A5102706610- Advanced Vision and Imaging
- Computer Graphics and Visualization Techniques
- Advanced Image and Video Retrieval Techniques
- Video Analysis and Summarization
- Robotics and Sensor-Based Localization
- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Human Pose and Action Recognition
- 3D Shape Modeling and Analysis
- Advanced X-ray and CT Imaging
- Image Retrieval and Classification Techniques
- Image Enhancement Techniques
- Human Motion and Animation
- Autism Spectrum Disorder Research
- AI in cancer detection
- Optical measurement and interference techniques
- Video Surveillance and Tracking Methods
- Sparse and Compressive Sensing Techniques
- Advanced Image Processing Techniques
- ECG Monitoring and Analysis
- Computational Geometry and Mesh Generation
- Image Processing Techniques and Applications
- 3D Surveying and Cultural Heritage
- Child Development and Digital Technology
- Remote-Sensing Image Classification
Indian Institute of Technology Bombay
2015-2025
South Texas Accelerated Research Therapeutics
2021
Start Treatment & Recovery Centers
2021
Indian Institute of Technology Indore
2003-2017
University of Maryland, College Park
1988-2005
Indian Institute of Technology Madras
1996
NTT (Japan)
1991
Ayurveda is a traditional medicine and natural healing system in India. Nadi-Nidan (pulse-based diagnosis) prominent method Ayurveda, known to dictate all the salient features of human body. In this paper, we provide details our procedure for obtaining complete spectrum nadi pulses as time series. The Nadi Tarangini contains diaphragm element equipped with strain gauge, transmitter cum amplifier, digitizer quantifying analog signal. acquires data 16-bit accuracy practically no external...
A diagnosis of autism typically depends on clinical assessments by highly trained professionals. This high resource demand poses a challenge in low-resource settings. Digital assessment neurodevelopmental symptoms non-specialists provides potential avenue to address this challenge. cross-sectional case-control field study establishes proof principle for such digital assessment. We developed and tested an app, START, that can be administered assess phenotypic domains (social, sensory, motor)...
Non-diffuse materials (e.g., metallic inks, varnishes, and paints) are widely used in real-world applications. Accurate spectral rendering relies on the bidirectional reflectance distribution function (BRDF). Current methods of capturing BRDFs have proven to be onerous accomplishing quick turnaround time, from conception design production. We propose a multi-layer perceptron for compact material representations, with 31 wavelengths four packaging materials. Our neural-based scenario reduces...
While geodesic active contours (GAC) have become very popular tools for image segmentation, they are sensitive to model initialization. In order get an accurate the typically needs be initialized close true object boundary. Apart from accuracy, automated initialization of objects interest is important pre-requisite being able run contour on large images (such as those found in digitized histopathology). A second limitation GAC that edge detector function based gray scale gradients; color...
We present a system for accurately quantifying the presence and extent of stain on account vascular biomarker tissue microarrays. demonstrate our flexible, robust, accurate, high-throughput minimally supervised segmentation algorithm, termed hierarchical normalized cuts (HNCuts) specific problem staining ovarian cancer The aspect HNCut is driven by use hierarchically represented data structure that allows us to merge two powerful image algorithms-a frequency weighted mean shift algorithm....
The centrally funded technical institutes (CFTIs) for undergraduate studies in India consist of the prestigious Indian Institutes Technology (IITs) as well several non-IITs (the National Technology, Information and others). IITs use candidate rankings obtained from performance on JEE Advanced exam their admissions, whereas a different set (obtained Main exam) admissions. Until 2014, used two separate processes to allocate seats candidates. Every year, individual candidates would get seats,...
Ayurveda is one of the most comprehensive healing systems in world and has classified body system according to theory Tridosha overcome ailments. Diagnosis similar traditional pulse-based method requires a clean input signals, extensive experiments for obtaining classification features. In this paper we briefly describe our generating pulse waveforms use various feature detecting methods show that an arterial contains typical physiological properties. The beat-to-beat variability captured...
Space Filling Curves (SFC) are particularly useful in linearization of data living two and three dimensional spaces have been used a number applications scientific computing, visualization. Interestingly, octrees, another versatile structure computer graphics, can be viewed as multiple SFCs at varying resolutions, albeit with parent-child relationship.
We propose a new dataset for learning local image descriptors which can be used significantly improved patch matching. Our proposed consists of an order magnitude more number scenes, images, and positive negative correspondences compared to the currently available Multi-View Stereo (MVS) from Brown et al. The also has better coverage overall viewpoint, scale, lighting changes in comparison MVS dataset. provides supplementary information like RGB patches with scale rotations values, intrinsic...
Introduction Early childhood development forms the foundations for functioning later in life. Thus, accurate monitoring of developmental trajectories is critical. However, such often relies on time-intensive assessments which necessitate administration by skilled professionals. This difficulty exacerbated low-resource settings where professionals are predominantly concentrated urban and private clinics, making them inaccessible to many. geographic economic inaccessibility contributes a...
We consider the problems of computing largest area triangle enclosed within a given n-sided convex polygon and smallest which encloses polygon. show that these are closely related by presenting single sequential linear time algorithm essentially solves both simultaneously. also present cost-optimal parallel in O( log n) using n/ n processors on CRCW PRAM. In order to achieve bounds we develop new techniques for design algorithms computational involving rotating calipers method.
JVRB, 4(2007), no. 7. - Image-based Relighting (IBRL) has recently attracted a lot of research interest for its ability to relight real objects or scenes, from novel illuminations captured in natural/synthetic environments. Complex lighting effects such as subsurface scattering, interreflection, shadowing, mesostructural self-occlusion, refraction and other relevant phenomena can be generated using IBRL. The main advantage image-based graphics is that the rendering time independent scene...
Heart rate variability (HRV) provides an estimate of sympathetic and parasympathetic influences on the heart rate. Although HRV has been extensively studied, sustained clinical use is still outstanding. The noninvasive, convenient, inexpensive arterial pulse originate from heartbeats, but not studied in a systematic fashion except rudimentary ways. In this paper, we present (PRV) as alternative to HRV. We give evidence for detection disorders patients using PRV, paving way future use.
Automatically classifying ECG recordings for malignant ventricular arrhythmia is fraught with several difficulties. Even normal signals exhibit only quasi-periodic nature, and contain various irregularities. The key to more accurate detection the use of position, amount local singularities in signals.In this paper, we propose a Holder-SVM algorithm using novel hybrid arrangement binary multiclass SVMs designed take care class imbalance rampant biomedical signals. As result, significantly...
Fiducials are commonly placed in environments to provide a uniquely identifiable object the scene. In quad copter applications, these fiducials often used evaluate planning algorithms given that ground truth positions can be detected from copter's camera. Low cost copters, however, subject quick and unstable motions cause significant motion blur severely affects detection rate of existing fiducials. This problem motivated us design fiducial is robust blur. Our proposed uses concentric...
Typical methods for abnormality detection in medical images, which is a one-class classification problem, rely on kernel principal component analysis (KPCA) and its robust invariants. However, typical KPCA appear heuristical nature often ignore the variances of data along modes variation. In this paper, we propose novel method statistical learning reproducing Hilbert space (RKHS) that relies our extension multivariate generalized Gaussian distribution to RKHS. We algorithms fit (KGG) RKHS,...
Introduction: The notion of local scale was introduced to characterize varying levels image detail so that localized processing tasks could be performed while simultaneously yielding a globally optimal result. In this paper, we have presented the methodological framework for novel locally adaptive definition, morphologic (MS), which is different from extant definitions in it attempts heterogeneity as opposed homogeneity. Methods: At every point interest, MS determined series radial paths...
The authors designed a process, based on the Deferred Acceptance algorithm, to allocate undergraduate admissions over 500 programs in 80 technical universities India. They also addressed complex rules regarding affirmative action by incorporating algorithmic innovations.
This paper address the problem of automatically extracting 3D configurations deformable objects from 2D features. Our focus in this work is to build on observation that subspace spanned by motion parameters a subset smooth manifold, and therefore we hunt for solution space, rather than use heuristics (as previously attempted earlier). We succeed attaching canonical Riemannian metric, using variant non-rigid factorisation algorithm structure motion. qualitatively quantitatively show our...
Mirroring the development of rendering algorithms for polygonal models, z-buffer style point-based models has given way recently to more advanced methods. A fast raycasting based approach [Wald and Seidel 2005] shows shadows, but does not demonstrate reflective effects. The general raytracing [Linsen et al. 2007] is substantially slower.