The Infosys Labs research blog tracks trends in technology with a focus on applied research in Information and Communication Technology (ICT)

« Data Virus Guard | Main | Emerging Tech in Airports »

Computer Vision enabling a Retail Utopia

Computer vision (CV) is the technology that enables a machine to 'see' and 'understand' its surroundings, just like or even better than humans. As per the British Machine Vision Association, "computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of images (video). It involves the development of a theoretical and algorithmic basis to achieve automatic visual understanding." It plays a vital role in providing innovative, immersive, futuristic solutions and applications across industries, including traffic management, surveillance, medical image analysis, payments, autonomous vehicles, quality control and many more.

We believe that the retail industry will embrace this technology rapidly with many use cases that will benefit from it across the retail value chain. 


The retail value chain (Figure 1) is essentially a series of actions and processes that adds value to the retailer's products, and enables them to be sold to customers. It includes product design, inventory management, store management, sales & marketing, delivery and support services (Reference: DUPress). CV can improve processes in each of these nodes to effectively enhance the overall value chain.

value chain6.png

Figure 1: Computer vision applications in the retail value chain

We'll take a closer look at the major areas in the retail value chain, viz. store management and marketing & sales, where CV can play a prominent role.

Intelligent store management: The different ways through which CV can help improve various store operations include:

  • Shelf auditing - Cameras and vision processing can help to analyze gaps in the shelves, identify misplaced products or those that are facing the wrong direction.
  • Customer tracking - CV cameras with motion detection capabilities can track customers, their emotions and behavior in the store, to understand and efficiently address customer concerns.
  • Security - CV enhances security & surveillance in stores, to avoid possible theft and pilferage by alerting store managers and blacklist the individuals in real-time.
  • Crowd management - CV can be used to generate a heat map based on the movement pattern of customers inside a retail shop to efficiently analyze and manage the crowd, and tweak sales strategies in real time.
  • Product management - Store managers can search for sales data, revenue, profit, inventory level etc. of each unique product in real time using CV, machine learning and analytics.

Personalized marketing and sales: Computer vision helps improve various marketing and sales activities in the store such as:

  • Custom ads - Cameras and screens at strategic location in the store can offer personalized advertisements, triggering a purchasing intend in customers.
  • Product discovery - Customers can take a photo of an object using the retail store's app in their smart phone, and get details such as price, availability, offers, complementary products etc. of the product or similar products with the retailer.
  • Personal assistants - Robotic assistants in a store can identify customers, greet them, provide recommendations, understand reactions, and answer customer queries using natural language processing, CV and machine learning.
  • Trusted payment and checkout - CV can enable multi-factor authentication including face recognition & emotion detection, which increases security and trust by ensuring that only the authorized person is making the payments. Virtual carts and e-wallets enable a seamless checkout experience for the customers, while emotion analysis further enables the retailer to gauge the customer satisfaction levels.

The main drivers and challenges in investment and adoption of CV in the retail scenario are:


We have come a long way from the first CV experiments of extracting 3D structures from images in the 1970's to the current day applications of recognizing emotions, identifying multiple objects and assisting self-driving cars. Developments in CV over the years would ensure advanced applications, solutions and reduction in costs, leading to wide spread adoption and improvements in efficiency and productivity of processes across industries.

Many retailers, such as Amazon and Walmart, are already investing in CV and associated technologies. It is an area that deserves recognition by all enterprises and service providers across industries, and is sure to be a game changer in the near future. CV applications will eventually evolve to a stage where we would trust and use it more than our own eyes, in hospitals, cars, homes, retail stores, banks, warehouses, farms etc., and it's at this stage, that we'd have truly empowered machines to 'see'.

Post a comment

(If you haven't left a comment here before, you may need to be approved by the site owner before your comment will appear. Until then, it won't appear on the entry. Thanks for waiting.)

Please key in the two words you see in the box to validate your identity as an authentic user and reduce spam.

Subscribe to this blog's feed

Follow us on