Dr. Prudhvi Gurram Profile

Dr. Prudhvi Gurram

Lead Scientist

SPIE Involvement:

Author

Proceedings Article | 5 June 2015 Paper

Dimensionality analysis of facial signatures in visible and thermal spectra

Nathan Short, Shuowen Hu, Prudhvi Gurram

Proc. SPIE. 9474, Signal Processing, Sensor/Information Fusion, and Target Recognition XXIV

KEYWORDS: Long wavelength infrared, Thermography, Mid-IR, Visible radiation, Facial recognition systems, Principal component analysis, Super resolution, Detection and tracking algorithms, Error analysis, Image resolution

Read Abstract +

Face images are an important source of information for biometric recognition and intelligence gathering. While face recognition research has made significant progress over the past few decades, recognition of faces at extended ranges is still highly problematic. Recognition of a low-resolution probe face image from a gallery database, typically containing high resolution facial imagery, leads to lowered performance than traditional face recognition techniques. Learning and super-resolution based approaches have been proposed to improve face recognition at extended ranges; however, the resolution threshold for face recognition has not been examined extensively. Establishing a threshold resolution corresponding to the theoretical and empirical limitations of low resolution face recognition will allow algorithm developers to avoid focusing on improving performance where no distinguishable information for identification exists in the acquired signal. This work examines the intrinsic dimensionality of facial signatures and seeks to estimate a lower bound for the size of a face image required for recognition. We estimate a lower bound for face signatures in the visible and thermal spectra by conducting eigenanalysis using principal component analysis (PCA) (i.e., eigenfaces approach). We seek to estimate the intrinsic dimensionality of facial signatures, in terms of reconstruction error, by maximizing the amount of variance retained in the reconstructed dataset while minimizing the number of reconstruction components. Extending on this approach, we also examine the identification error to estimate the dimensionality lower bound for low-resolution to high-resolution (LR-to-HR) face recognition performance. Two multimodal face datasets are used for this study to evaluate the effects of dataset size and diversity on the underlying intrinsic dimensionality: 1) 50-subject NVESD face dataset (containing visible, MWIR, LWIR face imagery) and 2) 119-subject WSRI face dataset (containing visible and MWIR face imagery).

Proceedings Article | 20 May 2015 Paper

Detection of anomalous track patterns for long term surveillance

Shuowen Hu, Prudhvi Gurram, Alex Lipchen Chan

Proc. SPIE. 9464, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VI

KEYWORDS: Statistical analysis, Data modeling, Video, Video surveillance, Surveillance, Computer vision technology, Video compression, Machine vision, Binary data, Process modeling

Read Abstract +

Proceedings Article | 20 June 2014 Paper

Thermal-to-visible face recognition using multiple kernel learning

Shuowen Hu, Prudhvi Gurram, Heesung Kwon, Alex Chan

Proc. SPIE. 9091, Signal Processing, Sensor/Information Fusion, and Target Recognition XXIII

KEYWORDS: Long wavelength infrared, Thermography, Mid-IR, Short wave infrared radiation, Optical filters, Visible radiation, Facial recognition systems, Databases, Feature extraction, Neodymium

Read Abstract +

Proceedings Article | 21 May 2014 Paper

Entropy formulations for signal reconstruction from sensor arrays

Raghuveer Rao, Prudhvi Gurram

Proc. SPIE. 9103, Wireless Sensing, Localization, and Processing IX

KEYWORDS: Optical sensors, Imaging systems, Sensors, Fourier transforms, Interferometry, Wave propagation, Image sensors, Imaging arrays, Electroluminescent displays, Hassium

Read Abstract +

Proceedings Article | 20 May 2013 Paper

Unsupervised pedestrian detection using support vector data description

Prudhvi Gurram, Shuowen Hu, Chris Reale, Alex Chan

Proc. SPIE. 8744, Automatic Target Recognition XXIII

KEYWORDS: Detection and tracking algorithms, Data modeling, Sensors, Image processing, Feature extraction, Niobium, Data centers, Algorithm development, Statistical modeling, Process modeling

Read Abstract +

Proceedings Article | 20 May 2013 Paper

Implementation of a cascaded HOG-based pedestrian detector

Christopher Reale, Prudhvi Gurram, Shuowen Hu, Alex Chan

Proc. SPIE. 8744, Automatic Target Recognition XXIII

KEYWORDS: Safety, Detection and tracking algorithms, Sensors, Video, Error analysis, Robotics, Feature extraction, Video surveillance, Surveillance, Machine learning

Read Abstract +

Proceedings Article | 12 March 2013 Paper

Uniform grid upsampling of 3D lidar point cloud data

Prudhvi Gurram, Shuowen Hu, Alex Chan

Proc. SPIE. 8650, Three-Dimensional Image Processing (3DIP) and Applications 2013

KEYWORDS: Data modeling, LIDAR, Clouds, 3D modeling, Buildings, Raster graphics, Data conversion, 3D image processing, Tin, Airborne laser technology

Read Abstract +

Proceedings Article | 24 May 2012 Paper

Kernel-based joint spectral and spatial exploitation using Hilbert space embedding for hyperspectral classification

Prudhvi Gurram, Heesung Kwon

Proc. SPIE. 8390, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII

KEYWORDS: Hyperspectral imaging, Data modeling, Image processing, Spectroscopy, Composites, Spectral resolution, Associative arrays, Analytical research, Spatial resolution, Algorithm development

Read Abstract +

Proceedings Article | 5 May 2012 Paper

Classification of Shiga toxin-producing escherichia coli (STEC) serotypes with hyperspectral microscope imagery

Bosoon Park, William Windham, Scott Ladely, Prudhvi Gurram, Heesung Kwon, Seung-Chul Yoon, Kurt Lawrence, Neelam Narang, William Cray

Proc. SPIE. 8369, Sensing for Agriculture and Food Quality and Safety IV

KEYWORDS: Hyperspectral imaging, Microscopes, Imaging systems, Scattering, Glasses, Crystals, Image acquisition, Pathogens, Image classification, Bacteria

Read Abstract +

SPIE Journal Paper | 14 March 2012

Semiautomated system for three-dimensional modeling of buildings from aerial video

Prudhvi Gurram, Harvey Rhody, Eli Saber

JEI Vol. 21 Issue 1

KEYWORDS: 3D modeling, Buildings, 3D image processing, Image segmentation, LIDAR, Video, Visualization, Information visualization, Data modeling, Imaging systems

Read Abstract +

Proceedings Article | 20 May 2011 Paper

Hyperspectral anomaly detection using sparse kernel-based ensemble learning

Prudhvi Gurram, Timothy Han, Heesung Kwon

Proc. SPIE. 8048, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVII

KEYWORDS: Target detection, Hyperspectral imaging, Roads, Detection and tracking algorithms, Data modeling, Sensors, Digital imaging, Image classification, Niobium, Binary data

Read Abstract +

Proceedings Article | 13 May 2010 Paper

Ensemble learning based on multiple kernel learning for hyperspectral chemical plume detection

Prudhvi Gurram, Heesung Kwon

Proc. SPIE. 7695, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI

KEYWORDS: Long wavelength infrared, Hyperspectral imaging, FT-IR spectroscopy, Matrices, Image processing, Artificial neural networks, Machine learning, Chemical analysis, Data centers, Binary data

Read Abstract +

Recently, a SVM-based ensemble learning technique has been introduced by the authors for hyperspectral plume detection/classification. The SVM-based ensemble learning consists of a number of SVM classifiers and the decisions from these sub-classifiers are combined to generate a final ensemble decision. The SVM-based ensemble technique first randomly selects spectral feature subspaces from the input data. Each individual classifier then independently conducts its own learning within its corresponding spectral feature space. Each classifier constitutes a weak classifier. These weak classifiers are combined to make an ensemble decision. The ensemble learning technique provides better performance than the conventional single SVM in terms of error rate. Various aggregating techniques like bagging, boosting, majority voting and weighted averaging were used to combine the weak classifiers, of which majority voting was found to be most robust. Yet, the ensemble of SVMs is suboptimal. Techniques that optimally weight the individual decisions from the sub-classifiers are strongly desirable to improve ensemble learning performance. In the proposed work, a recently introduced kernel learning technique called Multiple Kernel Learning (MKL) is used to optimally weight the kernel matrices of the sub-SVM classifiers. MKL basically iteratively performs l2 optimization on the Euclidian norm of the normal vector of the separating hyperplane between the classes (background and chemical plume) defined by the weighted kernel matrix followed by gradient descent optimization on the l1 regularized weighting coefficients of the individual kernel matrices. Due to l1 regularization on the weighting coefficients, the optimized weighting coefficients become sparse. The proposed work utilizes the sparse weighting coefficients to combine decision results of the SVM-based ensemble technique. A performance comparison between the aggregating techniques - MKL and majority voting as applied to hyperspectral chemical plume detection is presented in the paper.

Proceedings Article | 29 February 2008 Paper

Extraction of digital elevation map from parallel-perspective stereo mosaics

Prudhvi Gurram, Eli Saber, Harvey Rhody

Proc. SPIE. 6803, Stereoscopic Displays and Applications XIX

KEYWORDS: Data modeling, Cameras, Sensors, Image segmentation, Video, 3D modeling, Buildings, Computer aided design, Solid modeling, RGB color model

Read Abstract +

Proceedings Article | 5 March 2007 Paper

A novel triangulation method for building parallel-perspective stereo mosaics

Prudhvi Gurram, Eli Saber, Harvey Rhody

Proc. SPIE. 6490, Stereoscopic Displays and Virtual Reality Systems XIV

KEYWORDS: Prisms, 3D acquisition, Visualization, Imaging systems, Cameras, Sensors, Image segmentation, Video, Algorithm development, 3D image processing

Read Abstract +

Showing 5 of 14 publications

Conference Committee Involvement (3)

Video Surveillance and Transportation Imaging Applications 2015

10 February 2015 | San Francisco, California, United States

Video Surveillance and Transportation Imaging Applications 2014

3 February 2014 | San Francisco, California, United States

Video Surveillance and Transportation Imaging Applications

4 February 2013 | Burlingame, California, United States

Keywords/Phrases

Search In:

Publication Years