Watson

A Unified Vision API

Share this post:

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.

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 What's New Stories

Retirement of IBM Watson IoT Context Mapping

Thank you for using IBM Watson IoT Context Mapping On 12/21/2017 we are retiring the IBM Watson IoT Context Mapping

Continue reading

Closing the loop: the case for building a coherent platform for data science and machine learning

Many organizations have started to explore the value that machine learning can bring—from illuminating previously “dark data” such as images and videos, to creating models that help to guide or even automate business decision-making. However, very few companies have gone beyond pilots and prototypes, or made the transition from one-off projects to a scalable, repeatable workflow. Too often, machine learning exists in a bubble of its own, instead of being understood in the context of the broader data science workflow.

Continue reading

Watson Speech to Text and Text to Speech have released Lite Plans!

On Nov 1st, 2017, both Watson Speech to Text and Watson Text to Speech released Lite Plans, as part of IBM Cloud Platform’s initiative to roll out Lite Plans across public cloud services.

Continue reading