Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 30 of 59
Full-Text Articles in Physical Sciences and Mathematics
Bounding The Probability Of Error For High Precision Optical Character Recognition, Gary B. Huang, Andrew Kae, Carl Doersch, Erik G. Learned-Miller
Bounding The Probability Of Error For High Precision Optical Character Recognition, Gary B. Huang, Andrew Kae, Carl Doersch, Erik G. Learned-Miller
Erik G Learned-Miller
We consider a model for which it is important, early in proces sing, to estimate some variables with high precision, but perhaps at relatively low recall. I f some variables can be identified with near certainty, they can be conditioned upon, allowing furt her inference to be done efficiently. Specifically, we consider optical character recognition (O CR) systems that can be bootstrapped by identifying a subset of correctly translated document wo rds with very high precision. This “clean set” is subsequently used as document-specific train ing data. While OCR systems produce confidence measures for the identity of each letter or …
Learning To Align From Scratch, Gary Huang, Marwan Mattar, Honglak Lee, Erik Learned-Miller
Learning To Align From Scratch, Gary Huang, Marwan Mattar, Honglak Lee, Erik Learned-Miller
Erik G Learned-Miller
Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real-world images has required the careful selection of feature representation based on hand-crafted image descriptors, in order to achieve an appropriate, smooth optimization landscape. In this paper, we instead propose a novel combination of unsupervised joint alignment with unsupervised feature learning. Specifically, we incorporate deep learning into the congealing alignment framework. …
Distribution Fields For Tracking, Erik Learned-Miller, Laura Lara
Distribution Fields For Tracking, Erik Learned-Miller, Laura Lara
Erik G Learned-Miller
Visual tracking of general objects often relies on the assumption that gradient descent of the alignment function will reach the global optimum. A common technique to smooth the objective function is to blur the image. However, blurring the image destroys image information, which can cause the target to be lost. To address this problem we introduce a method for building an image descriptor using distribution fields (DFs), a representation that allows smoothing the objective function without destroying information about pixel values. We present experimental evidence on the superiority of the width of the basin of attraction around the global optimum …
Background Modeling Using Adaptive Pixelwise Kernel Variances In A Hybrid Feature Space, Erik G. Learned-Miller, Manjunath Narayana, Allen Hanson
Background Modeling Using Adaptive Pixelwise Kernel Variances In A Hybrid Feature Space, Erik G. Learned-Miller, Manjunath Narayana, Allen Hanson
Erik G Learned-Miller
Recent work on background subtraction has shown de- velopments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mix- tures of Gaussians at each pixel [ 7 ], to kernel density esti- mates at each pixel [ 1 ], and more recently to joint domain- range density estimates that incorporate spatial informa- tion [ 6 ]. Another line of work has shown the benefits of increasingly complex feature representations, including the use of texture information, local binary patterns, and re- cently scale-invariant local ternary patterns [ 4 ]. In this work, we use joint …
Scene Text Recognition With Bilateral Regression, Jacqueline Feild, Erik G. Learned-Miller
Scene Text Recognition With Bilateral Regression, Jacqueline Feild, Erik G. Learned-Miller
Erik G Learned-Miller
This paper focuses on improving the recognition of text in images of natural scenes, such as storefront signs or street signs. This is a difficult problem due to lighting conditions, variation in font shape and color, and complex backgrounds. We present a word recognition system that addresses these difficulties using an innovative technique to extract and recognize foreground text in an image. First, we develop a new method, called bilateral regression, for extracting and modeling one coherent (although not necessarily contiguous) region from an image. The method models smooth color changes across an image region without being corrupted by neighboring …
Unsupervised Joint Alignment And Clustering Using Bayesian Nonparametrics, Marwan Mattar, Allen Hanson, Erik G. Learned-Miller
Unsupervised Joint Alignment And Clustering Using Bayesian Nonparametrics, Marwan Mattar, Allen Hanson, Erik G. Learned-Miller
Erik G Learned-Miller
Joint alignment of a collection of functions is the process of independently transforming the func- tions so that they appear more similar to each other. Typically, such unsupervised alignment al- gorithms fail when presented with complex data sets arising from multiple modalities or make re- strictive assumptions about the form of the func- tions or transformations, limiting their general- ity. We present a transformed Bayesian infinite mixture model that can simultaneously align and cluster a data set. Our model and associated learning scheme offer two key advantages: the optimal number of clusters is determined in a data-driven fashion through the …
Learning Hierarchical Representations For Face Verification, Gary B. Huang, Honglak Lee, Erik G. Learned-Miller
Learning Hierarchical Representations For Face Verification, Gary B. Huang, Honglak Lee, Erik G. Learned-Miller
Erik G Learned-Miller
Most modern face recognition systems rely on a feature representation given by a hand-crafted image descriptor, such as Local Binary Patterns (LBP), and achieve improved performance by combining several such representations. In this paper, we propose deep learning as a natural source for obtaining additional, complementary representations. To learn features in high-resolution images, we make use of convolutional deep belief networks. Moreover, to take advantage of global structure in an object class, we develop local convolutional restricted Boltzmann machines, a novel convolutional learning model that exploits the global structure by not assuming stationarity of features across the image, while maintaining …
Half-Wits: Software Techniques For Low-Voltage Probabilistic Storage On Microcontrollers With Nor Flash Memory., Mastooreh Salajegheh, Yue Wang, Anxiao Jiang, Erik G. Learned-Miller, Kevin Fu
Half-Wits: Software Techniques For Low-Voltage Probabilistic Storage On Microcontrollers With Nor Flash Memory., Mastooreh Salajegheh, Yue Wang, Anxiao Jiang, Erik G. Learned-Miller, Kevin Fu
Erik G Learned-Miller
No abstract provided.
Improvements In Joint Domain-Range Modeling For Background Subtraction, Manjunath Narayana, Allen Hanson, Erik G. Learned-Miller
Improvements In Joint Domain-Range Modeling For Background Subtraction, Manjunath Narayana, Allen Hanson, Erik G. Learned-Miller
Erik G Learned-Miller
In many algorithms for background modeling, a distribution over feature values is modeled at each pixel. These models, however, do not account for the dependencies that may exist among nearby pixels. The joint domain-range kernel density estimate (KDE) model by Sheikh and Shah [ 7 ], which is not a pixel-wise model, represents the background and foreground processes by combining the three color dimensions and two spatial dimensions into a five-dimensional joint space. The Sheikh and Shah model, as we will show, has a peculiar dependence on the size of the image. In contrast, we build three-dimensional color distributions at …
Enforcing Similarity Constraints With Integer Programming For Better Scene Text Recognition, David L. Smith, Jacqueline Feild, Erik G. Learned-Miller
Enforcing Similarity Constraints With Integer Programming For Better Scene Text Recognition, David L. Smith, Jacqueline Feild, Erik G. Learned-Miller
Erik G Learned-Miller
The recognition of text in everyday scenes is made dif- ficult by viewing conditions, unusual fonts, and lack of lin- guistic context. Most methods integrate a priori appear- ance information and some sort of hard or soft constraint on the allowable strings. Weinman and Learned-Miller [ 14 ] showed that the similarity among characters, as a supple- ment to the appearance of the characters with respect to a model, could be used to improve scene text recognition. In this work, we make further improvements to scene text recognition by taking a novel approach to the incorpora- tion of similarity. In …
Forensic Triage For Mobile Phones With Dec0de, Robert Walls, Brian N. Levine, Erik G. Learned-Miller
Forensic Triage For Mobile Phones With Dec0de, Robert Walls, Brian N. Levine, Erik G. Learned-Miller
Erik G Learned-Miller
We present DEC0DE, a system for recovering information from phones with unknown storage formats, a critical problem for forensic triage. Because phones have myr- iad custom hardware and software, we examine only the stored data. Via flexible descriptions of typical data struc- tures, and using a classic dynamic programming algo- rithm, we are able to identify call logs and address book entries in phones across varied models and manufactur- ers. We designed DEC0DE by examining the formats of one set of phone models, and we evaluate its performance on other models. Overall, we are able to obtain high performance for …
Distribution Fields, Laura Sevilla Lara, Erik G. Learned-Miller
Distribution Fields, Laura Sevilla Lara, Erik G. Learned-Miller
Erik G Learned-Miller
No abstract provided.
Online Domain-Adaptation Of A Pre-Trained Cascade Of Classifiers, Vidit Jain, Erik G. Learned-Miller
Online Domain-Adaptation Of A Pre-Trained Cascade Of Classifiers, Vidit Jain, Erik G. Learned-Miller
Erik G Learned-Miller
Many classifiers are trained with massive training sets only to be applied at test time on data from a different dis- tribution. How can we rapidly and simply adapt a classifier to a new test distribution, even when we do not have ac- cess to the original training data? We present an on-line approach for rapidly adapting a “black box” classifier to a new test data set without retraining the classifier or ex- amining the original optimization criterion. Assuming the original classifier outputs a continuous number for which a threshold gives the class, we reclassify points near the ori g- …
Exploiting Half-Wits: Smarter Storage For Low-Power Devices, Mastooreh Salajegheh, Yue Wang, Kevin Fu, Anxiao Jiang, Erik G. Learned-Miller
Exploiting Half-Wits: Smarter Storage For Low-Power Devices, Mastooreh Salajegheh, Yue Wang, Kevin Fu, Anxiao Jiang, Erik G. Learned-Miller
Erik G Learned-Miller
This work analyzes the stochastic behavior of writing to embedded flash memory at voltages lower than recom- mended by a microcontroller’s specifications to reduce energy consumption. Flash memory integrated within a microcontroller typically requires the entire chip to op- erate on common supply voltage almost double what the CPU portion requires. Our approach tolerates a lower supply voltage so that the CPU may operate in a more en- ergy efficient manner. Energy efficient coding algorithms then cope with flash memory that behaves unpredictably. Our software-only coding algorithms ( in-place writes , multiple-place writes , RS-Berger codes ) enable reliable storage …
Fddb: A Benchmark For Face Detection In Unconstrained Settings, Vidit Jain, Erik Learned-Miller
Fddb: A Benchmark For Face Detection In Unconstrained Settings, Vidit Jain, Erik Learned-Miller
Erik G Learned-Miller
Despite the maturity of face detection research, it re- mains difficult to compare different algorithms for face de- tection. This is partly due to the lack of common evaluation schemes. Also, existing data sets for evaluating face detec- tion algorithms do not capture some aspects of face appear- ances that are manifested in real-world scenarios. In this work, we address both of these issues. We present a new data set of face images with more faces and more accurate annotations for face regions than in previous data sets. We also propose two rigorous and precise methods for evaluat- ing the …
Improving State-Of-The-Art Ocr Through High-Precision Document-Specific Modeling, Andrew Kae, Gary B. Huang, Carl Doersch, Erik G. Learned-Miller
Improving State-Of-The-Art Ocr Through High-Precision Document-Specific Modeling, Andrew Kae, Gary B. Huang, Carl Doersch, Erik G. Learned-Miller
Erik G Learned-Miller
Optical character recognition (OCR) remains a difficult problem for noisy documents or documents not scanned at high resolution. Many current approaches rely on stored font models that are vulnerable to cases in which the docu- ment is noisy or is written in a font dissimilar to the stored fonts. We address these problems by learning character models directly from the document itself, rather than using pre-stored font models. This method has had some success in the past, but we are able to achieve substantial improve- ment in error reduction through a novel method for creating nearly error-free document-specifictraining data and …
Reverse Engineering For Mobile Systems Forensics With Ares, John Tuttle, Robert J. Walls, Erik G. Learned-Miller, Brian Neil Levine
Reverse Engineering For Mobile Systems Forensics With Ares, John Tuttle, Robert J. Walls, Erik G. Learned-Miller, Brian Neil Levine
Erik G Learned-Miller
We present Ares ,areverseengineeringtechniqueforassist- ing in the analysis of data recovered for the investigation of mobile and embedded systems. The focus of investigations into insider activity is most often on the data stored on the insider’s computers and digital devices — call logs, email messaging, calendar entries, text messages, and browser his- tory — rather than on the status of the system’s security. Ares is novel in that it uses a data-driven approach that in- corporates natural language processing techniques to infer the layout of input data that has been created according to some unknown specification. While some other reverse …
Learning Class-Specific Image Transformations With Higher-Order Boltzmann Machines, Erik G. Learned-Miller, Gary Huang
Learning Class-Specific Image Transformations With Higher-Order Boltzmann Machines, Erik G. Learned-Miller, Gary Huang
Erik G Learned-Miller
In this paper, we examine the problem of learning a rep- resentation of image transformations specific to a complex object class, such as faces. Learning such a representation for a specific object class would allow us to perform im- proved, pose-invariant visual verification, such as uncon- strained face verification. We build off of the method of using factored higher-order Boltzmann machines to model such image transformations. Using this approach will po- tentially enable us to use the model as one component of a larger deep architecture. This will allow us to use the fea- ture information in an ordinary deep …
Learning On The Fly: Font Free Approaches To Difficult Ocr Problems, Andrew Kae, Erik Learned-Miller
Learning On The Fly: Font Free Approaches To Difficult Ocr Problems, Andrew Kae, Erik Learned-Miller
Erik G Learned-Miller
Despite ubiquitous claims that optical character recog- nition (OCR) is a “solved problem,” many categories of documents continue to break modern OCR software such as documents with moderate degradation or unusual fonts. Many approaches rely on pre-computed or stored charac- ter models, but these are vulnerable to cases when the font of a particular document was not part of the training set, or when there is so much noise in a document that the font model becomes weak. To address these difficult cases, we present a form of iterative contextual modeling that learns character models directly from the document it …
Bounding The Probability Of Error For High Precision Recognition, Andrew Kae, Gary B. Huang, Erik G. Learned-Miller
Bounding The Probability Of Error For High Precision Recognition, Andrew Kae, Gary B. Huang, Erik G. Learned-Miller
Erik G Learned-Miller
We consider models for which it is important, early in proces sing, to estimate some variables with high precision, but perhaps at relative ly low rates of recall. If some variables can be identified with near certainty, then th ey can be conditioned upon, allowing further inference to be done efficiently. Spe cifically, we consider optical character recognition (OCR) systems that can be boo tstrapped by identify- ing a subset of correctly translated document words with ver y high precision. This “clean set” is subsequently used as document-specific train ing data. While many current OCR systems produce measures of confidence …
Non-Parametric Curve Alignment, Marwan Mattar, Michael G. Ross, Erik G. Learned-Miller
Non-Parametric Curve Alignment, Marwan Mattar, Michael G. Ross, Erik G. Learned-Miller
Erik G Learned-Miller
Congealing is a flexible nonparametric data-driven framework for the joint alignment of data. It has been successfully applied to the joint alignment of binary images of digits, binary images of object silhouettes, grayscale MRI images, color images of cars and faces, and 3D brain volumes. This research enhances congealing to practically and effectively apply it to curve data. We develop a parameterized set of nonlinear transformations that allow us to apply congealing to this type of data. We present positive results on aligning synthetic and real curve data sets and conclude with a discussion on extending this work to simultaneous …
Cryptogram Decoding For Optical Character Recognition, Gary Huang, Erik G. Learned-Miller, Andrew Mccallum
Cryptogram Decoding For Optical Character Recognition, Gary Huang, Erik G. Learned-Miller, Andrew Mccallum
Erik G Learned-Miller
OCR systems for printed documents typically require large numbers of font styles and character models to work well. When given an unseen font, performance degrades even in the absence of noise. In this paper, we perform OCR in an unsupervised fashion without using any character models by using a cryptogram decoding algorithm. We present results on real and artificial OCR data.
The Umass Mobile Manipulator Uman: An Experimental Platform For Autonomous Mobile Manipulation, Dov Katz, Emily Horrell, Yuandong Yang, Brendan Burns, Thomas Buckley, Anna Grishkan, Volodymyr Zhylkovskyy, Oliver Brock, Erik G. Learned-Miller
The Umass Mobile Manipulator Uman: An Experimental Platform For Autonomous Mobile Manipulation, Dov Katz, Emily Horrell, Yuandong Yang, Brendan Burns, Thomas Buckley, Anna Grishkan, Volodymyr Zhylkovskyy, Oliver Brock, Erik G. Learned-Miller
Erik G Learned-Miller
Object identification is the task of identifying specific objects belonging to the same class such as cars. We often need to recognize an object that we have only seen a few times. In fact, we often observe only one example of a particular object before we need to recognize it again. Thus we are interested in building a system which can learn to extract distinctive markers from a single example and which can then be used to identify the object in another image as “same ” or “different”. Previous work by Ferencz et al. introduced the notion of hyper-features, which …
Combinatorial Markov Random Fields, Ron Bekkerman, Erik Learned-Miller
Combinatorial Markov Random Fields, Ron Bekkerman, Erik Learned-Miller
Erik G Learned-Miller
A combinatorial random variable is a discrete random variable defined over a combinatorial set (e.g., a power set of a given set). In this paper we introduce combinatorial Markov random fields (Comrafs), which are Markov random fields where some of the nodes are combinatorial random variables. We argue that Comrafs are powerful models for unsupervised and semi-supervised learning. We put Comrafs in perspective by showing their relationship with several existing models. Since it can be problematic to apply existing inference techniques for graphical models to Comrafs, we design two simple and efficient inference algorithms specific for Comrafs, which are based …
Improved Generative Models For Continuous Image Features Through Tree-Structured Non-Parametric Distributions, Marwan Mattar, Erik Learned-Miller
Improved Generative Models For Continuous Image Features Through Tree-Structured Non-Parametric Distributions, Marwan Mattar, Erik Learned-Miller
Erik G Learned-Miller
Density estimation arises in a wide range of vision problems and methods which can deal with high dimensional image features are of great importance. While in principle a non- parametric distribution can be estimated for the full featu re distribution using Parzen win- dows technique, the amount of data to make these estimates accurate is usually either unattainable or unmanageable. Consequently, most modelers resort to parametric models such as mixtures of Gaussians (or other more complicated parametric forms) or make in- dependence assumptions about the features. Such assumptions could be detrimental to the performance of vision systems since realistically, image …
The Processing And Analysis Of In Situ Gene Expression Images Of The Mouse Brain, Manjunatha Jagalur1,, Chris Pal, Erik Learned-Miller, R Zoeller, David Kulp
The Processing And Analysis Of In Situ Gene Expression Images Of The Mouse Brain, Manjunatha Jagalur1,, Chris Pal, Erik Learned-Miller, R Zoeller, David Kulp
Erik G Learned-Miller
Many important high throughput projects use in situ gene expression detection technology and require the analysis of images of spatial cross sections of organisms taken at cellular level resolution. Projects creating gene expression atlases at unprecedented scales for the embryonic fruit fly as well as the embryonic and adult mouse already involve the analysis of hundreds of thousands of high resolution experimental images. We present an end-to-end approach for processing raw in situ expression imagery and performing subsequent analysis. We use a nonlinear image registration technique specifically adapted for mapping expression images to anatomical annotations and a method for extracting …
Detecting Acromegaly: Screening For Disease With A Morphable Model, Erik G. Learned-Miller, Qifeng Lung, Angela Paisley, Peter Trainer, Volker Blanz, Katrin Dedden, Ralph Miller
Detecting Acromegaly: Screening For Disease With A Morphable Model, Erik G. Learned-Miller, Qifeng Lung, Angela Paisley, Peter Trainer, Volker Blanz, Katrin Dedden, Ralph Miller
Erik G Learned-Miller
Acromegaly is a rare disorder which affects about 50 of every million people. The disease typically causes swelling of the hands, feet, and face, and eventually permanent changes to areas such as the jaw, brow ridge, and cheek bones. The disease is often missed by physicians and progresses beyond where it might if it were identified and treated earlier. We consider a semi-automated approach to detecting acromegaly, using a novel combination of support vector machines (SVMs) and a morphable model. Our training set consists of 24 frontal photographs of acromegalic patients and 25 of disease-free subjects. We modelled each subject's …
Data Driven Image Models Through Continuous Joint Alignment, Erik G. Learned-Miller
Data Driven Image Models Through Continuous Joint Alignment, Erik G. Learned-Miller
Erik G Learned-Miller
This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar as possible by removing variability along the known axes of variation. This technique can be used to eliminate "nuisance” variables such as affine deformations from handwritten digits or unwanted bias fields from magnetic resonance images. In addition to separating and modeling the latent images—i.e., the images without the nuisance variables—we can model the nuisance variables themselves, leading to factorized generative image models. When nuisance variable distributions are …
Joint Feature Selection For Object Detection And Recognition, Jerod J. Weinman, Allen Hanson, Erik G. Learned-Miller
Joint Feature Selection For Object Detection And Recognition, Jerod J. Weinman, Allen Hanson, Erik G. Learned-Miller
Erik G Learned-Miller
Object detection and recognition systems, such as face detectors and face recognizers, are often trained separately and operated in a feed-forward fashion. Selecting a small number of features for these tasks is important to prevent over-fitting and reduce computation. However, when a system has such related or sequential tasks, selecting features for these tasks independently may not be optimal. We propose a framework for choosing features to be shared between object detection and recognition tasks. The result is a system that achieves better performance by joint training and is faster because some features for identification have already been computed for …
Discriminative Training Of Hyper-Feature Models For Object Identification, Vidit Jain, Erik G. Learned-Miller
Discriminative Training Of Hyper-Feature Models For Object Identification, Vidit Jain, Erik G. Learned-Miller
Erik G Learned-Miller
Object identification is the task of identifying specific objects belonging to the same class such as cars. We often need to recognize an object that we have only seen a few times. In fact, we often observe only one example of a particular object before we need to recognize it again. Thus we are interested in building a system which can learn to extract distinctive markers from a single example and which can then be used to identify the object in another image as “same ” or “different”. Previous work by Ferencz et al. introduced the notion of hyper-features, which …