dance form that are relatable to somatic dance/movements. Somatic dance/movement praxis generically includes body, action, space, time and energy. These practices are a customary part of Odissi dance as well. The Odissi dance form also allows an in-depth examination of the human body, feelings and flow through music, beat tempo and lyrics. These practices help develop an awareness of the body, its connection and its movements. The fundamental elements of somatic dance/movements, such as mindfulness, breath, sensing, connectivity, initiation, rhythm, movement patterns, temperament depiction and mirroring, are also prevalent in Odissi dance. The various aspects of somatic dance/movement and Odissi dance are explored, and their similarities are investigated in this work. This study also explores having Odissi dance as an alternative rehabilitation therapy form for the population suffering from ASD conditions. Twenty-seven children suffering from some degree of ASDs, aged between 4 and 14 years, for six months, underwent regular Odissi dance training. The participants were taught Odissi’s basics and trained in Bhumi Pranam, Guru Pranam, Mangalacharan and the initials of Sthayee and Battu. Certified teachers and therapists were involved in teaching the participants. Interactions with participants and parents/guardians presented an intuition of the usefulness of regular Odissi dance practice. Feedback was aggregated from subjective questionnaires. These feedbacks indicated increased general health, including physical well-being, cognitive enhancement and sensory-motor coordination. Almost all also reported betterment in social conditions and certain presented clinical conditions.

Soulful Rhythm, Dancing Bodies: Spirituality, Pain Tolerance, and the Risk of Lower Extremity Musculoskeletal Injuries Among Classical Kathak Dancers of India

Background: Dance and dancers reflect happiness, sadness, passion, anger, and all other emotions as every single dancing movement carries a significant signal that goes beyond words. Kathak, an Indian classical dance form, requires a divine balance between the soul and the physical body. This balance allows for a high pain tolerance of the dancers, but the spiritual nature of this dance form also generates ignorance and disinterest in their health seeking behavior towards injuries. Objectives: This comprehensive narrative review is aimed at exploring and examining the prevalence of lower extremity musculoskeletal injuries among Kathak dancers and proposes management strategies for their prevention and treatment. Methods: This review is based on a search of relevant articles, research papers, books and book chapters conducted across a wide array of online sources, utilizing the search engines like PubMed, Medline, CrossRef; etc. Considering the inclusion criterion, the review process included three stages: initial assessment of papers through title and abstract review, a detailed examination of relevant items, and systematic compilation of pertinent information into a categorized table under topical headings. Results: The review finds that the majority of injuries were reported in the foot and ankle region of dancers practicing Kathak. Conclusion: There is a need to develop supplementary exercise training programs and also spread awareness among dancers regarding their physical health and seeking medical care in time to delay/prevent lower extremity injuries.

MANIPURI RAAS LEELA: THE REMARKABLE MANIPURI CLASSICAL DANCE

Manipur is renowned for its cultural heritage, particularly in dance i.e., Manipuri Raas Leela, Pung Cholom, Lai Haraoba, Khamba Thoibi etc. Manipuri Raas Leela, the classical dance form is deeply rooted in the Vaishnavite tradition, depicting the love story of Shrimati Radhika and Lord Shri Krishna. It combines graceful movements, lyrical music and expressive gestures. Pung Cholom knew as the drum dance, this performance features dancers playing pung while performing acrobatic and vigorous movements. It is often performed during religious and cultural festivals. Lai Haraoba ia an ancient ritualistic dance celebrating the creation of the universe. It involves intricate movements and is performed in honor of traditional deities called Umang Lai. Khamba Thoibi, a popular folk dance depicting the legendary love story of Khamba and Thoibi, characters from the ancient Moirang folklore. It involves synchronized movements and is often performed during the Lai Haraoba festival. These dance forms reflect the rich cultural and spiritual traditions of Manipur, blending storytelling, music and intricate choreography. This paper is showcase about the Raas Leela of Manipur.

Non-Verbal Communication in Indian Classical Dance Forms

This study delves into the intricate world of non-verbal communication within the rich mosaics of the Indian classical dance forms. The statement quoted by Noam Chomsky, “Language is not an inborn quality, it is creative and acquired”. The objective of this research is to analyse and focus on the need for humans to communicate, that too using non-verbal communication. Dance will not be relegated to simply a performance genre but will be treated as an essential ingredient of life. The focus would be on identifying the non-verbal elements of the dance that would communicate not just the stories but also social messages if needed through the gestures and other elements in Indian Classical Dance Forms. For this analysis, the researcher has considered, Bharatanatyam, Kuchipudi, Mohiniyattam, and Kathakali, the dance forms that trace their origin to the southern states of India namely, Tamil Nadu, Andhra Pradesh, and Kerala. The research employs a multidisciplinary approach, combining elements of anthropology and performing arts to unravel the communicative nuances in the intricate hand gestures, facial expressions, body postures, and rhythmic footwork inherent in Indian classical dances. By examining the symbolism and cultural significance of gestures (mudras), the utilization of facial expressions (abhinaya), and the synchronization of movements with musical rhythms, the research seeks to unveil the deeper layers of communication that lie beneath the surface of these mesmerizing performances.

From Tradition to Transformation: Bharatanatyam Explored through Feminist and Psychological Contexts

This study explores the evolution and contemporary significance of Bharatanatyam, an Indian classical dance form. It examines the evolution of the dance form, focusing on the portrayal of stories, emotions, and characters. The research also reimagines the Ashta-Nayikas, the eight main female archetypes in classical dance, through the lens of contemporary psychology. The study uses qualitative data analysis, including media studies, historical texts, and in-depth interviews, to reveal the dynamic interaction between modernity and tradition. The study highlights the dance form’s innate resilience and the need for dance artists to develop coping mechanisms to navigate the intricacies of tradition and modernity.

An Indian classical dance form, Kathak in maintaining handgrip strength symmetry and reducing the risk of hypertension.

The present paper aimed to study handgrip strength (HGS) asymmetry and its association with hypertension in a sample of Kathak dancers and non-dancers of North India. Data on HGS and blood pressure were collected from 206 Kathak dancers and 235 age-matched controls, using standardized protocols. Pearson correlation coefficients assessed the association between HGS and hypertension, and binary logistic regression identified the risk of developing hypertension. HGS asymmetry was higher among non-dancers. In Kathak dancers, systolic blood pressure (SBP) was positively correlated with HGS and negatively correlated with HGS asymmetry whereas diastolic blood pressure (DBP) was negatively correlated with both HGS and HGS asymmetry. Dancers with high HGS, have significantly reduced risk of developing hypertension. Non-dancers with HGS asymmetry were 1.8 times more likely to report hypertension, relative to dancers. Kathak may be used as an alternative method for maintaining HGS symmetry and reducing the risk of developing hypertension.

Impact Of Mind Sound Resonance Technique On Work-Related Flow Inventory And Sleep Quality Among Enthusiast Kathak Dancers From Different Professional Backgrounds

BackgroundKathak is one of the most popular Indian classical dance forms. Working professionals out of passion enjoy kathak dance but due to work engagements and reduced sleep quality, discontinue the practice of Kathak. Mind Sound Resonance Technique has been proven to improve sleep quality. Investigation among practitioners of Khatak is low and the literature survey supports the basis for this study. The present research aims to explore the influence of MSRT on the work-life inventory and sleep quality among Kathak dancers who are working professionals.ObjectivesThe objective of the study is to assess the potential benefits of enhancing work enjoyment and sleep quality of Kathak dancers from different professional backgrounds through applications of Mind Sound Resonance Techniques.MethodsA single group pre-post study on (N=29) working professionals trained in Kathak were conveniently selected for the study. MSRT was imparted to all the participants for 20 minutes, per two times for 12 weeks. The pre and post-assessments were done on work-life inventory, job satisfaction, absorption, work enjoyment, and intrinsic work motivation using the Work-Related Flow Inventory (WOLF) and sleep quality using the Pittsburgh Sleep Quality Index.ResultsCronbach alpha measuring the reliability score of WOLF was (α = 0.8). Within-group analysis the total score of work-life balance and sleep quality was found to be statistically significant from pre- to post (p<.001).ConclusionThe results indicate improvement in various domains of work-related flow inventory and sleep quality. Thus, rejecting the null hypothesis. We conclude that the Yogic relaxation technique employed in this study attunes the body-mind system to be relaxed and practitioners can bring a balance in their work-life and pursue their interests and passion to lead a fulfilled life.

Gesture Identification Model In Traditional Indian Performing Arts By Employing Image Processing Techniques

Classical dance forms are an integral part of the Indian culture and heritage. Kathakali is an Indian classical dance composed of complex hand gestures, body moments, facial expressions and background music. Kathakali mudras are difficult to understand common peoples. There are 24 classes of hand gestures. The images of hand mudras of kathakali dance are collected from the dataset. The proposed work explores the possibilities of recognizing classical dance mudras in kathakali dance forms in india. This system has achieved an accuracy of 84% with Convolutional Neural Network for classifying the mudras.

The Crossover: Integrating Indian Sign Language with the Mudras in an Indian Classical Dance Performance Creation

Indian classical dance uses a variety of non-verbal communication devices, with gestures called hasta or mudra being one of the most ancient sign languages powerful to transmit the meaning of the lyrics through dance. The classical dance forms of Kerala have an elaborate scheme of gestures drawn from the ancient text on aesthetic sign language, called Hastalakṣanadīpika, inspired by the Vedic, Nāṭya and Tantric traditions. The following is an attempt to document a performance-oriented, socially inclusive effort that makes Indian traditional dance performance discernible to the Deaf and Hard of Hearing (DHH) community, a disparate group that is hardly considered as a spectator during performance creation by mainstream Indian classical dancers. The Indian Sign Language (ISL) of individuals with hearing impairments is elaborate, yet is rarely used as a gestural language along with other aesthetic gestural sign languages to disseminate a narrative in a work of art. In her role as both creator and performer, Methil Devika creates work in Mohiniyāṭṭam, a graceful dance form of Kerala, integrating the sign language of those with hearing impairments along with the gestural language prescribed in the ancient treatise Hastalakṣanadīpika. She applies it strategically in her work of art, as an interlinking tool between the art and the audience. In the first few moments, “all walls came crumbling down,” something the performer quotes in the visual documentation of the work. Any separation between the hearing impaired and the artiste, as well as the spectators, become inconsequential. The performance and the presentation have been video documented in a film called The Crossover, and the following is an attempt to describe the creative process.

POEM IN MOTION: A UNIQUE BLEND OF EAST AND WEST IN SANDHYA RAJU’S PERFORMANCE POETRY OF MAYA ANGELOU’S POEM ‘PHENOMENAL WOMAN’

Dance is an ancient, universal art form that stirs the souls of the performer as well as the admirers. Dance has the power to heal, nourish, teach, and spread joy and peace. In India, a multicultural and multilingual country, innumerable folk, and classical dance forms have flourished and continue to be practised across villages, towns, and cities. Religious festivals, cultural gatherings, social movements, and youth programmes are incomplete without the rhythm and beauty of music and dance. On Feb 2, 2022, the eminent Kuchipudi danseuse Sandhya Raju launched a terpsichorean rendition of the famous poem ‘Phenomenal Woman’ written by the American poet and activist Maya Angelou and published in 1978, as a tribute to the former’s mother on her birthday. Raju, with her co-dancers from the Aayana Dance Company, made a creative interpretation of the poet’s powerful words, while adding a verse of her own which in turn emphasised the concepts of inner strength of a woman and the depth of mother-daughter bonding. The choreography largely borrows from Kuchipudi, a dance form with its origin in an eponymous village in Andhra Pradesh and founded in the classical Sanskrit treatise Natya Sastra. Angelou’s emphatic paean to the confidence and inner beauty of the woman fuses with the Indian performance art form to weave a mesmerising visual-aural experience to the viewer, bringing in an East-West blend that surpasses the boundaries of language, culture, and race.

La Bayadère’s Nikiya vs. the Indian Hereditary Dancing Caste

Marius Petipa’s 1877 La Bayadère, inspired by F. Taglioni’s Le Dieu et La Bayadère as well as the opera Les Bayadères, presents the story of Indian temple dancer Nikiya and her navigation of a love triangle, ending in murder and tragedy. The character of Nikiya was inspired by Indian Bharatanatyam dancers, also known as temple dancers or Devadasis. Europe's primary exposure to this classical dance form occurred in 1838, when a troupe of “Devadasis” visited Paris on a tour of Europe, leading to several choreographers' Western adaptations in ballet. France, in particular, 's fascination with Indian culture can be correlated with France's loss of Indian territory to Great Britain in the previous century. However, most of Europe indulged in the exotic Indian "other." But Western recreations of Indian culture all too often misconstrued reality with a fantasized Oriental world. How does Nikiya's character contrast from the authentic Bharatnatyam dancers that inspired her creation?Nikiya's costuming, choreography, casting, and pieces of her plotline stray from the Indian culture and temple dancers she derives from. I use archival footage of the Bolshoi Ballet's 2013 performance of La Bayadère as well as footage of Bharatanatyam dance from Tanjore Balasaraswati's form, which upholds the traditions of the dance style. In addition, I use historical recounts covering Marius Petipa, the Devadasi European tour of 1938, Bharatanatyam dance, colonialism in India, and Indian-influenced ballets. I review Marius Petipa's diary entries as a primary source in my research. Ultimately, I argue that the only way for Western audiences to appreciate Indian temple dance was through the creation of the Westernized Nikiya.

SATTRIYA DANCE: AN AESTHETICAL OUTLOOK

Aesthetic is the pursuits of one’s individual mind. The theory or sense of beauty is always in connotation with art appreciation or criticism and is cultivated in the responsive spectators. The aesthetic experience evolve among the sahridaya and varies from person to person depending upon the perception of beauty. Indian Classical Dances are sacred art forms associated with the union of individual soul with the Absolute. They imbibe the spiritual values. Sattriya dance, one of the classical dance form from Assam, created by the great saint Sankaradeva in the 15th -16th century was a product of neo-vaishnavite movement. This form carrying the legacy of living tradition till today is performed in the Sattra precinct as a ritual service to appease the almighty while simultaneously seen performing on stage to appease the audience. This research paper is an attempt to assess the aesthetic qualities of Sattriya dance and to evaluate the aesthetic experience that arise out of the dance form in the minds of the spectators. The paper will be based on secondary sources comprising magazines, books, journals and internet content.

Generative adversarial network based data augmentation and quantum based convolution neural network for the classification of Indian classical dance forms

The study addresses the challenges of human action recognition and analysis in computer vision, with a focus on classifying Indian dance forms. The complexity of these dance styles, including variations in body postures and hand gestures, makes classification difficult. Deep learning models require large datasets for good performance, so standard data augmentation techniques are used to increase model generalizability. The study proposes the Indian Classical Dance Generative Adversarial Network (ICD-GAN) for augmentation and the quantum-based Convolutional Neural Network (QCNN) for classification. The research consists of three phases: traditional augmentation, GAN-based augmentation, and a combination of both. The proposed QCNN is introduced to reduce computational time. Different GAN variants DC-GAN, CGAN, MFCGAN are employed for augmentation, while transfer learning-based CNN models VGG-16, VGG-19, MobileNet-v2, ResNet-50, and new QCNN are implemented for classification. The study demonstrates that GAN-based augmentation outperforms traditional methods, and QCNN reduces computational complexity while improving prediction accuracy. The proposed method achieves a precision rate of 98.7% as validated through qualitative and quantitative analysis. It provides a more effective and efficient approach compared to existing methods for Indian dance form classification.

Approaches to Teaching a Bharatanatyam Class for Adults

ABSTRACTIn the independent sector, Bharatanatyam, an Indian classical dance form, is predominantly taught to children and young adults. This article follows my journey as an educator developing a Bharatanatyam class for adults. What would a class designed specifically for adults look like? I share the teaching strategies I employed to deliver the classes effectively online. I take a participatory approach to teaching the classes and, in doing so, widen the scope of teaching Bharatanatyam within the independent sector.

Novel Video Benchmark Dataset Generation and Real-Time Recognition of Symbolic Hand Gestures in Indian Dance Applying Deep Learning Techniques

A computational approach towards promoting, preservation, and dissemination of knowledge in the domain of cultural heritage, is one of the research areas that has a wide scope. There has been a seismic shift in the way many sectors in society have adapted themselves to the pandemic situation, be it healthcare, food, education, diplomacy, and performing arts. Virtual learning and performing have become the need of the hour in the field of performing arts as well. The objective of this work is threefold; first, this creates benchmark datasets to be shared to make a beneficial impact and for a meaningful engagement by capturing, recognising, and classifying the multimedia content for hastamudras (hand poses) in Bharatanatyam, an Indian classical dance form, which plays a significant role in the conservation of intangible cultural heritage, second, as tutoring system to aspiring learners and third, to build video recommendation systems to promote art as a tool for building an international relationship and further elevate the significance of soft-power through performing arts. This article proposes applying the deep-learning techniques of CNNs as a critical technology to recognise the correct mudra. Experimental results on our challenging mudra dataset through the MobileNet architecture show 85%–95% accuracy in real-time, which outperforms the Sebastien-Marcel dataset. The time taken to process an image is 0.172 seconds, and the result is significant considering that the images are dynamic. This work proves the accuracy of the proposed method, which significantly outperforms another CNN-based Inception v3 model.

Assessment of Foot Deviations and Associated Foot Injuries and its Effect on Foot Functional Activity among Amateur Adolescent Female Kathak Dancers in Selected Dance Schools in Bengaluru

Background & purpose: Kathak is a north Indian classical dance form that requires fast rhythmically sophisticatedfootwork and fast turns, which puts the dancers at risk of foot injuries. Any foot deviations or reduced foot functionare associated with an increased risk of a foot injury. This study aims to assess foot deviations and related footinjuries and their effect on functional activity and create awareness among kathak dancers about foot position andits risk factor for injury. Methods: This study included 100 recruited subjects based on the inclusion and exclusioncriteria. Demographic data and other variables were collected and recorded, and measures like foot posture andfunction indexes were used.Results: The foot posture index mean and SD of the left feet for the subjects recruited in the present study were1.83 and 1.43 and of the right feet were 1.89 and 1.54 respectively. The overall foot functional index score mean andSD, for the subjects recruited in the present study were 9.76 and 10.39.Conclusion: The present study concluded by stating that the foot posture index was normal and didn’t haverestrictions on foot usage while performing the kathak dance form. Whereas with the foot function index, it wasobserved that the pain experienced by subjects was severe which restricted their activity pattern and hinderedtheir dance performance.

THE SIGNIFICANCE OF UNIFORMITY IN KATHAK NRITTA HASTA

This paper talks about the significance of uniformity in the Nritta Hastas of Kathak dance across gharanas and eras. Kathak, an Indian classical dance form, hails from North India. Nritta Hastas refer to hand gestures or movements used in Indian classical dance. Often interchanged with” “hasta mudra”, “Nritta Hastas” encompass all hand movements and gestures, whereas “mudras” are more indicative of emotions and literal depictions of objects present in our environment.Kathak has evolved to appeal and cater to the spectators of today’s times - with lightning fast spins and hand movements along with intricate footwork. However, this has caused unfavorable negotiations with the original technique and overall uniformity of Nritta Hastas, thus resulting in the deterioration of quality in dance performances. For example, prioritizing the ability to execute multiple spins in quick succession, aiming to impress the audience with their speed and agility, leads to neglecting the intricate hand movements and mudras, which are essential for conveying the nuanced emotions and storytelling aspects of the dance. The purpose of this research paper is to shed light on the importance of maintaining uniformity by adhering to techniques, methods and pedagogies mentioned in ancient scriptures pertinent to Indian classical dance.

Automatic one-hand gesture (mudra) identification in bharatanatyam using eigenmudra projections and convolutional neural networks

Mudras in traditional Indian dance forms convey meaningful information when performed by an artist. The subtle changes between the different mudras in a dance form render automatic identification challenging as compared to conventional hand gesture identification, where the gestures are uniquely distinct from each other. Therefore, the objective of this study is to build a classifier model for the identification of the asamyukta mudra of bharatanatyam, one of the most popular classical dance forms in India. The first part of the paper provides a comprehensive review of the issues present in bharatanatyam mudra identification and the various studies conducted on the automatic classification of mudras. Based on this review, we observe that the unavailability of a large mudra corpus is a major challenge in mudra identification. Therefore, the second part of the paper focuses on the development of a relatively large database of mudra images consisting of 29 asamyukta mudras prevalent in bharatanatyam, which is obtained by incorporating different variabilities, such as subject, artist type (amateur or professional), and orientation. The mudra image database so developed is made available for academic research purposes. The final part of this paper describes the development of a convolutional neural network (CNN)-based automatic mudra identification system. Multistyle training of mudra classes on a conventional CNN showed a 92% correct identification rate. Based on the “eigenface” projection used in face recognition, “eigenmudras” projections of mudra images are proposed for improving the CNN-based mudra identification. Although the CNNs trained on the eigenmudra-projected images provide nearly equal identification rates as that obtained using the CNNs trained on raw mudra grayscale images, both models provide complementary mudra class information. The presence of complementary class information is confirmed by the improvement in the mudra identification performance when the CNN models trained from the raw mudra and eigenmudra-projected images are combined by computing the average of the scores obtained in the final softmax layers of both models. The same trend of improved mudra identification is observed upon combination of the average score level of VGG19 CNN models of the raw mudra images and corresponding eigenmudra-projected images.