Pooja Venkatesh

Bio: Pooja Venkatesh is an academic researcher from International Institute of Information Technology, Bangalore. The author has contributed to research in topics: Expression (mathematics). The author has an hindex of 1, co-authored 2 publications receiving 2 citations. Previous affiliations of Pooja Venkatesh include International Institute of Information Technology.

Automatic expression recognition and expertise prediction in Bharatnatyam

Abstract: Bharatnatyam is an ancient Indian Classical Dance form consisting of complex postures and expressions. One of the main challenges in this dance form is to perform expression recognition and use the resulting data to predict the expertise of a test dancer. In this paper, expression recognition is carried out for the 6 basic expressions in Bharatnatyam using iMotions tool. The intensity values obtained from this tool for 4 distinct expressions — Joy, Surprise, Sad and Disgust are being used as our feature set for classification and predictive analysis. The recognition was performed on our own dataset consisting of 50 dancers with varied expertise ratings. Logistic Regression performed the best for Joy, Surprise and Disgust expressions giving an average accuracy of 80.78% whereas Support Vector Machine classifier with Radial Basis kernel function performed best for Sad expression giving an accuracy of 71.36%. A separate analysis on positive and negative emotions is carried out to determine the expertise of each rating on the basis of these emotions.

Automatic Bharatnatyam Dance Posture Recognition and Expertise Prediction Using Depth Cameras

Abstract: Bharatnatyam is an ancient Indian Classical Dance form consisting of complex postures and movements. One main challenge which has not been addressed till now in the intelligent systems community is to perform pose recognition for the basic postures of this dance form called the Bhangas and use this for expertise prediction. In this paper, pose recognition is performed for some important postures in Bharatnatyam in order to find the origin of these postures from the Bhangas and further use this result to predict the expertise of a Bharatnatyam dancer. The features extracted are 10 joint angles using 15 joint locations to predict the 22 postures derived from the basic postures (Bhangas). Support Vector Machine classifier with a radial basis function kernel performed the best for pose recognition. By performing stick figure analysis and grouping of labels we estimate the origin of each of these postures from the Bhangas. This is followed by verification of the grouping using Hamming distance calculation. Testing is done on our own Bharatnatyam dataset consisting of 102 dancers, achieving an accuracy of 87.14%. Expertise prediction of the dancers for the 22 poses was performed for four ratings - Excellent, Good, Satisfactory and Poor giving an accuracy of 68.46% without grouping of postures and 80.80% with grouping of postures.

Handwritten digit recognition using svm algorithm in machine learning

Abstract: Meanwhile Neural Networks based algorithms have intimated steadfast potential on various visual tasks including the recognition of Digits. This paper presents Support Vector Machine (SVM) based Real Time Hand-Written Digit Recognition System. The system involves two main sections i.e. training and recognition section. SVM classifier is used as the training algorithm and then tested it on MNIST dataset. We achieved a training accuracy of 98.05% and a test accuracy of 97.83% demonstrating that the proposed method can achieve significant and promising performance in digit recognition. Then we implemented our model to recognize user given handwritten digits in real time.

Acceptance of dance training system based on augmented reality and technology acceptance model (TAM)

Abstract: The advancement in Computer Vision (CV) has evolved drastically from image processing to object recognition, tracking video, restoration of images, three-dimensional (3D) pose recognition, and emotion analysis These advancements have eventually led to the birth of Augmented Reality (AR) technology, which means embedding virtual objects into the real-world environment The primary focus of this research was to solve the long-term learning retention and poor learning efficiency for mastering a dance skill through the AR technology based on constructivism learning theory, Dreyfus model and Technology Acceptance Model (TAM) The problem analysis carried out in this research had major research findings, in which the retention and learning efficiency of a dance training system were predominantly determined through the type of learning theory adopted, learning environment, training tools, skill acquisition technology and type of AR technique Therefore, the influential factors for the user acceptance of AR-based dance training system (ARDTS) were based on quantitative analysis These influential factors were determined to address the problem of knowledge gap on acceptance of AR-based systems for dance education through self-learning The evaluation and testing were conducted to validate the developed and implemented ARDTS system The Technology Acceptance Model (TAM) as the evaluation model and quantitative analysis was done with a research instrument that encompassed external and internal variables TAM consisted of 37 items, in which six factors were used to assess the new developed ARDTS by the authors and its acceptability among 86 subjects The current study had investigated the potential use of AR-based dance training system to promote a particular dance skill among a sample population with various backgrounds and interests The obtained results support a general acceptance towards ARDTS among the users who are interested in exploring the cutting-edge technology of AR for gaining expertise in a dance skill

Handwritten Essay Grading on Mobiles using MDLSTM Model and Word Embeddings

Abstract: Assessing handwritten essays is a human skill which is very important for school level language exams. If automated, it will enable scalable assessment and feedback at low cost. This problem involves two modalities, viz. images for Offline Handwriting Recognition (OHR) and Natural Language Processing (NLP) for essay grading. We consider the sequential information of handwriting for getting the transcriptions from text images. We train a Multidimensional Long Short Term Memory (MDLSTM) network with Connectionist Temporal Classification (CTC) cost function at the output for the task of OHR. The paper discusses the generalization of the handwriting recognition model for images taken from scanner and mobile camera. Further a comparison of results of essay grading is shown for features of essays based on GloVe and fastText based word vector representation models. We trained different models for the essay grading task considering it both as a classification and regression problem. The results show that the state of the art fastText word vector representation based features for essays perform better than the other features considered in this work. The best performing model shows Quadratic Weighted Kappa (QWK) agreement of 0.80 for grading between the human graded text essays and model graded text essays. The same model shows the QWK agreement of 0.81 for grading between the human graded text essays and the OHR transcribed essays. In this work, we consider handwritten essays written in English.

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

Abstract: Abstract. 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.

Sequence Recognition in Bharatnatyam Dance

Abstract: Bharatanatyam is the oldest Indian Classical Dance (ICD) which is learned and practiced across India and the world. Adavu is the core of this dance form. There exist 15 Adavus and 58 variations. Each Adavu variation comprises a well-defined set of motions and postures (called dance steps) that occur in a particular order. So, while learning Adavus, students not only learn the dance steps but also take care of its sequence of occurrences. This paper proposed a method to recognize these sequences. In this work, firstly, we recognize the involved Key Postures (KPs) and motions in the Adavu using Convolutional Neural Network (CNN) and Support Vector Machine (SVM), respectively. In this, CNN achieves 99% and SVM’s recognition accuracy becomes 84%. Next, we compare these KP and motion sequences with the ground truth to find the best match using the Edit Distance algorithm with an accuracy of 98%. The paper contributes hugely to the state-of-the-art in the form of digital heritage, dance tutoring system, and many more. The paper addresses three novelties; (a) Recognizing the sequences based on the KPs and motions rather than only KPs as reported in the earlier works. (b) The performance of the proposed work is measured by analyzing the prediction time per sequence. We also compare our proposed approach with the previous works that deal with the same problem statement. (c) It tests the scalability of the proposed approach by including all the Adavu variations, unlike the earlier literature, which uses only one/two variations.