San Diego Java User's Group

Speakers: Zoran Sevarac, Kevin Berendsen and Frank Greco

Title: JSR381 - Visual Recognition for Java - A Java-Friendly ML API

Abstract: Learn about JSR381, Visual Recognition for Java, which is a Java-friendly machine learning API to detecting objects.

We all know Machine Learning (ML) is a huge, long-term global trend that affects every part of the stack from the user to the hardware. All developers, especially Java developers, need to understand how to build apps that use ML.

Visual Recognition (VisRec) is an important subclass of ML. There are wide business applications for visual recognition across many types of industries and use cases.

But for Java developers, there doesn’t seem to be many coding options other than learning Python. The current ML libraries available for Java developers have several issues. They either are very complex and designed for data scientists, or they are Java wrappers around C/C++ libraries and don’t “feel” like Java tools.

But now there is JSR381, a Java-friendly API for ML. We’ll talk about goals with JSR381, the API, its internal architecture, and run some cool examples. We even have a Star Wars demo that detects Tie Fighters in case they buzz your house!

Speaker Bios: Zoran Sevarac University of Belgrade, Java Champion, NetBeans Dream Team, JSR381 Spec Lead
Kevin Berendsen - Senior Software Engineer, OpenValue, JSR381 Expert Group
Frank Greco - NYJavaSIG Chair, Java Champion, Cloud/ML Consultant, JSR381 Spec Lead

JSR381 INFORMATION:
JCP.org : https://jcp.org/en/jsr/detail?id=381
JSR Repo : github.com/JavaVisRec
Getting Started : github.com/JavaVisRec/visrec-api/wiki/Getting-Started-Guide
Examples : github.com/JavaVisRec/jsr381-examples
API : github.com/JavaVisRec/visrec-api
Mailing List : visrec@groups.io