Computer vision (CV) has evolved tremendously over the years, adding exciting capabilities to the field of marketing. Using artificial intelligence and machine learning, this technology enables computers to gain a visual understanding of the world. Much like how people use their eyes and brains to make sense of their surroundings, computer vision can scan images and translate their contents into metadata. Marketers can then collect, organize, and assess that data to enhance their marketing efforts.
Here, you can explore seven computer vision applications in marketing.
If you’re an intermediate or advanced practitioner, we’ve created premium education to help you and your team master recent breakthroughs in applied AI for marketing. Click here to purchase our AI in marketing research summaries.
Common Applications of Computer Vision in Marketing
Computer vision is reshaping marketing in several ways. Read on to discover cutting-edge opportunities to elevate your marketing efforts.
1. Original Content Generation with GANs
One of the greatest challenges of online marketing is creating new content. Fortunately, there are neural networks called Generative Adversarial Networks (GANs) that will make this process so much easier and faster.
GANs can create hyper-realistic visual content, including videos, photos, and 3D-models. Pose-guided person image generation is one of the technology’s many applications. It lets you transform any image into different poses by feeding data on poses into the system. This approach uses a two-stage generator and a discriminator. The generators transform a photo using metadata and the authentic image, while the discriminator determines whether the input is real or generated.
Another example of generating original content with GANs comes from a Japanese tech company DataGrid that uses generative adversarial networks to create realistic images of fake fashion models. Instead of hiring new people every single time, brands can generate their own original content in a budget-friendly and efficient way.
Virtual model Imma
2. Branded Object Recognition
Brands have to monitor social media platforms and other online channels to determine where prospects, customers, and critics can engage with them. Image detection enables brands to see the threats and opportunities that influence their success. Gumgum is a company which performs social listening. They use computer vision to identify brand logos and find good and bad reviews all over the web.
Recognizing branded images in social media and captioning them for marketing analytics is vital to marketers as it lets them understand customers’ interaction with a product, shows whether consumers make emotional connections with the brand, enables tracking of popularity and perception change over time.
Logo detection (Su, Zhu and Gong, 2016)
If this in-depth educational content on using AI in marketing is useful for you, you can subscribe to our Enterprise AI mailing list to be alerted when we release new material.
3. Product Discovery Through Visual Similarity
When it comes to online shopping, customers mostly use the search bar or a filter function to discover new products. This usually requires extensive use of tags, all of which are manually assigned to products. Since tagging depends entirely on the retailer, this can be very confusing and inconvenient for consumers, especially if they don’t know brand jargon.
Pinterest has an AI-based tool called Visual Search for visual product discovery, eliminating the need for manual tags. Instead of standard filtering systems, consumers – via mobile app or browser extension – can select any image they want, and they will be shown a whole roster of similar items. This way, consumers don’t have to know brand jargon to find what they’re looking for.
Pinterest’s Visual Search
4. Tracking Consumer Attention and Emotions
Advancements in face analysis algorithms are now powerful enough to assess consumers’ facial expressions and measure their emotions. Disney developed an algorithm (Factorized Variational Autoencoders) to determine how their audience responds to their films. Infrared cameras detect and capture people’s reactions during movie screenings. The software identifies complex facial cues and even predicts how moviegoers would feel at certain parts of the movies. This helps Disney understand what provokes certain emotions.
Learning about consumer attention and emotions is now a priority in business. Using emotion detection technology, brands can gauge foot traffic, predict sales revenue, and adjust marketing strategies accordingly.
Modeling audience reactions with Factorized VAE (Deng et al., 2017)
5. Optimizing Conversion Rates with Images
Equipped with deep learning algorithms, Yelp can curate the most beautiful photos for any establishment to maximize their conversion rates. Instead of using the number of likes to determine the best photos, they judge photos based on the characteristics that actually matter: contrast, depth of field, and alignment to name a few.
Yelp used convolutional neural networks to design a photo scoring model. In their datasets, DSLR photos served as positive examples, while non-DSLR images were negative examples. They fed their data into the deep learning model, enabling it to recognize the qualities of good photos.
Photo scoring model by Yelp
6. Facial Recognition for Personalized Customer Experience
Lolli & Pops stores are powered by facial recognition software, enabling them to identify valued customers as soon as they step inside the store. Using a specific app, the sales associates can check out a customer’s purchasing history, preferences, taste profile, and allergies. Then AI-powered analytics helps them in delivering personalized product recommendations for every customer.
Neutrogena also delivers personalized experiences with the help of an app. They have a skin-scanning gadget which you can attach to a smartphone. The scanner syncs with their Skin360 app, which analyzes your scans and determines your skin health. After all the measures are taken and analyzed, you will be pointed towards the relevant Neutrogena products.
Skin360 score example
Learn about the Cutting-Edge AI Research Techniques for Personalizing Customer Experience in our premium research summaries.
7. Trying a Product on Virtually
Sephora uses augmented reality and artificial intelligence to create virtual shopping experiences for their patrons. Their customers can try on the latest makeup products through a mobile app called Sephora Virtual Artist. From lipsticks and eyeshadows to false lashes, consumers can try on every product that Sephora sells.
In addition, Sephora uses AI to help consumers find the perfect products that match their skin tone. All they have to do is upload a photo.
Sephora product try-on
Elevate Your Marketing with Computer Vision
Due to the dramatic explosion of visual sharing among consumers and brands, the ability to break down images into datasets has become crucial to online marketing.
Marketers who integrate computer vision into their marketing efforts will gain the opportunity to improve campaigns, influence buying decisions, and enhance customer experiences, among other things. As CV continues to mature, marketers can anticipate many new and powerful applications to come out in the future.
Enjoy this article? Sign up for more updates on using AI in marketing.
We’ll let you know when we release more technical education.