Loading...
WeSee: Deep Learning-based Computer Vision 2017-11-08T08:45:06+00:00

Powerful image and video recognition technology that enables you to match and understand content in milliseconds.

How Does It Work?

Visual Intelligence On-Demand

WeSee doesn’t just see visual content, it understands every multi-layered element within images and videos. Using biologically-inspired artificial intelligence, WeSee comprehends the visual world in the same way as humans do.

Automatically harness the opportunities and value hidden inside all images and videos in order to revolutionise the way you work, live, appear and interact with others.

  • Recognise faces from side or low-light not just frontal
  • Highlight brands from related products and imagery
  • See objects even when distorted or partly concealed
  • Even soft focus, continually moving or motion blurred

0M
IMAGES PROCESSED PER HOUR*
0X
FASTER THAN HUMANS*
0M hrs
VIDEOS PROCESSED PER YEAR*

*all capabilities are increasing continually and based on client requirements

SCALABLE

Infinite scalability and capable of processing big data archives

ACCURATE

90%

Average accuracy is in excess of 90%*

FLEXIBLE

Fully flexible with ability to create and detect bespoke visual categories

For those who video

WeSee enables content owners to accurately define, categorise and surface relevant long- or short-form content for brand advertisers to connect with consumers – and consumers to connect with the content they love.

  • Automatic Tagging
  • Content Analysis
  • Campaign Targeting
  • Image Intelligence

  • Visual Analytics
  • Brand Safety

“THE WORLD’S MOST ADVANCED VIDEO CATEGORISATION TECHNOLOGY.”

Why choose wesee?

WeSee revolutionises image recognition by not requiring metadata

Parsing multiple simultaneous layers of information, WeSee can convey the actual subject matter of images and videos, bringing contextual insights to visual content.

Logos and Objects

Recognise brand trademarks, graphical elements and objects – even when obscure or moving.

Logos and Objects

Recognise brand trademarks, graphical elements and objects – even when obscure or moving.

Facial Recognition

Identify individuals and groups of people from multiple angles while performing activities.

Facial Recognition

Identify individuals and groups of people from multiple angles while performing activities.

Shot Change Detection

Detect context and scene changes, varied angles and shot boundaries within video streams.

Shot Change Detection

Detect context and scene changes, varied angles and shot boundaries within video streams.

Visual Classification

Categorise content with customised granular taxonomies or industry standards.

Visual Classification

Categorise content with customised granular taxonomies or industry standards.

Pattern Matching

Find visually similar content in order to serve recommendations or related content in real-time.

Pattern Matching

Find visually similar content in order to serve recommendations or related content in real-time.

Negative Content

Filter degrees of nudity, gore, violence, language and profanity by assignable thresholds.

Negative Content

Filter degrees of nudity, gore, violence, language and profanity by assignable thresholds.

Text Mining

Pull keyword and topics directly from subtitles/captioning, speech and transcripts.

Text Mining

Pull keyword and topics directly from subtitles/captioning, speech and transcripts.

Audio Semantics

Extract meaning from an audio stream, such as sounds, music or speech recognition.

Audio Semantics

Extract meaning from an audio stream, such as sounds, music or speech recognition.

Auto-Content Recognition

Certify content played or present in a media file through prior ACR-embedded tags.

Auto-Content Recog.

Certify content played or present in a media file through prior ACR-embedded tags.

Emotional Sentiment

Analyse facial expressions that denote emotions, feelings, intentions and moods. (BETA)

Emotional Sentiment

Analyse facial expressions that denote emotions, feelings, intentions and moods. (BETA)

Human Deceit

Detect whether someone is lying via suspicious behaviour, pupil dilation and micro expressions. (BETA)

Human Deceit

Detect whether someone is lying via suspicious behaviour, pupil dilation and micro expressions. (BETA)

Language Processing

Evaluate speech using natural language processing (NLP) to match voice biometric information. (BETA)

Language Processing

Evaluate speech using natural language processing (NLP) to match voice biometric information. (BETA)

Built to be versatile, scalable and platform-agnostic to solve a multitude of industry issues.

Don’t take our word for it

Our video and image recognition technology is suitable for a broad range of industries: Media, Finance, Recruitment, Entertainment, Insurance, Real Estate, Travel, Automotive, Defence or Medical.

WHAT’S YOUR NEED?

     Let us deliver the solution.