Discover, Connect & Collaborate at TECHINNOVATION 2021

Leading Emotion Recognition AI

Technology Overview

We offer healthcare grade technology that utilises a highly accurate Psychology Circumplex Model resulting in more precise emotion measurements with multi-dimension data points. Our solution offers Thousands of Mood Detection versus 7 basic labelling that accounts for ethnicity and cultural differences. Real-Time facial expressions analytics of large crowds and individuals with highest accuracy of up to 93%.

The strength of our algorithm results from the volume and granularity with patients and non-patients’ scientific investigation. This genuine data enables it to detect and assess a broad range of emotions with precision. Annotated datasets from various phycological fields are used to train our algorithm to recognizes minutiae scale of emotions for further affective computing research on multimodal speech, physiological signals and gestures.

Our emotion analytics runs on popular platforms, any device with camera or wearable optical devices. It requires less than 1 GHz processing on the Edge with minimum bandwidth needed. We offer SDK with APIs libraries to create new applications with 3rd party development.

Our AI can be used in mental health analysis, vehicle safety, education, unbiased emotion feedback for advertising and public security. Emotion AI have also been deployed for audience measurement, customer satisfaction, human resources and training.

We seek to partner system integrators and manufacturers of cameras and micro-processors, currently in the OEMs / SDK to incorporate Emotion Recognition A.I into their end devices. IoTs and Smart Nation providers for surveillance, wearable and end sensing devices.

Technology Features, Specifications and Advantages

With over 10 years of R&D and commercial collaboration in the field of human–computer interaction, our technology developed in A*STAR advocates a perfect discernment of emotions with high accuracy and natural capabilities of extracting concealed feelings.

The strength of our algorithm results from the volume and granularity with patients and non-patients scientific investigation. This genuine data enables it to detect and assess a broad range of emotions with precision.

Unique selling propositions :

  • Only one in the world using psychology circumplex model with 2 Dimensions subtle expressions analyses
  • Real-time processing and analysis for individual and large group emotional state. Only single expression from competitors
  • Technology accounts for ethnicity and cultural differences with high accuracy especially in negative expression
  • Millions have been invested with over 5 years of R&D and 7 International Awards and Accolades (Proven accuracy of 93%)

Potential Applications

  • Media & Advertising industry to use for analysing buyer emotional reactions to videos and ads, improve targeted marketing and sales campaign.
  • Digital Out Of Home (DOOH) for audience and context-aware signage displays that leverage the emotion of audience behaviour.
  • Focus group and FMCG market research to identify key emotional indicators and make improvements in products and services
  • Emotional feedback surveys to capture unbiased consumer reaction data.
  • Talent recruitment in emotional analysis with Pre-Employment Screening, Assessment Testing to Increase accuracy.
  • Gaming to understand gamer emotions and adapt to create more immersive games and providing gamers ability to drive gameplay with their emotions.
  • Automotive and taxis for emotion of drivers and passengers, integrated into infotainment systems and Advanced Driver Assistance Systems.
  • Retail & Hospitality to interact and assist shoppers, greet customers at the store entrance or customer service desk.
  • Healthcare monitor and analyse mental health, hyper-connected devices to measure and track emotions sense, measure and analyse wellbeing.
  • IoT for surveillance, enable robotics with emotional intelligence, making them truly social, empathic and more effective.
  • Education with measure of real-time learner emotional responses to educational content.
  • Public safety by adding another layer to security at malls, airports, sports arenas, and other public venues to detect malicious intent with emotion detection.

In the post COVID-19 scenario, the global emotion detection and recognition market size is projected to grow from USD 19.5 billion in 2020 to USD 37.1 billion by 2026, at a Compound Annual Growth Rate (CAGR) of 11.3% during the forecast period.

Customer Benefits

  • Gain Emotion insights in a non-intrusive for content, A/B testing and packaging.
  • Boost content designed in a practical approach beyond the spoken or written feedback, as motion feedback is more genuine
  • Enlarge survey measurement. High survey scores but low emotion recognition as users tend to be polite.
  • Strengthen market research methods to formulate preferences verbally with collation to emotions for new service or products.
  • Deepen behavioral methods and automate the emotion analysis to scale the data collection efforts from multiple sources.
  • Discover emotions in real-time for customers service, improve productivity, save costs and improve user experience.
Contact Person

Andrew Ow


Opsis Pte Ltd

Technology Category

  • Infocomm
  • Artificial Intelligence, Healthcare ICT, Natural Language Processing & Semantic Technology, Smart Cities, Video/Image Analysis

Technology Readiness Level