A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Text segmentation using Gabor filters for automatic document processing
Machine Vision and Applications - Special issue: document image analysis techniques
Fast software for box intersections
Proceedings of the sixteenth annual symposium on Computational geometry
k-anonymity: a model for protecting privacy
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
Image Segmentation by Jensen-Shannon Divergence. Application to Measurement of Interfacial Tension
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
L-diversity: Privacy beyond k-anonymity
ACM Transactions on Knowledge Discovery from Data (TKDD)
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
Designing and deploying usetube, google's global user experience observation and recording system.
CHI '09 Extended Abstracts on Human Factors in Computing Systems
Sikuli: using GUI screenshots for search and automation
Proceedings of the 22nd annual ACM symposium on User interface software and technology
Least squares quantization in PCM
IEEE Transactions on Information Theory
Optimal Gabor filters for texture segmentation
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
As information technology permeates healthcare (particularly provider-facing systems), maximizing system effectiveness requires the ability to document and analyze tricky or troublesome usage scenarios. However, real-world health IT systems are typically replete with privacy-sensitive data regarding patients, diagnoses, clinicians, and EMR user interface details; instrumentation for screen capture (capturing and recording the scenario depicted on the screen) needs to respect these privacy constraints. Furthermore, real-world health IT systems are typically composed of modules from many sources, mission-critical and often closed-source; any instrumentation for screen capture can rely neither on access to structured output nor access to software internals. In this paper, we present a tool to help solve this problem: a system that combines keyboard video mouse (KVM) capture with automatic text redaction (and interactively selectable unredaction) to produce precise technical content that can enrich stakeholder communications and improve end-user influence on system evolution. KVM-based capture makes our system both application-independent and OS-independent because it eliminates software-interface dependencies on capture targets. Using a corpus of EMR screenshots, we present empirical measurements of redaction effectiveness and processing latency to demonstrate system performances. We discuss how these techniques can translate into instrumentation systems that improve real-world health IT deployments.