Elizabeth Christiansen

Title: Innovations by Elizabeth Christiansen

Introduction

Elizabeth Christiansen is a notable inventor based in London, GB. She has made significant contributions to the field of anomaly detection in document images. With a total of 2 patents, her work focuses on enhancing the accuracy and efficiency of identifying anomalies in various types of documents.

Latest Patents

One of her latest patents is titled "Generalized Anomaly Detection." This patent describes methods and systems for training a system to detect anomalies in images of documents within a specific class. The process involves obtaining a plurality of training document images, segmenting them into regions of interest, and applying various transformations to generate features and anomaly scores. A transform-specific threshold is then computed to differentiate between document images containing anomalies and those that do not.

Another significant patent is "Signal-Based Machine Learning Fraud Detection." This invention outlines methods for training a machine learning model to detect anomalies in document images. The process begins with obtaining images that relate to specific regions of documents, including both anomalous and non-anomalous examples. Signal processing algorithms are applied to these images to generate signals, and the discriminative power of each algorithm is evaluated. Based on this evaluation, a suitable algorithm is selected to generate input data for training the machine learning model.

Career Highlights

Elizabeth currently works at Onfido Ltd., where she continues to develop innovative solutions in the field of document verification and fraud detection. Her expertise in machine learning and signal processing has positioned her as a key player in her organization.

Collaborations

Some of her notable coworkers include Philip Botros and Roberto Annunziata, who contribute to the collaborative environment at Onfido Ltd. Their combined efforts enhance the development of advanced technologies in the industry.

Conclusion

Elizabeth Christiansen's work in anomaly detection and machine learning represents a significant advancement in the field of document analysis. Her innovative patents and contributions to Onfido Ltd. highlight her role as a leading inventor in this domain.