David Doermann

Publication List Details

Period

1993 - 2009

Number

118

Co-Authors

Offline Loop Investigation for Handwriting Analysis (2009)

Tal Steinherz, David Doermann, Senior Member, Ehud Rivlin, Nathan Intrator

Abstract—Resolution of different types of loops in handwritten script presents a difficult task and is an important step in many classic word recognition systems, writer modeling, and signature...

Morphology Induction from Limited Noisy Data Using Approximate String Matching (2008)

Burcu Karagol-ayan, David Doermann, Amy Weinberg

For a language with limited resources, a dictionary may be one of the few available electronic resources. To make effective use of the dictionary for translation, however, users must be able to...

ABSTRACT A Platform Independent Image and Video Engine (2008)

David Doermann, Arvind Karunanidhi, Niketu Parekh, Ville Rautio

This paper describes progress on the development of a platform independent media engine for mobile devices. The effort is part of the CAPNET (Context Aware Pervasive NETworks) project and focuses on...

Using Computer Vision to Detect Web Browser Display Errors (2008)

Xu Liu, David Doermann

As the functionality and complexity of the WWW continues to grow so does the need for WWW quality assurance and testing. Although there have been numerous approaches to automated Web testing,...

Learning Higher-order Transition Models in Medium-scale Camera Networks (2008)

Ryan Farrell, David Doermann, Larry S. Davis

We present a Bayesian framework for learning higherorder transition models in video surveillance networks. Such higher-order models describe object movement between cameras in the network and have a...

Adaptive Transformation-based Learning for Improving Dictionary Tagging (2008)

Burcu Karagol-ayan, David Doermann, Amy Weinberg

We present an adaptive technique that enables users to produce a high quality dictionary parsed into its lexicographic components (headwords, pronunciations, parts of speech, translations, etc.)...

Morphology Induction from Limited Noisy Data Using Approximate String Matching (2008)

Burcu Karagol-ayan, David Doermann, Amy Weinberg

For a language with limited resources, a dictionary may be one of the few available electronic resources. To make effective use of the dictionary for translation, however, users must be able to...

Abstract Imaging as an Alternative Data Channel for Camera Phones (2008)

Xu Liu, David Doermann

In this paper, we demonstrate a solution to use cameras to download data to cell phones as an alternative to existing wireless (CDMA/GPRS, BlueTooth), infrared or cable connections. In our method the...

DeMenthon D.: Hierarchical Part-Template Matching for Human Detection and Segmentation (2008)

Zhe Lin, Larry S. Davis, David Doermann, Daniel Dementhon

Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detectors are capable of...

, Paul Over 2 (2008)

Alan F. Smeaton, Cash J. Costello, David Doermann, Er Hauptmann, Mark E. Rorvig, ...

The development of techniques to support content-based access to archives of digital video information has recently started to receive much attention from the research community. During 2001, the...

The Design and Implementation of ViPER (2008)

David Mihalcik, David Doermann

A video sequence may contain any number of persons, objects and activities. ViPER-GT is a tool for annotating a video with detailed spatial and temporal information about its contents. This paper is...

Identifying Script on Word-Level with Informational Confidence (2008)

Stefan Jaeger, Huanfeng Ma, David Doermann

In this paper, we present a multiple classifier system for script identification. Applying a Gabor filter analysis of textures on word-level, our system identifies Latin and non-Latin words in...

Font Identification Using the Grating Cell Texture Operator (2008)

Huanfeng Ma, David Doermann

In this paper, a new feature extraction operator, the grating cell operator, is applied to analyze the texture features and classify fonts of scanned document images. This operator is compared with...

Automatic Document Logo Detection (2008)

Guangyu Zhu, David Doermann

Automatic logo detection and recognition continues to be of great interest to the document retrieval community as it enables effective identification of the source of a document. In this paper, we...

Document Image Retrieval Based on Layout Structural Similarity (2008)

Christian Shin, David Doermann

Abstract—In this paper, we describe issues related to the measurement of structural similarity between document images. We define structural similarity, and discuss the benefits of using it as a...

Adaptive Transformation-based Learning for Improving Dictionary Tagging (2008)

Burcu Karagol-ayan, David Doermann, Amy Weinberg

We present an adaptive technique that enables users to produce a high quality dictionary parsed into its lexicographic components (headwords, pronunciations, parts of speech, translations, etc.)...

DeMenthon D.: Hierarchical Part-Template Matching for Human Detection and Segmentation (2008)

Zhe Lin, Larry S. Davis, David Doermann, Daniel Dementhon

Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detectors are capable of...

Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion (2008)

Zhe Lin, Larry S. Davis, David Doermann, Daniel Dementhon

Abstract. We describe an approach to segmenting foreground regions corresponding to a group of people into individual humans. Given background subtraction and ground plane homography, hierarchical...

ABSTRACT AN APPEARANCE BASED APPROACH FOR CONSISTENT LABELING OF HUMANS AND OBJECTS IN VIDEO (2008)

Martí Balcells, Daniel Dementhon, David Doermann

We present an approach for consistently labeling people and for detecting human-object interactions using mono-camera surveillance video. The approach is based on a robust appearance based...

Text Extraction, Enhancement and OCR in Digital Video (2007)

Huiping Li, David Doermann, Omid Kia

. In this paper we address the problem of text extraction, enhancement and recognition in digital video. Compared with optical character recognition (OCR) from document images, text extraction and...

A Closed-Loop Training System for Video Text Detection (2007)

Huiping Li, David Doermann

In this paper we present a video text detection system based on neural network training. Compared with previous work [3, 5, 7] which detected only graphical text with fixed parameters, our system has...

Integrated Segmentation and Clustering for Enhanced Compression of Document Images (2007)

Omid Kia And, Omid Kia, David Doermann

The symbolic compression of document images is a method which represents patterns found in the image by a set of prototypes stored in a library. The ability to represent patterns by a single...

Hybrid Thinning Through Reconstruction (2007)

David Doermann And, David Doermann, Omid Kia

One difficulty with many pixel-wise thinning algorithms is that they produce unacceptable results at junction points, or in the presence of contour noise. In this paper we present a novel approach to...

Model-Based Graphics Recognition (2007)

Marc Vuilleumier Stückelberg, David Doermann

In this paper, we illustrate the use of a novel probabilistic framework for document analysis on typical problems of document layout analysis and graphics recognition. Our system uses an explicit...

Hybrid Thinning Through Reconstruction (2007)

David Doermann, Omid Kia

One difficulty with many pixel-wise thinning algorithms is that they produce unacceptable results at junction points, or in the presence of contour noise. In this paper we present a novel approach to...

Background Line Detection with A Stochastic Model (2007)

Yefeng Zheng, Huiping Li, David Doermann

Background lines often exist in textual documents. It is important to detect and remove those lines so text can be easily segmented and recognized. A stochastic model is proposed in this paper which...

Video Indexing and Retrieval for TREC 2002 (2007)

Christian Wolf, David Doermann

The goal of the TREC conference Video Retrieval Track is the investigation of content-based retrieval from digital video. We participated at the conference with a query and browsing system. For...

a (2007)

Vikrant Kobla, David Doermann, Christos Faloutsos

A high-level representation of a video clip comprising information about its physical and semantic structure is necessary for providing appropriate processing, indexing and retrieval capabilities for...

Video Retrieval Using Spatio-Temporal Descriptors (2007)

Daniel Dementhon, David Doermann

This paper describes a novel methodology for implementing video search functions such as retrieval of near-duplicate videos and recognition of actions in surveillance video. Videos are divided into...

Adaptive Hindi OCR using generalized Hausdorff image comparison (2007)

Huanfeng Ma, David Doermann

We present an adaptive Hindi OCR implemented as part of a rapidly retargetable language tool effort. The system includes: script identification, character segmentation, training sample creation and...

Adaptive Hindi OCR using generalized Hausdorff image comparison (2007)

Huanfeng Ma, Huanfeng Ma, David Doermann, David Doermann

In this paper, we present an adaptive Hindi OCR using generalized Hausdorff image comparison implemented as part of a rapidly retargetable language tool effort. The system includes: script...

Mining Tool for Surveillance Video (2007)

Nagia Ghanem David, David Doermann, Larry Davis, Daniel Dementhon

This paper describes a system for the mining of surveillance video. Our main contributions are: providing a high level query language for submitting queries about spatial and temporal relations of...

M. Agosti and C. Thanos (Eds.): ECDL 2002, LNCS 2458, pp. 266-275, 2002. (2007)

Alan F. Smeaton, Cash J. Costello, David Doermann, Er Hauptmann, ...

This paper is not intended to provide a comprehensive picture of the different approaches taken by the TREC2001 video track participants but instead we give an overview of the TREC video search task...

A Model-based Line Detection Algorithm in Documents (2007)

Yefeng Zheng, Huiping Li, David Doermann

In this paper we present a novel model based approach to detect severely broken parallel lines in noisy textual documents. It is important to detect and remove these lines so the text can be...

Thesis: “Resource Generation from Structured Documents for Low-density Languages” (2007)

Advisors Amy Weinberg, David Doermann, Advisor Bonnie, J. Dorr, Advisor Cem Bozsahin

Resource generation for less commonly thought languages. Computational morphology. Information extraction from structured noisy documents. Information extraction and morpheme discovery from...

DeMenthon D.: An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans (2007)

Zhe Lin, Larry S. Davis, David Doermann, Daniel Dementhon

An interactive human segmentation approach is described. Given regions of interest provided by users, the approach iteratively estimates segmentation via a generalized EM algorithm. Specifically, it...

Geometric Rectification of Camera-captured Document Images (2007)

Jian Liang, Daniel Dementhon, David Doermann, Daniel Dementhon, David Doermann, College Park, ...

Compared to typical scanners, handheld cameras offer convenient, flexible, portable, and non-contact image capture, which enables many new applications and breathes new life into existing ones....

Motivations (2007)

Guangyu Zhu, David Doermann

� Logos are widely used in business and government environments as a declaration of document source and ownership � Given a large collection of documents, searching for a specific logo is a...

A New Algorithm for Detecting Text Line in Handwritten Documents (2006)

Li, Yi, Zheng, Yefeng, Doermann, David, Jaeger, Stefan

Curvilinear text line detection and segmentation in handwritten documents is a significant challenge for handwriting recognition. Given no prior knowledge of script, we model text line detection as...

SOFTCBIR: OBJECT SEARCHING IN VIDEOS COMBINING KEYPOINT MATCHING AND GRADUATED ASSIGNMENT (2006)

Ming Luo, Daniel Dementhon, Xiaodong Yu, David Doermann

This paper proposes a new approach to object searching in video databases, SoftCBIR, which combines a keypoint matching algorithm and a graduated assignment algorithm based on softassign. Compared...

1 2 3 4 5 6 Mosaicing of Camera-captured Documents Without Pose Restriction (2006)

Jian Liang A, Daniel Dementhon B, David Doermann B, Wa Usa, B Daniel Dementhon, David Doermann

In this paper we present an image mosaicing method for camera-captured docu-ments. Our method is unique in not restricting the camera position, thus allowing greater flexibility than approaches using...

SCRIPT-INDEPENDENT TEXT LINE SEGMENTATION IN FREESTYLE HANDWRITTEN DOCUMENTS (2006)

Li Yi, Yefeng Zheng, David Doermann, Stefan Jaeger

Text line segmentation in freestyle handwritten documents remains an open document analysis problem. Curvilinear text lines and small gaps between neighboring text lines present a challenge to...

Robust point matching for nonrigid shapes by preserving local neighborhood structures (2006)

Yefeng Zheng, David Doermann

Abstract—In previous work on point matching, a set of points is often treated as an instance of a joint distribution to exploit global relationships in the point set. For nonrigid shapes, however,...

A robust stamp detection framework on degraded documents (2006)

Guangyu Zhu, Stefan Jaeger, David Doermann

Detecting documents with a certain stamp instance is an effective and reliable way to retrieve documents associated with a specific source. However, this unique problem has essentially remained...

Video retrieval of near-duplicates using k-nearest neighbor retrieval of spatiotemporal descriptors (2005)

Daniel Dementhon, David Doermann

This paper describes a novel methodology for implementing video search functions such as retrieval of near-duplicate videos and recognition of actions in surveillance video. Videos are divided into...

Fast camera motion estimation for hand-held devices and applications (2005)

Xu Liu, David Doermann, Huiping Li

In this paper we present an efficient motion estimation algorithm for camera-enabled handheld devices, such as mobile phones and PDAs. Compared to general camera motion estimation, the estimation of...

Representation and recognition of events in surveillance video using petri nets (2004)

Nagia Ghanem, Daniel Dementhon, David Doermann, Larry Davis

Detection of events is an essential task in surveillance applications. This task requires finding a general event representation method and developing efficient recognition algorithms dealing with...

Machine Printed Text and Handwriting Identification in Noisy Document Images (2004)

Yefeng Zheng, Student Member, Huiping Li, David Doermann

In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text...

Building an Information Retrieval Test Collection for (2004)

Spontaneous Conversational Speech, Douglas W. Oard, Dagobert Soergel, David Doermann, Xiaoli Huang, G. Craig Murray, ...

Test collections model use cases in ways that facilitate evaluation of information retrieval systems. This paper describes the use of search-guided relevance assessment to create a test collection...

Representation and recognition of events in surveillance video using petri nets (2004)

Nagia Ghanem, Daniel Dementhon, David Doermann, Larry Davis

Detection of events is an essential task in surveillance applications. This task requires finding a general event representation method and developing efficient recognition algorithms dealing with...

Word level script identification for scanned document images (2004)

Huanfeng Ma, David Doermann

In this paper, we compare the performance of three classifiers used to identify the script of words in scanned document images. In both training and testing, a Gabor filter is applied and 16 channels...

Acquisition of bilingual MT lexicons from OCRed dictionaries (2003)

Burcu Karagol-ayan, David Doermann, Bonnie J. Dorr

This paper describes an approach to analyzing the lexical structure of OCRed bilingual dictionaries to construct resources suited for machine translation of low-density languages, where online...

Progress in camera-based document image analysis (2003)

David Doermann, Jian Liang, Huiping Li

The increasing availability of high performance, low priced, portable digital imaging devices has created a tremendous opportunity for supplementing traditional scanning for document image...

An appearance based approach for human and object tracking (2003)

Mart Balcells Capellades, David Doermann, Daniel Dementhon

A system for tracking humans and detecting human-object interactions in indoor environments is described. A combination of correlogram and histogram information is used to model object and human...

Parsing And Tagging Of Binlingual Dictionary (2003)

Huanfeng Ma, Burcu Karagol-Ayan, Huanfeng Ma, David Doermann, David Doermann, Doug Oard, ...

Bilingual dictionaries hold great potential as a source of lexical resources for training and testing automated systems for optical character recognition, machine translation, and cross-language...

Parsing And Tagging Of Bilingual Dictionary (2003)

Huanfeng Ma, Burcu Karagol-ayan, David Doermann, Doug Oard, Jianqiang Wang

Bilingual dictionaries hold great potential as a source of lexical resources for training and testing automated systems for optical character recognition, machine translation, and cross-language...

Text Identification in Noisy Document Images Using Markov Random Field (2003)

Yefeng Zheng, Huiping Li, David Doermann

In this paper we address the problem of the identification of text from noisy documents. We segment and identify handwriting from machine printed text because 1) handwriting in a document often...

Acquisition of Bilingual MT Lexicons from OCRed Dictionaries (2003)

Burcu Karagol-ayan, David Doermann, Bonnie J. Dorr

This paper describes an approach to analyzing the lexical structure of OCRed bilingual dictionaries to construct resources suited for machine translation of low-density languages, where online...

An appearance based approach for human and object tracking (2003)

Martí Balcells Capellades, David Doermann, Daniel Dementhon

A system for tracking humans and detecting human-object interactions in indoor environments is described. A combination of correlogram and histogram information is used to model object and human...

Bootstrapping structured page segmentation (2003)

Huanfeng Ma, David Doermann

In this paper, we present an approach to the bootstrapping learning of a page segmentation model. The idea evolves from attempts to segment dictionaries that often have a consistent page structure,...

IJDAR (2005) Digital Object Identifier (DOI) 10.1007/s10032-004-0138-z Camera-based analysis of text and documents: a survey (2003)

Jian Liang, David Doermann, Huiping Li

Abstract. The increasing availability of highperformance, low-priced, portable digital imaging devices has created a tremendous opportunity for supplementing traditional scanning for document image...

TREC-10 experiments at University of Maryland: CLIR and video (2002)

Kareem Darwish, David Doermann, Ryan Jones, Douglas Oard, Mika Rautiainen

The University of Maryland Researchers participated in both the Arabic-English Cross Language Information Retrieval (CLIR) and Video tracks of TREC-10. In the CLIR track, our goal was to explore...

V.: Video analysis applications for pervasive environments (2002)

Arvind Karunanidhi, David Doermann, Niketu Parekh, Ville Rautio

Abstract. Network capabilities are expanding at a rate that will soon allow a much wider range of image and video content to be delivered to and transmitted from mobile wireless devices. Current...

Hidden loop recovery for handwriting recognition (2002)

David Doermann, Nathan Intrator, Ehud Rivlin, Tal Steinherz

One significant challenge in the recognition of offline handwriting is in the interpretation of loop structures. Although this information is readily available in online representation, close...

Binarization of Low Quality Text Using a Markov Random Field Model (2002)

Christian Wolf, David Doermann

Binarization techniques have been developed in the document analysis community for over 30 years and many algorithms have been used successfully. On the other hand, document analysis tasks are more...

The segmentation and identification of handwriting in noisy document images (2002)

Yefeng Zheng, Huiping Li, David Doermann

Abstract. In this paper we present an approach to the problem of segmenting and identifying handwritten annotations in noisy document images. In many types of documents such as correspondence, it is...

Logical Labeling of Document Images using layout graph matching with adaptive learning, Document Analysis Systems (2002)

Jian Liang, David Doermann

Abstract. Logical structure analysis of document images is an important problem in document image understanding. In this paper, we propose a graph matching approach to label logical components on a...

Hybrid Independent Component Analysis And Support Vector Machine (2002)

Learning Scheme For, Yuan Qi, David Doermann, Daniel Dementhon

In this paper we propose a new hybrid unsupervised / supervised learning scheme that integrates Independent Component Analysis (ICA) withthe SupportVector Machine (SVM) approach and apply this new...

Hybrid Independent Component Analysis And Support Vector Machine (2002)

Learning Scheme For, Yuan Qi, David Doermann, Daniel Dementhon

In this paper we propose a new hybrid unsupervised / supervised learning scheme that integrates Independent Component Analysis (ICA) withthe SupportVector Machine (SVM) approach and apply this new...

The segmentation and identification of handwriting in noisy document images (2002)

Yefeng Zheng, Huiping Li, David Doermann

Abstract. In this paper we present an approach to the problem of segmenting and identifying handwritten annotations in noisy document images. In many types of documents such as correspondence, it is...

Video indexing and retrieval at UMD (2002)

Christian Wolf, David Doermann, Mika Rautiainen

Our team from the University of Maryland and INSA de Lyon participated in the feature extraction evaluation with overlay text features and in the search evaluation with a query retrieval and browsing...

The TREC2001 video track: information retrieval on digital video information (2002)

Smeaton, Alan F., Over, Paul, Costello, Cash J., De Vries, Arjen P., Doermann, David, Hauptmann, Alexander, ...

The development of techniques to support content-based access to archives of digital video information has recently started to receive much attention from the research community. During 2001, the...

The TREC2001 video track: information retrieval on digital video information (2002)

Smeaton, Alan F., Over, Paul, Costello, Cash J., De Vries, Arjen P., Doermann, David, Hauptmann, Alexander, ...

The development of techniques to support content-based access to archives of digital video information has recently started to receive much attention from the research community. During 2001, the...

Thesis: “Resource Generation from Structured Documents for Low-density Languages” (2001)

Advisors Amy Weinberg, David Doermann, Advisor Bonnie, J. Dorr, Advisor Cem Bozsahin

Resource generation for less commonly thought languages. Computational morphology. Information extraction from structured noisy documents. Information extraction and morpheme discovery from...

Identifying Sports Videos Using Replay, Text, and Camera Motion Features (2000)

Vikrant Kobla, Daniel Dementhon, David Doermann

Automated classification of digital video is emerging as an important piece of the puzzle in the design of content management systems for digital libraries. The ability to classify videos into...

Automatic Text Detection and Tracking in Digital Video (2000)

Huiping Li David, David Doermann, Omid Kia

Text which appears in a scene or is graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and for...

Event Detection from MPEG Video in the Compressed Domain (2000)

Kyongil Yoon, Daniel DeMenthon, David Doermann

The use of information in the compressed domain allows for the rapid analysis of video content using standard hardware. This paper describes two techniques for detecting dynamic events using the...

Hidden Markov Models for Images (2000)

Daniel Dementhon, David Doermann, Marc Vuilleumier Stückelberg

In this paper we investigate how speech recognition techniques can be extended to image processing. We describe a method for learning statistical models of images using a second-order hidden Markov...

Hidden Markov Models for Images (2000)

Daniel Dementhon, David Doermann

In this paper we investigate how speech recognition techniques can be extended to image processing. We describe a method for learning statistical models of images using a second-order hidden Markov...

Image distance using hidden Markov models (2000)

Daniel Dementhon, David Doermann

We describe a method for learning statistical models of images using a second-order hidden Markov mesh model. First, an image can be segmented in a way that best matches its statistical model by an...

Text Enhancement in Digital Video Using Multiple Frame Integration (1999)

Huiping Li, David Doermann

In this paper a multiple frame based technique to enhance text in digital video is presented. After extracting a reference text block, we use an image matching technique to find the corresponding...

Text Enhancement in Digital Video Using Multiple Frame Integration (1999)

Huiping Li, David Doermann

In this paper we address the problem of text enhancement in digital video for Optical Character Recognition (OCR). Compared withOCR problem of scanned documents, text recognition in digital video...

Detection Of Slow-Motion Replay Sequences For Identifying Sports Videos (1999)

Vikrant Kobla, Daniel Dementhon, David Doermann

Automated classification of digital video is emerging as an important piece of the puzzle in the design of content management systems for digital libraries. The ability to classify videos into...

Text Enhancement in Digital Video (1999)

Huiping Li, Omid Kia, David Doermann

One difficulty with using text from digital video for indexing and retrieval is that video images are often in low resolution and poor quality, and as a result, the text can not be recognized...

Detection of slow-motion replay sequences for identifying sports videos (1999)

Vikrant Kobla, Daniel Dementhon, David Doermann

Abstract- Automated classi cation of digital video is emerging as an important piece of the puzzle in the design of content management systems for digital libraries. The ability to classify videos...

A Theory Of Document Object Locator Combination (1998)

Jung Soh, Dr. Venugopal Govindaraju, Dr. Zhongfei Zhang, Dr. David Doermann

Traditional approaches to document object location use a single locator that is expected to locate as many instances of the object class of interest as possible. However, if the class includes...

Video Summarization by Curve Simplification (1998)

Daniel Dementhon Vikrant, Daniel Dementhon, Daniel Dementhon, Vikrant Kobla, Vikrant Kobla, David Doermann, ...

A video sequence can be represented as a trajectory curve in a high dimensional feature space. This video curve can be analyzed by tools similar to those developed for planar curves. In particular,...

The Indexing and Retrieval of Document Images: A Survey (1998)

David Doermann, David Doermann

The economic feasibility of maintaining large databases of document images has created a tremendous demand for robust ways to access and manipulate the information these images contain. In an attempt...

Video Summarization by Curve Simplifiation (1998)

Daniel Dementhon, Daniel Dementhon, Vikrant Kobla, Vikrant Kobla, David Doermann, David Doermann

A video sequence can be represented as a trajectory curve in a high dimensional feature space. This video curve can be analyzed by tools similar to those developed for planar curves. In particular,...

Automatic Text Tracking in Digital Videos (1998)

Huiping Li, David Doermann

In this paper we address the problem of automatically tracking moving text in digital videos. Our scheme consists of two separate processes: monitoring which detects the new text line entering a...

Indexing and Retrieval of MPEG Compressed Video (1998)

Vikrant Kobla, David Doermann

To keep pace with the increased popularity of digital video as an archival medium, the development of techniques for fast and efficient analysis of video streams is essential. In particular,...

Automatic Text Detection and Tracking in Digital Video (1998)

Huiping Li, Huiping Li, David Doermann, David Doermann, Omid Kia, Omid Kia

Text which either appears in a scene or is graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and...

Automatic Identification of Text In Digital Video Key Frames (1998)

Huiping Li, David Doermann

Scene and graphic text can provide important supplemental index information in video sequences. In this paper we address the problem automatically identifying text regions in digital video key...

Automatic Text Tracking in Digital Videos (1998)

Huiping Li, David Doermann

In this paper we address the problem of automatically tracking moving text in digital videos. Our scheme consists of two separate processes including monitoring which detects the new text line...

Lamp-Tr-0013 (1998)

David Doermann, David Doermann

The economic feasibilityofmaintaining large databases of document images has created a tremendous demand for robust ways to access and manipulate the information these images contain. In an attempt...

Compressed domain video indexing techniques using DCT and motion vector information in MPEG video (1997)

Vikrant Kobla, David Doermann, Christos Faloutsos

Development of various multimedia applications hinges on the availability of fast and efficient storage, browsing, indexing, and retrieval techniques. Given that video is typically stored efficiently...

Videotrails: Representing and visualizing structure in video sequences (1997)

Vikrant Kobla, David Doermann, Christos Faloutsos

The problem of determining the physical and semantic structure of an extended video sequence is essential for providing appropriate processing, indexing and retrieval capabilities for video...

The Detection of Duplicates in Document Image Databases (1997)

David Doermann, David Doermann, Huiping Li, Huiping Li, Omid Kia, Omid Kia, ...

Document imaging technology has developed to the point where it is not uncommon for organizations to scan large numbers of documents into databases with little or no index information. This may be...

VideoTrails (1997)

Representing And, Vikrant Kobla, David Doermann, Christos Faloutsos

The problem of determining the physical and semantic structure of an extended video sequence is essential for providing appropriate processing, indexing and retrieval capabilities for video...

Compressed domain video indexing techniques using DCT and motion vector information in MPEG video (1997)

Vikrant Kobla David, David Doermann, Christos Faloutsos

Development of various multimedia applications hinges on the availability of fast and efficient storage, browsing, indexing, and retrieval techniques. Given that video is typically stored efficiently...

Archiving, indexing, and retrieval of video in the compressed domain (1996)

Vikrant Kobla, David Doermann

Fast and efficient storage, indexing, browsing, and retrieval of video is a necessity for the development of various multimedia database applications. This can be achieved by analyzing the video...

The Representation of Document Structure: A Generic Object-Process Analysis (1996)

H. Bunke, Dov Dori, David Doermann, Christian Shin, Robert Haralick, Ihsin Phillips, ...

Document understanding has attained a level of maturity that requires migration from ad-hoc experimental systems, each of which employs its own set of assumptions and terms, into a solid, standard...

The Function of Documents (1996)

David Doermann, Ehud Rivlin, Azriel Rosenfeld

The purpose of a document is to facilitate the transfer of information from its author to its readers. It is the author's job to design the document so that the information it contains can be...

Archiving, Indexing, and Retrieval of Video in the Compressed Domain (1996)

Vikrant Kobla David, David Doermann

Fast and efficient storage, indexing, browsing, and retrieval of video is a necessity for the development of various multimedia database applications. This can be achieved by analyzing the video...

Compressed Domain Video Segmentation (1996)

Vikrant Kobla, David Doermann, Azriel Rosenfeld

Segmentation of video into shots and scenes in the compressed domain allows rapid, real-time analysis of video content using standard hardware. This paper presents robust techniques for parsing...

Generating Synthetic Data for Text Analysis Systems (1995)

David Doermann And, David Doermann, Shee Yao

In this paper we describe work on a system for modeling errors in the output of OCR systems. The project is motivated by the desire to evaluate the performance of various text analysis systems under...

The Representation of Document Structure: A Generic Object-Process Analysis (1995)

H. Bunke, Dov Dori, David Doermann, Christian Shin, Robert Haralick, Ihsin Phillips, ...

Document understanding has attained a level of maturity that requires migration from ad-hoc experimental systems, each of which employs its own set of assumptions and terms, into a solid, standard...

Document Understanding Research At Maryland (1994)

David Doermann

Research in the Computer Vision Laboratory at the University of Maryland covers a broad range of topics and applications related to visual processing. This paper highlights some recent and ongoing...

Document Page Segmentation by Integrating Distributed Soft Decisions (1994)

Kamran Etemad, Rama Chellappa, David Doermann

A new algorithm for image segmentation is suggested. The suggested algorithm is based on making local soft decisions on small blocks and integrating them to reduce their "ambiguities" and...

Page Segmentation Using Decision Integration and Wavelet Packets (1994)

Kamran Etemad, David Doermann, Rama Chellappa

A new algorithm for layout-independent document page segmentation is suggested. Text, image and graphics regions in a document image are treated as three different "texture" classes. Soft...

Basic Visual Capabilities (1993)

Cornelia Fermüller, David Doermann, Daniel Dementhon, Liuqing Huang, Radu Jasinschi, Ehud Rivlin, ...

tive Vision and especially Prof. Ruzena Bajcsy, Henrik Christianssen, Prof. Jim Crowley, Prof. Randal Nelson and Prof. Giulio Sandini were most useful in the development of my ideas. The help of...