Watson

A Unified Vision API

Since AlchemyAPI joined IBM Watson family in 2015, our goal has been to maintain a platform as unified and efficient as possible for all of our users. Today we will merge the AlchemyVision capabilities with the Visual Recognition service capabilities for a unified Watson Visual Recognition API.

Combined Visual Recognition Capabilities!

  • Image Tagging: “Give me natural language which describes this image.”
  • Face Detection: “Tell me if there is a person in this picture so I can identify them.”
  • Visual Learning: “Learn about my custom content in this image so I can create a unique classifier.”
  • Text from images(beta): “Transcribe any text or natural language contained in this image.”

Multi-class training comes to Visual Recognition

Our team has been hard at work brainstorming and building new capabilities for Visual Recognition. In addition to keeping existing features, the unified Visual Recognition will introduce multi-class training, improved algorithm accuracy, and faster performance.

With multi-class training and the ability to train for multiple custom visual classifiers at once, users will be able to identify and attribute images to more than two classes at a time, opening up possibilities to adapt Watson to a broader range of image recognition challenges.

Visual Recognition tackles global challenges

We love our customers who are already using Visual Recognition and solving pressing environmental and industry issues. Here are a few examples we’re excited to share!

OmniEarth uses Watson Visual Recognition to help California’s water districts

Water conservation is a top concern in drought-stricken California. At the beginning of 2014, the governor declared a state of emergency because the dire situation was affecting quality of life, agriculture and business. The state’s water districts needed a firm grasp of water usage patterns, where water was being overused, how much water could be saved, and where to target consumer outreach and education efforts. OmniEarth is helping the State of California analyze aerial images to monitor water consumption on each parcel of land across the state. Using IBM Watson Visual Recognition, OmniEarth adopted a cognitive visual solution that identifies topographical features in images, giving water districts insight into dynamic patterns of water consumption and weather.

Dory app wins Fishackathon NYC using Watson Visual Recognition

Dory app

Seafood fraud is a global issue affecting everyday consumers, disrupting the global fish market, compromising the health of the marine ecosystem, threatening endangered species, and much more. A local team won the U.S. Department of State-sponsored Fishackathon NYC using IBM Watson Visual Recognition to help with responsible and sustainable fishing practices by identifying mystery seafood.

We would love to hear from you! If you have any comments or questions, please reach out to us in the Watson forum or leave a comment below.

Share this post:

Share on LinkedIn

Add Comment
2 Comments

Leave a Reply

Your email address will not be published.Required fields are marked *


Pierre de Battista

Hello Melissa,

I have to implement a classifier for a huge quantity of data, requiring on premise processing.
Is this api available on premise, like alchemy before ?
In this case what is the pricing model ?

Best regards,
Pierre

Reply
More Watson Stories

Twilio Signal – Watson Services on Twilio Marketplace

At Twilio Signal, IBM announced that IBM Watson Message Sentiment and IBM Watson Message Insights will be available as Add-Ons in Twilio’s recently announced Marketplace.

Watson IoT Platform Removing Bronze, Silver and Gold Plans

The Watson Internet of Things (IoT) Platform will remove the Bronze, Silver and Gold Plans by December 31, 2017. If you're currently on any of these plans, please take three steps (yes only three!) to change to the Standard Plan.

Connect native Android app to Watson Text to Speech in under 10 minutes

Continuing the how-to Connect native Android app to Watson Sentiment Analysis in under 10 minutes, this post describes how you can quickly add Watson’s Text to Speech service to an Android app.