You are viewing content from a past/completed QCon

Presentation: Detecting Similar Id Documents Using Deep Learning

Track: Deep Learning Applications & Practices

Location: Cyril Magnin I

Duration: 2:20pm - 2:30pm

Day of week: Wednesday

Share this on:


Identity verification is the process in which we digitally confirm the legitimacy of a real world document. This process is necessary for many businesses to meet their compliance requirements and mitigate their fraud risk. A common form of fraud is the duplication and alteration of stolen documents across multiple user accounts. In this talk, we will discuss how Coinbase solves the problem of detecting similar identity documents using deep learning.

Speaker: Burkay Gur

Risk Engineer @Coinbase

Find Burkay Gur at

2019 Tracks

  • Groking Timeseries & Sequential Data

    Techniques, practices, and approaches around time series and sequential data. Expect topics including image recognition, NLP/NLU, preprocess, & crunching of related algorithms.

  • Deep Learning in Practice

    Deep learning use cases around edge computing, deep learning for search, explainability, fairness, and perception.