Search
Now showing items 31-40 of 98
Devanagari Online Handwritten Character Recognition
In this thesis, a classifier based on local sub-unit level and global character level representations
of a character, using stroke direction and order variations independent features, is developed
for recognition of ...
AlGaN/GaN Heterojunction Based Hall Sensors for Magnetic Field Sensing over Wide Temperature Range
Hall sensor has proved to be an attractive solution for sensing requirements in electric
machines for direct measurement of fields or indirect estimation of physical quantities
such as current, speed and torque. Current ...
Fast High-Dimensional Filtering
Smoothing (diffusion) is a fundamental task in low-level vision and image processing. In the context of natural images, where edges (sharp discontinuities) play an important psychovisual role, the smoothing process needs ...
Cross-Modal Retrieval and Hashing
The objective of cross-modal retrieval is to retrieve relevant items from one modality (say image), given a query from another modality (say textual document). Cross-modal retrieval has various applications like matching ...
Improved Generative Models for Zero-shot object recognition
Recognizing objects from their images automatically using computers is an important research area in the computer vision community. In this scenario, the testing images are automatically classified into one of the classes ...
Soft Switched Multilevel Unidirectional High Frequency Link DC to AC Converter for Medium Voltage Grid Integration of Solar Photovoltaics
Grounding the frame of photovoltaic (PV) panel is a necessity for the safety of humans. This
leads to the formation of large capacitance between PV cells and ground. Hence, to reduce
leakage current due to parasitic ...
Neural Representation Learning for Speech and Audio Signals
Representation learning is the branch of machine learning consisting of techniques that are capable of automatically discovering meaningful representations from raw data for efficient information extraction. In recent ...
Pitch-Synchronous Discrete Cosine Transform Features for Speaker Recognition and Other Applications
Extracting speaker-speci c information from the speech is of great interest since speaker recognition
technology nds application in a wide range of areas such as forensics and biometric
security systems. In this thesis, ...
Robust Risk Minimization under Label Noise
In the setting of supervised learning, one learns a classi fier from training data consisting of
patterns and the corresponding labels. When labels of the examples in training data have errors,
it is referred to as label ...
Multiview Registration Using Rank-Constrained Semide nite Programming
We consider the problem of reconstructing a 3D surface from its multiview scans. Typically, the
computational pipeline for this problem has two phases: (I) finding point-to-point correspondences
between overlapping scans, ...