Skip to content
This repository was archived by the owner on Nov 18, 2020. It is now read-only.

Home

Jump to bottom
Scott D'Angelo edited this page Jan 8, 2018 · 2 revisions

Short Name

Watson Vehicle Damage Analyzer

Short Description

Create a custom classifier for visual recognition using images of automobile damage.

Offering Type

Cognitive

Introduction

We'll create a Visual Recognition custom classifier to identify issues with automobiles, such as a flat tire, broken window, or vandalism, and a server that will use this classifier given an uploaded image. We'll also create a mobile app that takes a picture of an automobile problem to sent to a server for classification.

Author

By Scott D'Angelo

Code

https://github.com/IBM/watson-vehicle-damage-analyzer

Demo

N/A

Video

https://youtu.be/rVL1HsbsdBI

Overview

In this developer code pattern, we will create a mobile app using Apache Cordova, Node.js and Watson Visual Recognition. This mobile app sends pictures of auto and motorcycle accidents and issues to be analyzed by a server app, using Watson Visual Recognition. The server application will use pictures of auto accidents and other incidents to train Watson Visual Recognition to identify various classes of issues, i.e. vandalism, broken windshield, motorcycle accidnet, or flat tire. A developer can leverage this to create their own custom Visual Recognition classifiers for their use cases.

When the reader has completed this Code Pattern, they will understand how to:

Create a Node.js server that can utilize the Watson Visual Recognition service for classifying images. Have a server initialize a Visual Recognition custom classifier at startup. Create a Visual Recognition custom classifier in an application. Create an Android mobile application that can send pictures to a server app for classification using Visual Recognition.

Flow

  1. User interacts with the mobile app and captures an image.
  2. The image on the mobile phone is passed to the server application running in the cloud.
  3. The server sends the image to Watson Visual Recognition Service for analysis.
  4. Visual Recognition service classifies the image and returns the information to the server.

Included components

  • Watson Visual Recognition: Visual Recognition understands the contents of images - visual concepts tag the image, find human faces, approximate age and gender, and find similar images in a collection.

Featured technologies

  • Mobile: Systems of engagement are increasingly using mobile technology as the platform for delivery.
  • Node.js: An asynchronous event driven JavaScript runtime, designed to build scalable applications

Blog

Blog Title

Blog Author

Blog Content

Links

Clone this wiki locally