Extracting and recognizing complex human movements from unconstrained online/offline video sequence is a challenging task in computer vision. This paper proposes the classification of Indian classical dance actions using a powerful artificial intelligence tool: convolutional neural networks (CNN). In this work, human action recognition on Indian classical dance videos is performed on recordings from both offline (controlled recording) and online (live performances, YouTube) data. The offline data is created with ten different subjects performing 200 familiar dance mudras/poses from different Indian classical dance forms under various background environments. The online dance data is collected from YouTube for ten different subjects. Each dance pose is occupied for 60 frames or images in a video in both the cases. CNN training is performed with 8 different sample sizes, each consisting of multiple sets of subjects. The remaining 2 samples are used for testing the trained CNN. Different CNN architectures were designed and tested with our data to obtain a better accuracy in recognition. We achieved a 93.33% recognition rate compared to other classifier models reported on the same dataset.
Extracting and recognizing complex human movements from unconstraint online video sequence is an interesting task. In this paper the complicated problem from the class is approached using unconstraint video sequences belonging to Indian classical dance forms. A new segmentation model is developed using discrete wavelet transform and local binary pattern (LBP) features for segmentation. A 2D point cloud is created from the local human shape changes in subsequent video frames. The classifier is fed with 5 types of features calculated from Zernike moments, Hu moments, shape signature, LBP features, and Haar features. We also explore multiple feature fusion models with early fusion during segmentation stage and late fusion after segmentation for improving the classification process. The extracted features input the Adaboost multiclass classifier with labels from the corresponding song (tala). We test the classifier on online dance videos and on an Indian classical dance dataset prepared in our lab. The algorithms were tested for accuracy and correctness in identifying the dance postures.
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.
Privacy-preserving online disease prediction and diagnosis are critical issues in the emerging edge-cloud-based healthcare system. Online patient data processing from remote places may lead to severe privacy problems. Moreover, the existing cloud-based healthcare system takes more latency and energy consumption during diagnosis due to offloading of live patient data to remote cloud servers. Solve the privacy problem. The proposed research introduces the edgecloud enabled privacy-preserving healthcare system by exploiting additive homomorphic encryption schemes. It can help maintain the privacy preservation and confidentiality of patients' medical data during diagnosis of Parkinson's disease. In addition, the energy and delay aware computational offloading scheme is proposed to minimize the uncertainty and energy consumption of end-user devices. The proposed research maintains the better privacy and robustness of live video data processing during prediction and diagnosis compared to existing healthcare systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.