Our AI-powered Product Description revolutionizes the way you manage your fashion apparel catalogs by fully automating the creation of product titles and descriptions. Instead of spending hours manually tagging and writing descriptions, our AI-driven generator swiftly produces optimized texts, saving you valuable time and effort.

With the ability to customize style, tonality, format, length, and preferred product tags, you can ensure that each description aligns perfectly with your brand’s voice and SEO needs. This service is designed to streamline your workflow, providing accurate, engaging, and search-friendly descriptions for your entire fashion inventory.

Enhanced Taxonomy for Accessories Product Tagging

We’ve upgraded our taxonomy for accessories tagging. For sunglasses and glasses, you can now get tags for frame types (Frameless, Fully Framed, Half-Framed), materials (Combined, Metal, Plastic & Acetate), and shapes (Aviator, Cat-eye, Geometric, Oval, Rectangle, Vizor/Sport, Wayfarer, Round, Square). Try how it works on your images in our public demo.

Automate Detection & Tagging of Home Decor Images With AI

Our new Home Decor Tagging service streamlines the process of categorizing and managing your home decor product images. It uses advanced recognition technology to automatically assign categories, sub-categories, and tags to each image, making your product catalog more organized. You can customize the tags and choose translations to fit your needs.

The service also offers flexibility with custom profiles, allowing you to rename tags or add new ones based on your requirements. For pricing details and to see the service in action, check our API documentation or contact our support team for help with custom tagging and translations.

Visual Search for Home Decor: Find Products With Real-Life Photos

With our new Home Decor Search service, customers can use real-life photos to find visually similar items from your furniture and home decor catalogue.

Our tool integrates four key functionalities: home decor detection, product tagging, colour extraction, and visual search. It allows users to upload a photo, which the system analyzes to detect home decor items and match them with similar products from your inventory.

To use Home Decor Search, you first sync your database with Ximilar’s cloud collection. This involves processing product images to detect and tag items, and discarding the images immediately after. Once your data is synced, you can perform visual searches by submitting photos and retrieving similar products based on visual and tag similarity.

The API allows for customized searches, such as specifying exact objects of interest or integrating custom profiles to modify tag outputs. For a streamlined experience, Ximilar offers options for automatic synchronization and data mapping, ensuring your product catalog remains up-to-date and accurate.

The post New Solutions & Innovations in Fashion and Home Decor AI appeared first on Ximilar: Visual AI for Business.

The technology behind image similarity is robust, reliable & fast. Built on state-of-the-art (SOTA) AI models and vector databases, you can search millions of images/products in milliseconds. It is used by big e-commerce players as well as small startups for showing visual alternatives or finding products with pictures. Some of our customers have hundreds of millions of images in their collections and do more than 100 million requests per month. Let’s dive into building a superfast similarity search service for your web.

What is Image Similarity?

Image Similarity, or image similarity search, is a visual AI service comparing, grouping, and recommending visually similar images. For example, a typical use case is a product recommendation of similar items in e-shops. It can also be used for reverse image search, where the query is an external image and the results are images from the collection. This approach gives way more accurate results than searching by tags, labels and other attributes.

Ximilar is using state-of-the-art deep learning models for all visual search services. We build our own indexing & searching technology that can run both as a service or on your hardware if needed. The collections can be focused either on product photos, fashion, image matching, or generic photos (stock images).

Features of the Image Similarity Service

Here are several features of the Image Similarity service that we think are crucial:

• Simple access through the Ximilar App (creating a collection on click) and connection to REST API
• The scalable search service can handle collections with hundreds of millions of similar items (images, videos, etc.) and hundreds of requests per second with both CRUD operations and searching
• The ultra-fast and reliable engine that is mostly deployed in large e-commerce platforms – the query for finding the most visually similar product is low latency (in milliseconds)
• The service is customizable – the platform enables you to train your own model for visual similarity search
• Advanced filtering that supports JSON meta-data – if you need to restrict the result to a specific field
• Grouping based on similarity – our search technology can group photos of the same product as one item
• Security and privacy of your data – only meta-data and the visual representation of the images are stored, therefore your images are not stored anywhere
• The service is affordable and cost-effective both for startups and enterprises, offering free plan for tests as well as discounts with your growth over time
• We can deploy it on your hardware, independently of our infrastructure, and also offline – custom similarity model and deployment appropriate to your needs
• Our search engine and machine learning models improve constantly – maintaining much higher quality than any other open-source project & we are able to build custom search engines with trained models

Applications Using Visual Similarity

According to this research by Deloitte, merchandising with artificial intelligence is more and more relevant, and recommendation engines play a vital part in it. Here are a few use cases for visual similarity engines:

• E-shops that use product similarity to help customers to browse and find related products (e.g. in fashion & luxury items, home decor & furniture, art, wall art, prints & posters, collectible trading cards, comics, trademarks, etc.)
• Stock photo databases suggesting similar content – getting visual alternatives of photos, designs, product images, and videos
• Finding the exact products – apps like Vivino for finding wine or any kind of product are easy to develop for us
• Visual similarity duplicate finder (also image matching or deduplication), to know which images are already in your database, or which product photos you can merge together
• Reverse image search – finding a product or an image with a picture online
• Finding similar real estate based for example on interior design, furniture, garden, etc.
• Comparing two images for similarity – for example patterns or designs

Recommending products to your customers has several advantages. Firstly, it creates a better user experience and helps your customers find the right products faster. Secondly, it instantly makes the purchase rate on your web higher. This means a win on both sides – satisfied customers and higher revenue for you. Read more about customer experience and product recommendations in our blog post on fashion search.

Step by step: Building Real-Estate Image Search

Creating the Collection

So let’s take a look at how to easily build your own similarity search engine with the Ximilar platform. The first step is to log in to the Ximilar App. If you don’t have an account, then sign up – it’s free and takes just a minute. After that, on the Dashboard, click on the Visual Search tile and then the Image Similarity service. Then go to the Collections in the left menu and click on Create New Collection. It will show a pop-up with different collection types from which you need to select one.

The collection is a space where you upload your images. With this collection, you are performing queries for search. You can choose from Generic Photo Collection, Product Photo Collection, Dominant Colors Similarity, and Image Matching. Clicking on one of the cards will create a collection for your account.

Each of these collection types is suitable for different types of images:

• Use Generic Photos if you work with stock photos
• Pick a Product Photos collection if you are an e-commerce company
• Select Image Matching to find duplicates in your images
• For the fashion sector, we recommend using a specialized service called Fashion Search
• Custom Similarity is suitable if you are working with another type of data (e.g. videos or 3D models). To do this, please schedule a call with us, and we will develop your own model tuned for your data. For instance, we built a photo search system for the Magic the Gathering Trading Cards for one of our customers.

For this example of real estate, I will use a Generic Photo Collection. The advantage of Generic Photo Collection is that it also supports searching images via text input/query. We usually develop custom similarity models for real estate, when the customers need specific and more accurate results. However, for this simple use case, the generic real estate model will be enough.

Format of Image Similarity Dataset

First, we need to prepare a text file with JSON records. Each record represents an image that we want to store/insert into our collection. The key field is "_url" with the image URL. The advantage of the _url is that you can directly see and inspect the results via app.ximilar.com.

You can also optionally send records with base64 data, this is great if your data are stored locally on your computer. Don’t worry, we are not storing the whole images (data or base64) in the collection database, just URLs with all other metadata present in the records.

The JSON records look like this:

{"_id": "1_1", "_url": "_URL_IMAGE_PATH_", "estate_id": "1", "category": "indoor", "subcategory": "kitchen", "tags": []}
{"_id": "1_2", "_url": "_URL_IMAGE_PATH_", "estate_id": "1", "category": "indoor", "subcategory": "kitchen", "tags": []}
...

If you don’t have image URLs, you can use either "_file" or "_base64" fields for the image data (locally stored "_file" data are automatically converted by the Python client to base64). The image similarity engine is indexing every record of the collection by extracting a representation from the image by a neural network model. However, we are not storing the images in our engine. So, only records that contain "_url" will be visualized in the Ximilar App.

You must store unique identifiers of each image in the "_id" field to identify your images in the collection. The value of this field must be a string. The API endpoint for searching is returning this _id values, that is how you get the results for visual search. You can also store additional fields for every JSON record, and then you can use these fields for filtering, grouping, and tuning the similarity function (see below).

Filling the Collection With Your Data

The next step requires a few lines of code. We are going to insert the prepared images into our collection using our python-client library. You can install the library using pip or directly from GitLab. The usage of the client is very straightforward and basically, you can just use the script tools/collections/insert_json_records.py:

python insert_json_records.py --type generic --auth_token __YOUR_TOKEN__ --collection_id __COLLECTION_ID__ --path /path/to/the/file.json

You will find the collection ID and the Authorization token on the “collection page” in the Ximilar App. This script will run for a few minutes, depending on the size of your image dataset.

Result: Finding Visually Similar Pictures

That was pretty easy, right? Now, if you go to the collections page, you will see something like this:

All images from the JSON file were indexed, and now you can inspect the collection in the Ximilar App. Select the Similarity Search in the left menu of the Image Similarity service and test how the similarity works. You can specify the query image either by upload, by URL, or your IDs, or by choosing one of the randomly selected images from the collection.

Even though we have indexed just several hundred images, you can see that the similarity engine works pretty well. The first image is the query image and the next images are the k-nearest to the query image:

Rest API Connection for Image Search

The next step might be to integrate the service into your application via API. You can either directly use the REST API for searching visually similar images or, if you are using Python, we recommend our Python SDK client like this:

# pip install ximilar-client
from ximilar.client import SimilarityPhotosClient
client = SimilarityPhotosClient("_API_TOKEN_", "_COLLECTION_ID_")
# search k nearest items
client.search({"_id": "1"}, k = 3)
# search by external image
client.search({"_url": "_URL_PATH_"})

Advanced Features for Photo Similarity

The search for visually similar images can be combined with filtering on metadata. This metadata can be stored in the JSON, as in our example with the "category" and "subcategory" fields. In the API, the filtering is specified using a MongoDB-like syntax – see the documentation.

For example, let’s say that we want to search for images similar to the image with ID=1_1 that are indoor photos made in a kitchen. We assume that this meta-information is stored in the “category” and “subcategory” fields of every JSON record. The query will look like this:

client.search({"_id": "1_1"}, filter={"category": "Indoor", "subcategory": "Kitchen"})

If we know that we will often filter on some fields, we can specify them in the “Fields to index” option of the collection to make the query processing more efficient.

Often, your data contains several photos of one “object” – a product or, in our example, real estate. Our service can group the search results not by individual photos but by product IDs. You can set this in the advanced options of the collection by specifying the name of the real estate in the Product ID field, and the magic will happen.

Enhancing Image Similarity Engine with Tags

The image similarity is based purely on the visual content of the image. However, you can use your tags (labels, keywords) to enhance the similarity search. In the example, we assume that the data already contains categories, subcategories, and tags. In order to enhance the visual similarity search with tags, you can fill the “tags” field for every record with your tags, and also use method /v2/visualTagsKNN. After that, your search results will be based on a combination of visual similarity and keywords.

If you don’t have categories and tags, you can create your own photo tagger through our Image Recognition service, and enrich your image data automatically before indexing. The possibilities of image recognition models and their combinations are endless, resulting in highly customizable solutions. Read our guide on how to build your own Image Recognition API.

You can build several models:

• One classifier for categorizing indoor/outdoor/floor plan photos
• One classifier for getting room type (Bedroom, Kitchen, Living room, etc.)
• One tagger for outdoor tags like (Pool, Garden, Garage, House view, etc.)

To Sum Up

The real estate photo similarity search is only one use case of visual similarity from many (fashion, e-commerce, art, stock photos, healthcare…). We hope that you will enjoy working with this service, and we are looking forward to seeing your projects based on it. Thanks to our developers Libor and Ludovit, you can use this service through the frontend app.

Visual Similarity service by Ximilar is unique in terms of search quality, speed performance, and all the possibilities of the API. Our engineers are constantly upgrading the quality of the search, so you don’t have to. We are able to build custom solutions suitable for your data. With multiple collections, you can even A/B test the performance on your websites. This can run in our cloud as SaaS or in your warehouse! If you have more questions about pricing, and technical details,  or you would like to run the similarity search engine on your own machines, then contact us.

The post Image Similarity as a Service For Your Web appeared first on Ximilar: Visual AI for Business.

Customer Experience is Important

It all starts and ends with the customer experience. According to PwC, a good experience leaves people feeling heard and appreciated. And a disappointing experience, on the other hand, drives them away almost instantaneously. When the respondents were asked what they value the most, 80 % chose efficiency, convenience and friendly service, and 75 % chose up-to-date technology.

80 % of American consumers say that speed, convenience, knowledgeable help and friendly service are the most important elements of a positive customer experience. Prioritize technologies that provide these benefits rather than adopting new technologies for the sake of being cutting edge.

PwC, Experience is Everything

The KPMG 2018 research findings were similar: customer experience is more influential than ever. More importantly, AI gains more clout by delivering personalized, customized, and localized experiences to customers. AI, such as machine learning algorithms, intelligent search, or chatbots, take part in the entire product and service cycle nowadays. In addition, Accenture recently wrote that AI, neural networks, and image search are the leading technologies behind the apps taking over the market. And that they are important trends to watch in the following years.

Fashion E-Commerce Trends in 2021

Big trends in current fashion e-commerce are sustainability, slow fashion, second-hand apparel, and resale. For example, the second-hand clothes marketplace Vinted is growing exponentially. According to THREDUP, there are more second-hand shoppers than ever before, and the resale is going to be bigger than fast fashion by 2029.

There were major changes to consumer behaviour as well during the coronavirus pandemic. Glami’s 2021 Fashion Research showed that an astonishing half of the shops moved to the online world, and the number of online consumers is still growing. They are looking for visual inspiration, want shopping to be intuitive and fast, and expect personalized experiences more than ever.

What is Fashion Search?

The Fashion Search is an advanced Visual AI service, custom-built for the fashion industry. It enables you to create your own product discovery system, work smarter with data, and build a better customer experience. Fashion Search brings together the services and features most requested by our fashion e-commerce customers:

1. Object Detection & Fashion Tagging
   The fashion apparel in your images is automatically detected and tagged. Our Fashion Tagging works with a hundred recognition models, hundreds of labels, and dozens of features, all chained into interconnected flows, enabling you to add content 24/7. We refine the quality and add new fashion attributes (features, categories & tags) to this service constantly. However, custom tags are welcomed as well. Read more about Fashion Tagging here.
   
   
2. Product Similarity & Search by Photo
   This Visual Similarity combo enables you to provide a personalized customer experience. The Product Similarity finds and suggests similar products to the item your customer is viewing. As a result, the click rate increases up to 380 %. Search by Photo accepts the pictures your visitors uploaded and automatically recommends similar items from your collection. For example, it can analyze fashion influencer photos and help your customers find trending items on your site. Read more about Visual Search in Fashion or How to Build Superfast Image Similarity for your Website.
   
   
3. Synchronizing Product Data on Cloud
   Our customers’ image databases are synchronized to their private collections on the Ximilar cloud. When you upload new products or images on your website, our AI automatically recognizes the fashion attributes and provides tags. There are two major benefits of synchronization. First, simple filtering or searching with fashion tags on your website. Second, personalized recommendations of your products similar to the users’ images. The synchronization periodicity is up to you. This way the visually similar results on your web are always up to date with your actual SKUs.

How Does Fashion Search Work?

The Fashion Search works as a customizable recommendation service allowing you to easily build your own fashion product discovery system. Imagine you are building a watch shop with product recommendations based on material, dial colour, and type. You can add your custom tags and show customers products of specific colours and types.

The main added value of the Fashion Search lies in the possibility of combining advanced automatic Fashion Tagging with Visual Search. The technology behind our Visual Search is complex. It contains more than a hundred deep-learning models and algorithms for the extraction of dominant colours and other features. It also allows advanced filtering of visually similar results based on user-provided attributes.

Besides bringing these things together, there’s more we implemented to make the Fashion Search an effective and reliable tool tailored to the needs of fashion e-commerce. See how it works in our public demo.

Advanced Tagging with Object Detection

Object Detection is an indispensable tool for processing complex pictures with many items to recognize and tag. The service detects all fashion-related items on the picture and then provides tags for individual items.

We work with seven Top Categories (or types) of apparel: Clothing, Footwear, Watches, Bags, Accessories, Jewellery, and Underwear. Our system classifies the products from these categories into a hundred different categories, subcategories, and features with about 600 labels.

Customization of Fashion Search with Profiles

The most common questions we get from our customers in fashion are “What if I need something that is not included in the Fashion Tagging? “ and “What if I need to rename or translate the labels? “.

We always welcome customization and Fashion Search is not an exception. It enables our users to create a fully customized environment. Adding a new feature requires only a few hundred example images per tag for the system to recognize them automatically. Also, it is natural that everyone has their own taxonomy and preferred language. Even the naming can be different, such as Jacket vs. Coat in the USA and the UK. Renaming and changing the category structure is done using a custom fashion profile according to your needs.

Also, for specialized sellers, the requirements for the richness of labels are much higher if they want to bring the best product discovery experience. For example, a shop specializing in luxury jewellery needs to rename the tags for Colour (gold, golden, yellow gold, gold-coloured, rose gold) or add exclusive features and tags, such as the colour of the gemstones. If you like this approach, don´t hesitate to contact us.

Upgraded Fashion Taxonomy

Our fashion annotation team focuses on widening fashion taxonomy and training new machine learning algorithms to recognize new features daily. Categories such as Clothing, Accessories or Footwear are constantly growing, while others are being made. For instance, we recently added a new recognition model for Embellishment (e.g. embroidery or studs), rich sub-categories of Dresses, and new categories of Jewellery and Watches. In the last couple of months, we added over 50 new categories and attributes, improving the precision of tagging results.

We have a lot of discussions about what’s next to explore and expand – and that is where the customer’s ideas come into play. Check if you can find your categories in our Fashion Taxonomy.

Download the Fashion Taxonomy Sheet Here

Advanced Analysis and Sorting of Fashion Images

Some customers need to obtain more detailed information about their images. Features such as the presence of a human model, background quality, or perspective can be used for filtering and sorting. To enable deeper image analysis, we built a specialized Meta Tagging model, that can be used to:

• identify if there’s a person in the picture,
• filter images with white background,
• sort product images by the view,
• and many more.

This Visual AI model enables you to manage the display of product images and build a smoother customer experience. More importantly, it makes your web easier to understand and navigate with features such as:

• the first photo in the product list is always with/without a person,
• the next photos are sorted by perspective,
• the last photo is the detail, focused on the material, colour, or pattern,
• all images with low quality are filtered out,
• and so on.

This way, the visitors will always know what to expect and where to click to find what they’re looking for. For instance, it is important to display jewellery in standardised high-quality images with details, but also on the human body. Seeing a ring or a necklace on a hand or neck helps customers understand the fit and size of the jewellery, as well as the colours of materials and gems in natural light.

Community content also makes e-shopping sites more personal and engaging for visitors. A good example is Shein, where users can upload pictures along with their reviews of the product. This strategy definitely adds up to the trustworthiness and reliability of the seller.

How We Work with Data

Working with big specialized databases requires caution, patience, and a specific skill set. Our team of fashion annotators puts thousands of hours into building high-quality datasets with relevant labels and objects. To make their work more efficient and time well-spent, we developed our own image Annotation Tool, enhancing the functionalities of our App. It is the main reason why we deliver new features quickly, and it is available to our customers as well.

Each image shown to the model in training is verified numerous times by multiple annotators. Then, an optimisation mechanism makes sure we achieve the highest accuracy with the smallest amount of training images possible. After that, everything is evaluated on a broad test dataset. As a result, we only deploy models, that are inspected by Machine Learning specialists, and precise in their predictions.

Never-Ending Innovations

What else? There have been some significant improvements to our speed performance. Cooperating with the Intel AI team, we did a lot of work on our backend side so you can query the results in milliseconds. We firmly believe that our Fashion AI services are some of the best in the market. Covering a variety of items from Clothing, Footwear, or Accessories, our Fashion AI works with a very rich taxonomy. To sum up, we are now ready to focus on more new features. For example, mining relevant keywords from textual metadata, enhancing and upscaling product images with the Super-Resolution model, model explainability, or background removal, but also on better and richer customer experience.

Would you like to discuss your custom solution or ask anything? Read our story, check the pricing, or let’s talk!

The post Everything You Need to Know About Fashion Search appeared first on Ximilar: Visual AI for Business.