Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Physical Sciences and Mathematics
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 …