Kenneth Sullivan has over 10 years of experience in research and development of computer vision, image analysis, and machine learning software. He has built frameworks for large-scale image/video search, video activity recognition, object classification, geolocation, and malware detection. He is currently an Imaging Consultant at Epic Sciences designing approaches for automatic cancer cell detection using deep learning.
This document provides an overview of topics to be covered in a multimedia course including lossless and lossy image and audio compression techniques, standards like JPEG and MPEG, image and audio processing, video compression, multimedia interfaces, content retrieval over networks, and references for further reading on fundamentals of multimedia, data compression, digital image processing, JPEG, MPEG video compression, audio and video networking protocols, and more.
A Segmentation based Sequential Pattern Matching for Efficient Video Copy De...SWAMI06
A considerable number of videos are illegal copies or manipulated versions of existing media, making copyright management a complicated process.
Call for Change:-
Today’s widespread video copyright infringement calls for the development of fast and accurate copy-detection algorithms.
As video is the most complex type of digital media, it has so far received the least attention regarding copyright management.
Protect Data:-
Content-based copy detection (CBCD) ,a promising technique for video monitoring and copyright protection.
Zhipeng Zhao is seeking a research-oriented position utilizing his 6 years of experience and 6 publications in computer vision, machine learning, and data mining. He holds a Ph.D. in Computer Science from Rutgers University where he focused on object recognition, motion analysis, and statistical modeling. He also has 2 years of industrial experience applying skills in Java, C/C++, and data mining technologies at IBM.
M. Deepak Kumar has experience as a Machine Learning Engineer and Software Engineer Intern. He has worked at companies including Spline.ai, Betterhalf.ai, and TWB Inc., where he built and deployed machine learning models for tasks like disease prediction, personality analysis, and ad targeting. Deepak has skills in Python, JavaScript, machine learning frameworks like TensorFlow and Keras, and web technologies like Node.js, Flask, and Bootstrap. He holds a B.Tech. in Electrical and Electronics Engineering from Christ University.
Kadir A. Peker is an assistant professor in the Department of Computer Engineering at Melikşah University in Turkey. His research interests include machine learning, computer vision, and deep learning, with a focus on convolutional neural networks for image matching and comparison. He has over 17 years of experience in academia and industry, teaching courses in programming, machine learning, and computer vision.
Duc M. Le is a PhD candidate in computer science at USC studying software architecture and mining software repositories. He has experience in software design, development, and data mining. His research focuses on analyzing architectural changes in open source software systems and predicting potential bugs. He has worked as an intern at several companies including NEC Labs, Veritas, and Samsung Research America.
Resume Nimisha Jha Mainframe Developer 6 Years 5 MonthsNimisha Jha
The document contains the resume of Nimisha Jha, who is seeking a challenging role to utilize her technical skills and knowledge in mainframes such as COBOL, DB2, JCL. She has over 6 years of experience as a Senior Software Engineer and Project Lead working with clients like Hexaware Technologies and Tata Consultancy Services. Her expertise includes analysis, development, testing and providing production support for applications in the credit industry.
Rakesh Kumar Sinha is an expert programmer and computer scientist with over 3 years of experience in areas like artificial intelligence, web development, scientific programming, GIS mapping, network programming, data visualization, and mobile app development. He has worked as a research scientist at SAMEER, IIT Bombay developing software for weather research including pilot balloon tracking systems, weather radar data acquisition, and surface observation tools. He has a bachelor's degree in computer science and has knowledge of languages like C++, C#, Python, ASP.NET, and skills in tools like Eclipse and Visual Studio.
This document provides an overview of topics to be covered in a multimedia course including lossless and lossy image and audio compression techniques, standards like JPEG and MPEG, image and audio processing, video compression, multimedia interfaces, content retrieval over networks, and references for further reading on fundamentals of multimedia, data compression, digital image processing, JPEG, MPEG video compression, audio and video networking protocols, and more.
A Segmentation based Sequential Pattern Matching for Efficient Video Copy De...SWAMI06
A considerable number of videos are illegal copies or manipulated versions of existing media, making copyright management a complicated process.
Call for Change:-
Today’s widespread video copyright infringement calls for the development of fast and accurate copy-detection algorithms.
As video is the most complex type of digital media, it has so far received the least attention regarding copyright management.
Protect Data:-
Content-based copy detection (CBCD) ,a promising technique for video monitoring and copyright protection.
Zhipeng Zhao is seeking a research-oriented position utilizing his 6 years of experience and 6 publications in computer vision, machine learning, and data mining. He holds a Ph.D. in Computer Science from Rutgers University where he focused on object recognition, motion analysis, and statistical modeling. He also has 2 years of industrial experience applying skills in Java, C/C++, and data mining technologies at IBM.
M. Deepak Kumar has experience as a Machine Learning Engineer and Software Engineer Intern. He has worked at companies including Spline.ai, Betterhalf.ai, and TWB Inc., where he built and deployed machine learning models for tasks like disease prediction, personality analysis, and ad targeting. Deepak has skills in Python, JavaScript, machine learning frameworks like TensorFlow and Keras, and web technologies like Node.js, Flask, and Bootstrap. He holds a B.Tech. in Electrical and Electronics Engineering from Christ University.
Kadir A. Peker is an assistant professor in the Department of Computer Engineering at Melikşah University in Turkey. His research interests include machine learning, computer vision, and deep learning, with a focus on convolutional neural networks for image matching and comparison. He has over 17 years of experience in academia and industry, teaching courses in programming, machine learning, and computer vision.
Duc M. Le is a PhD candidate in computer science at USC studying software architecture and mining software repositories. He has experience in software design, development, and data mining. His research focuses on analyzing architectural changes in open source software systems and predicting potential bugs. He has worked as an intern at several companies including NEC Labs, Veritas, and Samsung Research America.
Resume Nimisha Jha Mainframe Developer 6 Years 5 MonthsNimisha Jha
The document contains the resume of Nimisha Jha, who is seeking a challenging role to utilize her technical skills and knowledge in mainframes such as COBOL, DB2, JCL. She has over 6 years of experience as a Senior Software Engineer and Project Lead working with clients like Hexaware Technologies and Tata Consultancy Services. Her expertise includes analysis, development, testing and providing production support for applications in the credit industry.
Rakesh Kumar Sinha is an expert programmer and computer scientist with over 3 years of experience in areas like artificial intelligence, web development, scientific programming, GIS mapping, network programming, data visualization, and mobile app development. He has worked as a research scientist at SAMEER, IIT Bombay developing software for weather research including pilot balloon tracking systems, weather radar data acquisition, and surface observation tools. He has a bachelor's degree in computer science and has knowledge of languages like C++, C#, Python, ASP.NET, and skills in tools like Eclipse and Visual Studio.
This document is a resume for Soumyanil Banerjee summarizing his education and experience. He received a M.S in Electrical and Computer Engineering from the University of Michigan in 2015, and a B.Tech in Electronics and Communications Engineering from West Bengal University of Technology in 2012. His objective is to find a full-time opportunity in signal and image processing, computer vision, and machine learning. He has internship experience developing medical imaging tools and has strong skills in programming languages like C/C++, MATLAB, and Python.
Alexander Burkart is seeking an electrical engineering position with a focus on software development. He has 1 year of experience developing imaging software for non-destructive testing of oil pipelines. He is receiving dual BSEE and BSCoE degrees from the University of Kentucky in May 2016 with honors and a 4.0 GPA. His project experience includes designing hearing aid circuits, microprocessors, image processing systems, and various antennas. He is proficient in languages such as C++, Matlab, and Python.
This document is a resume for Xiaoxin Ren, who is seeking a software engineering position. Ren has a Ph.D. in applied science and an M.S. in computer science from UC Davis, and a B.S. in modern physics from the University of Science and Technology of China. Ren has strong programming skills in Python, C++, JavaScript and other languages. Course projects include data visualization, software analysis, and numerical optimization methods. Research involved microwave imaging systems, big data visualization, and dimensionality reduction techniques. Ren has published papers in scientific journals and lists two advisors as references.
Ron Newman is an experienced web developer with a background in computer science, music education, and professional experience developing web and health applications. He has over 20 years of experience innovating and developing new technologies and solutions. He is skilled in languages like Java, PHP, and C and frameworks like Struts2 and Spring. He holds two patents and has made open source contributions.
The document provides a summary of Shwetambari Gulhane's qualifications and experience. She has over 10 years of experience in software development and IT services. Her technical skills include languages like Java, C#, .NET and tools like ArcGIS Desktop. She has a Master's in Computer Science from USC and is currently working as a Programming Support Analyst at Esri, where she develops custom GIS applications. Previously she has worked on projects related to banking, networking and GIS.
This document provides information on Deepak Kumar's education, experience, skills, and publications. It summarizes that he has a B.Tech in Electrical and Electronics Engineering from Christ University, Bangalore. He has worked as a Machine Learning Engineer at multiple companies developing models and deploying them in production. His skills include Python, TensorFlow, Keras, computer vision, and cloud platforms like AWS and GCP. He has published a paper on 3D printing.
This document provides a summary of a candidate's skills and work experience for a position in analytics, data mining, and machine learning. The candidate has over 15 years of experience in data analysis, machine learning, artificial intelligence, and developing predictive models. They have extensive experience developing fraud detection models for credit cards and other domains. They also have a PhD in Computer Science and have published papers in conferences on topics like decision trees and feature selection.
Yu-Fang Chang has a Master's degree in Computer Vision from Carnegie Mellon University and a Bachelor's degree in Electrical Engineering from National Taiwan University, with experience interning at Volkswagen, Intel, and Carnegie Mellon researching computer vision and deep learning topics like visual representation learning and object recognition. She has skills in programming languages like C/C++, Python, and MATLAB as well as software tools like Caffe, Tensorflow, OpenCV, and has conducted research projects involving finger band multiplayer games, defocus map acceleration, and air hockey robotics.
Pankaj Rajan has over 10 years of experience in software engineering and machine learning. He currently works as a Senior Software Engineer at eBay, where he has contributed to refactoring machine translation services and developing new databases and APIs. Previously, he worked at Microsoft and AMD in various roles involving product development, mentoring, and technical leadership. Rajan holds an MS in Computer Science from Texas A&M University and a BTech from NIT Rourkela. He has published over 10 papers in conferences and journals on topics related to sketch recognition, image processing, and cultural heritage preservation.
Michael Yao is seeking a position that utilizes his programming skills and expands his experience in different technologies. He has a B.S. in Computer Science from UC San Diego and an A.S. in Computer Information Systems from Victor Valley College. His skills include Java, C++, C#, Android development, and various SDKs. He has worked as a Project Full Stack Software Developer/Deputy at Northrop Grumman where he developed custom applications using technologies like SQL, ASP.NET, and Unity. He also has research experience developing projects like a first person shooting game and a wireless video streaming system between a camera and laptop.
This document is a resume for Giacomo Mellone. It summarizes his experience as an embedded software engineer, including improving and developing software modules for a CubeSat at Argotec, designing neural networks for image classification, and supporting mission procedures. It also lists his personal projects involving FPGA firmware, ray tracing, and generative adversarial networks. His education includes a Master's in Electronics Engineering and a Bachelor's in Electronic and Information Engineering.
The following resources come from the 2009/10 BSc (Hons) in Multimedia Technology (course number 2ELE0075) from the University of Hertfordshire. All the mini projects are designed as level two modules of the undergraduate programmes.
The objectives of this project are to demonstrate abilities to:
• Handle camera setup, calibrate and capture still and video faces
• Pre-process images and extract features
• Perform face recognition by a) using existing methods and b) trying new techniques.
This project requires the students to apply their abilities to handle image capture hardware and software. Since this is an active area of research, students will need to perform literature survey and discuss ( through brainstorm sessions) their performance characteristics. In addition, they will need to design and implement pre-processing and recognition codes leading to face recognition.
Ashish Kumar Singh is seeking a position that allows him to develop his technical and management skills. He has over 2 years of experience in embedded software development. His skills include C, C++, C#, Linux, Windows, networking, databases, and quality control tools like JIRA and HP Quality Center. He has worked on projects for Visteon, HP, and completed an academic project involving mobile solutions for farmers.
Ravi Kiran Godugu is a computer science graduate from Indian Institute of Technology, Jodhpur with a master's degree from University of California, Irvine. He has work experience as an intern and software developer at Yahoo, Morgan Stanley, IBM, and CAIR. His skills include Java, Python, C, JavaScript, Hadoop, MongoDB, Apache Storm, and machine learning tools like R and OpenCV. He has developed systems for online advertising analytics, infrastructure monitoring, security integration, and more. His personal projects include an investment optimization app, a Mario-style game, and a distributed simulation agent.
Raymond Yan-Lok Chan has experience as a software developer at NBC Universal and as a junior development engineer and lab assistant at UCLA. He developed tools for content protection at NBC Universal using Python, multiprocessing, and RabbitMQ. At UCLA, he developed Android and Windows tablet apps for lensfree microscopy as well as a Windows Phone app for Giardia parasite detection using a custom camera and Python server. He has skills in languages like Java, C/C++, C#, Python, and IDEs like Eclipse and Visual Studio.
This document contains a summary of Jai Prakash Kunwar's work experience and qualifications. He has over 11 years of experience developing software using Java technologies like JEE, Spring, and Hibernate. Some of his roles and responsibilities included requirements gathering, technical design, development, testing, and project management. He has worked on projects for clients like Royal Bank of Canada, Bank of America, and Genzyme in domains like banking, healthcare, and digital pathology. He is proficient with tools like Eclipse, Oracle, Jenkins, and version control systems.
Zhiyu Lin is a software engineer seeking new opportunities. He received a Master's degree in Software Engineering from Carnegie Mellon University and Bachelor's degrees in Software Engineering and Finance from Shanghai Jiao Tong University. His research experience includes developing a service management portal for NASA JPL and utilizing machine learning algorithms. He has worked as an intern at Johnson & Johnson and the Shanghai Fire Extinguish Department. His skills include Java, C#, C++, Python, and computer vision.
- Prashant S. Soman has over 2 years of experience in the mobile and wireless communication industry, with expertise in network stack deployment, troubleshooting, and design of wireless and VoIP systems.
- He currently works as a Customer Engineer at Qualcomm Technologies, providing support to carriers and OEMs from solution design to product deployment.
- He led the invention of a patent-pending technology for power-efficient network search by mobile devices.
Radhika Sharma is a technology lead from India with over 10 years of experience in IT and project management. She has extensive experience working with .NET, SQL, and web development technologies. Some of her roles include project manager, technology lead, security anchor, and onsite coordinator for clients in various domains like insurance and retail. She is looking for a new challenging position that allows growth.
An Enhanced Method to Detect Copy Move Forgey in Digital Image Processing usi...IRJET Journal
This document presents a study on detecting copy-move forgery in digital images. It discusses an enhanced method using 2D discrete wavelet transform (DWT) approach. The key steps of the proposed method include preprocessing, feature extraction using DWT, block matching to identify duplicated regions, and filtering to reduce false matches. The method aims to develop an efficient, robust technique for copy-move forgery detection. It reviews existing literature on various detection techniques in the intensity and frequency domains. The proposed method extracts DWT features and uses a block matching algorithm to detect duplicated regions more precisely compared to other methods.
This document is a resume for Soumyanil Banerjee summarizing his education and experience. He received a M.S in Electrical and Computer Engineering from the University of Michigan in 2015, and a B.Tech in Electronics and Communications Engineering from West Bengal University of Technology in 2012. His objective is to find a full-time opportunity in signal and image processing, computer vision, and machine learning. He has internship experience developing medical imaging tools and has strong skills in programming languages like C/C++, MATLAB, and Python.
Alexander Burkart is seeking an electrical engineering position with a focus on software development. He has 1 year of experience developing imaging software for non-destructive testing of oil pipelines. He is receiving dual BSEE and BSCoE degrees from the University of Kentucky in May 2016 with honors and a 4.0 GPA. His project experience includes designing hearing aid circuits, microprocessors, image processing systems, and various antennas. He is proficient in languages such as C++, Matlab, and Python.
This document is a resume for Xiaoxin Ren, who is seeking a software engineering position. Ren has a Ph.D. in applied science and an M.S. in computer science from UC Davis, and a B.S. in modern physics from the University of Science and Technology of China. Ren has strong programming skills in Python, C++, JavaScript and other languages. Course projects include data visualization, software analysis, and numerical optimization methods. Research involved microwave imaging systems, big data visualization, and dimensionality reduction techniques. Ren has published papers in scientific journals and lists two advisors as references.
Ron Newman is an experienced web developer with a background in computer science, music education, and professional experience developing web and health applications. He has over 20 years of experience innovating and developing new technologies and solutions. He is skilled in languages like Java, PHP, and C and frameworks like Struts2 and Spring. He holds two patents and has made open source contributions.
The document provides a summary of Shwetambari Gulhane's qualifications and experience. She has over 10 years of experience in software development and IT services. Her technical skills include languages like Java, C#, .NET and tools like ArcGIS Desktop. She has a Master's in Computer Science from USC and is currently working as a Programming Support Analyst at Esri, where she develops custom GIS applications. Previously she has worked on projects related to banking, networking and GIS.
This document provides information on Deepak Kumar's education, experience, skills, and publications. It summarizes that he has a B.Tech in Electrical and Electronics Engineering from Christ University, Bangalore. He has worked as a Machine Learning Engineer at multiple companies developing models and deploying them in production. His skills include Python, TensorFlow, Keras, computer vision, and cloud platforms like AWS and GCP. He has published a paper on 3D printing.
This document provides a summary of a candidate's skills and work experience for a position in analytics, data mining, and machine learning. The candidate has over 15 years of experience in data analysis, machine learning, artificial intelligence, and developing predictive models. They have extensive experience developing fraud detection models for credit cards and other domains. They also have a PhD in Computer Science and have published papers in conferences on topics like decision trees and feature selection.
Yu-Fang Chang has a Master's degree in Computer Vision from Carnegie Mellon University and a Bachelor's degree in Electrical Engineering from National Taiwan University, with experience interning at Volkswagen, Intel, and Carnegie Mellon researching computer vision and deep learning topics like visual representation learning and object recognition. She has skills in programming languages like C/C++, Python, and MATLAB as well as software tools like Caffe, Tensorflow, OpenCV, and has conducted research projects involving finger band multiplayer games, defocus map acceleration, and air hockey robotics.
Pankaj Rajan has over 10 years of experience in software engineering and machine learning. He currently works as a Senior Software Engineer at eBay, where he has contributed to refactoring machine translation services and developing new databases and APIs. Previously, he worked at Microsoft and AMD in various roles involving product development, mentoring, and technical leadership. Rajan holds an MS in Computer Science from Texas A&M University and a BTech from NIT Rourkela. He has published over 10 papers in conferences and journals on topics related to sketch recognition, image processing, and cultural heritage preservation.
Michael Yao is seeking a position that utilizes his programming skills and expands his experience in different technologies. He has a B.S. in Computer Science from UC San Diego and an A.S. in Computer Information Systems from Victor Valley College. His skills include Java, C++, C#, Android development, and various SDKs. He has worked as a Project Full Stack Software Developer/Deputy at Northrop Grumman where he developed custom applications using technologies like SQL, ASP.NET, and Unity. He also has research experience developing projects like a first person shooting game and a wireless video streaming system between a camera and laptop.
This document is a resume for Giacomo Mellone. It summarizes his experience as an embedded software engineer, including improving and developing software modules for a CubeSat at Argotec, designing neural networks for image classification, and supporting mission procedures. It also lists his personal projects involving FPGA firmware, ray tracing, and generative adversarial networks. His education includes a Master's in Electronics Engineering and a Bachelor's in Electronic and Information Engineering.
The following resources come from the 2009/10 BSc (Hons) in Multimedia Technology (course number 2ELE0075) from the University of Hertfordshire. All the mini projects are designed as level two modules of the undergraduate programmes.
The objectives of this project are to demonstrate abilities to:
• Handle camera setup, calibrate and capture still and video faces
• Pre-process images and extract features
• Perform face recognition by a) using existing methods and b) trying new techniques.
This project requires the students to apply their abilities to handle image capture hardware and software. Since this is an active area of research, students will need to perform literature survey and discuss ( through brainstorm sessions) their performance characteristics. In addition, they will need to design and implement pre-processing and recognition codes leading to face recognition.
Ashish Kumar Singh is seeking a position that allows him to develop his technical and management skills. He has over 2 years of experience in embedded software development. His skills include C, C++, C#, Linux, Windows, networking, databases, and quality control tools like JIRA and HP Quality Center. He has worked on projects for Visteon, HP, and completed an academic project involving mobile solutions for farmers.
Ravi Kiran Godugu is a computer science graduate from Indian Institute of Technology, Jodhpur with a master's degree from University of California, Irvine. He has work experience as an intern and software developer at Yahoo, Morgan Stanley, IBM, and CAIR. His skills include Java, Python, C, JavaScript, Hadoop, MongoDB, Apache Storm, and machine learning tools like R and OpenCV. He has developed systems for online advertising analytics, infrastructure monitoring, security integration, and more. His personal projects include an investment optimization app, a Mario-style game, and a distributed simulation agent.
Raymond Yan-Lok Chan has experience as a software developer at NBC Universal and as a junior development engineer and lab assistant at UCLA. He developed tools for content protection at NBC Universal using Python, multiprocessing, and RabbitMQ. At UCLA, he developed Android and Windows tablet apps for lensfree microscopy as well as a Windows Phone app for Giardia parasite detection using a custom camera and Python server. He has skills in languages like Java, C/C++, C#, Python, and IDEs like Eclipse and Visual Studio.
This document contains a summary of Jai Prakash Kunwar's work experience and qualifications. He has over 11 years of experience developing software using Java technologies like JEE, Spring, and Hibernate. Some of his roles and responsibilities included requirements gathering, technical design, development, testing, and project management. He has worked on projects for clients like Royal Bank of Canada, Bank of America, and Genzyme in domains like banking, healthcare, and digital pathology. He is proficient with tools like Eclipse, Oracle, Jenkins, and version control systems.
Zhiyu Lin is a software engineer seeking new opportunities. He received a Master's degree in Software Engineering from Carnegie Mellon University and Bachelor's degrees in Software Engineering and Finance from Shanghai Jiao Tong University. His research experience includes developing a service management portal for NASA JPL and utilizing machine learning algorithms. He has worked as an intern at Johnson & Johnson and the Shanghai Fire Extinguish Department. His skills include Java, C#, C++, Python, and computer vision.
- Prashant S. Soman has over 2 years of experience in the mobile and wireless communication industry, with expertise in network stack deployment, troubleshooting, and design of wireless and VoIP systems.
- He currently works as a Customer Engineer at Qualcomm Technologies, providing support to carriers and OEMs from solution design to product deployment.
- He led the invention of a patent-pending technology for power-efficient network search by mobile devices.
Radhika Sharma is a technology lead from India with over 10 years of experience in IT and project management. She has extensive experience working with .NET, SQL, and web development technologies. Some of her roles include project manager, technology lead, security anchor, and onsite coordinator for clients in various domains like insurance and retail. She is looking for a new challenging position that allows growth.
An Enhanced Method to Detect Copy Move Forgey in Digital Image Processing usi...IRJET Journal
This document presents a study on detecting copy-move forgery in digital images. It discusses an enhanced method using 2D discrete wavelet transform (DWT) approach. The key steps of the proposed method include preprocessing, feature extraction using DWT, block matching to identify duplicated regions, and filtering to reduce false matches. The method aims to develop an efficient, robust technique for copy-move forgery detection. It reviews existing literature on various detection techniques in the intensity and frequency domains. The proposed method extracts DWT features and uses a block matching algorithm to detect duplicated regions more precisely compared to other methods.
An Enhanced Method to Detect Copy Move Forgey in Digital Image Processing usi...
sullivan_resume
1. Kenneth Sullivan
12650 Carmel Country Road #107, San Diego, CA, 92130
sullivak@gmail.com
Summary
An experienced researcher and developer, I write software to solve problems in computer vision, image and video
analysis, and machine learning. I have more than 10 years of experience in research and development both as an
individual contributor and as a technical lead. During this time I have built frameworks to perform large scale
image/video content-based search, video activity recognition, object classification, automated geolocation, saliency
based compression, and malware detection. In addition to technical development, I have demonstrated writing and
presentation skills to win competitive contracts and communicate ideas with colleagues and customers.
Work Experience
Imaging Consultant Epic Sciences, San Diego, CA Feb 2016-Present
• Designing and implementing new approaches for automatic detection of cancer cells using deep neural
networks.
Research Staff Member Mayachitra, Inc., Santa Barbara, CA Sep 2005-Jan 2016
• Delivered fully functional software systems including an end-to-end image and video content-based search
system, a video activity analysis pipeline, and a saliency-enhanced video compression tool.
• Won several image and video analysis projects from competitive calls-for-proposals (BAA grant, SBIR, and
subcontract) and led these projects as principal investigator (PI).
• Consistently won optional contract extensions and phases based on technical performance for projects led.
• Developed algorithms in computer vision, image processing, and high-dimensional indexing, including
methods for content-based search, object classification, activity recognition, and indexing of large databases
of multimedia descriptors.
Grad Student Researcher University of California, Santa Barbara 2001-2005
• Researched and published novel approaches to digital image steganalysis (detection of hidden data in images)
extending the state-of-the-art.
Teaching Assistant University of California, Santa Barbara 2001, 2005
• Conducted laboratory and discussion classes in upper-division classes: Digital Signal Processing, Analog
Communications, and Network Synthesis. Supervised and assisted students with labs and homework.
HW/SW Engineer Tiernan Communications Inc., San Diego, CA 1998-2000
• Designed hardware (PCB, FPGA) and software (C, C++ firmware) for commercial broadcast equipment.
• Developed hardware and software for new MPEG-2 IRD (integrated receiver and decoder), both cheaper to
build and with more features then previous models.
Education
Doctor of Philosophy in Electrical Engineering 2005 • University of California, Santa Barbara
Thesis: “Image Steganalysis: Hunting and Escaping”. Dissertation topic is steganalysis, the detection of data
hidden in images, a field marrying elements of image analysis, statistics, and communications. Advisors: Profs.
Manjunath, Madhow, and Chandrasekaran.
Master of Science in Electrical Engineering 2002 • University of California, Santa Barbara
Focus on image and signal processing, and communications (emphasis on source and channel coding).
Bachelor of Science in Electrical Engineering, Minor in Economics 1998 • University of California, San
Diego
Skills
• Languages (from very comfortable to played with): C++, Python, C, MATLAB, Objective-C
• Libraries/frameworks: OpenCV, NumPy/SciPy, PostgreSQL, Caffe, HDF5, Boost, Hadoop, Accumulo,
IPP
Projects
Active Learning Based Scalable Representations for Event Understanding in Video, ONR Project
• 9/2015 to 1/2016, developed deep neural network models for classification and segmentation of overhead
images/video.
VIRAT (Video Image Retrieval and Analysis Tool), DARPA Project
• Led project team (2-6 people) as Mayachitra Principal Investigator (PI), 10/2008 to 10/2013. Project goal
was implementation and integration of fast large-scale search of high-dimensional descriptor feature vectors
generated from various groups.
• Designed and implemented large-scale video activity indexing database in C++ from ground up.
• Won Phase II award based on performance (speed and accuracy), competing against two other teams.
• Ported single-server system to distributed processing on Hadoop distributed system exploiting MapReduce
algorithm, for scalability and integration with customer systems.
• For further details, see indexing section here http://www.kitware.com/virat avss 2015.html
2. MalSee: Using vision, hearing, and other features to detect malware, ONR SBIR
• Principal Investigator, 7/2015 to 1/2016. Project goal is to use novel, unique approaches to malware
classification.
• Built initial prototype for vision-based malware detection able to correctly classify malware families of new
variants with 98% accuracy.
MIECS: Motion Imagery Exploitation with Compressive Sensing, ONR STTR
• Principal Investigator, 7/2013 to 7/2015. Project goal is reduction of required video bandwidth for Navy
drones, in some cases where processing is too limited for traditional compression.
• Halved required bandwidth by developing novel methods for saliency based compression.
Mixed Initiative Multiple Cue Image Localization (Finder), IARPA Project
• Principal Investigator at Mayachitra, 4/2012 to 12/2014. Project goal is determining location of unknown
query image/video. Mayachitra team focus is matching to public datasets of images with known locations.
• Built geolocalizing image/video search system comparing query to large database of public images (Flickr,
Panoramio, etc.) covering large geographic regions (roughly 100 km2
). Output is heatmap of likely locations
and top matches.
AVAAMO (Automated Video Activity Analysis for Military Operations), DARPA STTR
• Principal Investigator, 1/2009 to 6/2013. Project goal was development of video activity analysis methods,
especially for unmanned aerial vehicles (UAV).
• Successfully won competitive Phase 2 award based on Phase 1 performance.
• Developed novel video activity descriptors with unique features compared to state-of-the-art. In the second
phase, added these to existing end-to-end video search system to retrieve untrained activities from large video
databases.
Learning a Visual Thesaurus and Applications, ONR Project
• Principal Investigator, 10/2006 to 12/2009. Project goal was scene understanding of aerial imagery. This
includes automatic detection and classification, that is, the ability to both locate and categorize regions of
interest within very large geographical regions.
• In completing project goals, built end-to-end software system for content-based image search of aerial images,
including descriptor extraction, search algorithms, and GUI (Cocoa).
• Developed novel method to automatically use spatial context to improve results of classification.
Other projects
• Automatic scene understanding and generation of textual descriptions, ONR SBIR 3/2009 to
3/2011, developed methods for detection and classification of objects in aerial imagery.
• Geospatial Representation and Analysis (GEO*), DARPA Project 9/2005 to 10/2009, built
prototype search engine for aerial imagery.
• Multimedia data hiding, ONR Project 6/2001 to 9/2005, while at UCSB, developed steganalysis
methods extending the state-of-the-art, found theoretical limits to safe (undetectable) hiding, and proposed
new hiding methods resistant to steganalysis.
Academic Community Involvement
• Program Co-Chair for Information Hiding 2008, Member of Program Committee for Information Hiding
conference
• Reviewed papers for IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), IEEE Trans. Signal
Processing, IEEE Trans. Information Forensics and Security, ACM Multimedia, ACM Workshop on
Multimedia and Security, IEEE Int’l Conference on Image Processing, SPIE Electronic Imaging, and others.