Frequently Asked Questions

Artificial Intelligence in an easy to use package. Smart machine learning techniques improved to the max. Tools for quick use.

About Tagging Services

Fashion Tagging

Fashion Tagging is a visual AI service that automatically recognizes the fashion product in a product image, categorizes it and provides tags. It can be easily combined with automatic object detection to categorize and tag all the fashion products in complex images separately.

We provide both Fashion Tagging and a more complex service called Fashion Search, which implements Fashion Tagging, as well as Visual & Similarity Search (Search by Photo) and Object Detection.

Go to:

The automated Fashion Tagging is used on fashion product images of e-shops, price comparators, fashion brands, and specialized collections. It is based on numerous image recognition tasks trained to recognize separate product categories, as well as object detection models. That is why it works on both single product images and more complex images, including user-generated content or social media images.

Go to:

Fashion Tagging is one of our most complex ready-to-use services. It works with over a hundred recognition tasks, hundreds of labels, and dozens of fashion attributes. It identifies the top category of product (e.g., accessories, bags, jewellery, watch, clothing, underwear, footwear), then the category (e.g., accessories/belts or underwear/bras), and its features such as colour, design, material, or pattern. Furthermore, it can be combined with object detection to ensure even more complex images are properly tagged. If you miss any important attributes, the taxonomy can be adjusted to fit your use case.

Go to:

You can download our full fashion taxonomy in a PDF under the link below, try out our public demo, or check the API documentation for news and additions.

Go to:

Fashion Tagging can be combined with object detection to categorize and tag individual items in a more complex fashion image. You can also use Fashion Search, which automatically detects apparel, footwear and accessories in your images, provides tags, and finds the most similar products or images.

These fashion services work on both product images and real-life photos, e.g., fashion influencer pictures.

Go to:

Yes! Ximilar has a free and public Fashion Tagging demo. You can either upload images or their URLs and see for yourself how automatic fashion tagging works.

You can also use Fashion Tagging in our App. See our Pricing for details. If you have large volumes of images to be processed every month or need customization, contact us to discuss a custom plan.

Go to:

Yes, you can! Automated Fashion Tagging works on product images as well as real-life photos. Our tagging combines object detection, which identifies fashion items in an image, with image recognition, which categorizes these items and provides you with tags.

Go to:

We recommend downloading the Ximilar Fashion Tagging taxonomy, checking the API documentation, and trying how the service works in our public demo and App before setting up a custom solution. If you do not find the attributes you need, contact us to modify the service to fit your use case.

You can also try to train your own custom categorization or object detection tasks using the Custom Image Recognition services.

Go to:

With Ximilar, you can use your own taxonomy and get the results of Fashion Tagging in your own language. It is achieved by mapping your taxonomy to ours. Contact us to set up a custom profile.

Go to:

Dominant Colors

Dominant Colors is a visual AI service extracting the most prevailing colors from images. You can choose one of the two ways to use this service, depending on whether you need to analyze generic photos (real life and stock photos) or product photos.

The endpoint for generic photos detects up to 6 dominant colors (covering the most area) from the whole image, without modifying it. This endpoint is more suitable for stock photos or real-life photos where you need the entire picture to be analyzed, not only the foreground object.

The endpoint for product photos, in addition, contains a background removal task, after which it analyzes the 6 dominant colors of the foreground object and picks 3 major colors (covering the largest area). The product color endpoint is great for product photos, where one dominant item is in the picture.

Both endpoints return one or more dominant colors in three formats: RGB number values, RGB hex, CIE Luv and name according to CSS3 color standard and Pantone color naming.

Go to:

The basic palette of 16 basic colors is useful for tagging, sorting and filtering products or pictures in e-shops and on comparison websites. The Dominant Colors with this basic setting are included in our Fashion Tagging service.

The results of the advanced colour analysis are provided as a group of colors on the Pantone color palette. You get their exact Hex code, the name of the closest color in this palette, and the percentage of the area they cover. This way is ideal for similarity & visual search solutions, where you need to know the exact colors.

Go to:

All of our services can be used through an App or via API, and separately or as a part of a more complex solution built with Flows.

In our App, you can find the Dominant Colors under the Ready-to-use Image Recognition services. It is available to all pricing plans, including Free. You can upload images with URLs or by drag-and-drop.

Go to:

Yes, you can. Check the API documentation and see how it works in our App.

Go to:

Home Decor & Furniture Tagging

Automated Home Decor & Furniture Tagging is a visual AI service that automatically recognizes categories and sub-categories in furniture or home decor product images, and provides tags describing the main products.

Go to:

The automated Home Decor & Furniture Tagging works mainly with home decor and furniture product images from price comparators, sellers, hotels, architectural studios, designers, and specialized collections. You can try how it works on your images in a public demo.

Go to:

This service categorizes and tags the dominant home decor or furniture item in the image. It identifies the top category of image (all rooms, bathroom, bedroom, kitchen), then the category (e.g., bedroom/duvet covers), and its features such as colour, shape, pattern, and material.

Go to:

The full taxonomy is available in the API documentation.

Go to:

This service was created to work mainly with product images, therefore it categorizes the dominant product in the image, based on an image recognition task. It can however be combined with a custom object detection task to detect specific furniture pieces or decorations and then analyze them separately. Feel free to contact us to discuss a custom solution.

Go to:

Yes! Ximilar has a public Home Decor & Furniture Tagging demo. You can either upload images or their URLs, and see for yourself how it works. You can also use this service in our App. The Home Decor & Furniture Tagging is available in all pricing plans. If you have large volumes of images to be processed every month or need customization, contact us to discuss a custom plan.

Go to:

With Ximilar, you can use your own taxonomy and get the tagging results in your own language. It is achieved by mapping your taxonomy to ours. Contact us to set up a custom profile.

Go to:

Image Recognition of Collectibles

Image Recognition of Collectibles is a service created for websites and apps for collectors. It automatically detects and recognizes collectible items, such as cards, coins, banknotes, or stamps.

The service is fully customizable for different types of collectibles. For example, let’s say you are building an app for the automatic recognition of baseball cards. We would use the basic service and add a precise recognition of different cards based on their images, texts or packaging.

We can add tasks that will recognize edition, year, symbols or texts on the collectible items and provide you with tags, that can be used as keywords for search and filtering of items on your website.

Additionally, this service can be combined with other solutions, such as:

  • Visual Search – This technology will browse your collection based purely on the appearance of the item. You can find the exact or similar items in your collection based on an image query.
  • Background Removal – Remove the background from all single-item images automatically.
  • Image Upscaler – To enhance the quality of low-resolution images.

Read more: Go to:

As for now, the service is able to detect (and mark by bounding boxes) the collectibles such as stamps, coins, banknotes, comic books and trading cards.

For collectible cards, the service can identify whether it is a Trading Card Game (Pokémon, Magic The Gathering, Yu-Gi-Oh!, and so on) or a Sport Card (Baseball, Basketball, Hockey, Football, Soccer, or MMA), with several additional features (e.g., signature).

The service is constantly expanding based on the requests from our customers.


Read more: Go to:

Yes, it can. We will create a customized visual search. After that, you will be able to search in your database with image queries or recommend similar items. The visual search will be independent of the origin, resolution, or quality of colours of your images.

The system works via REST API and is able to scale to hundreds of requests per second.


Read more: Go to:

Image Recognition of Collectibles is a basic AI system for detecting and analyzing images of collectibles. It can be combined with a custom visual search solution to find images in your collection based on a query image, recommend similar items, or match and eliminate duplicates in item galleries. This system is always customized for specific customers’ needs.

 


Read more: Go to:

Visual inspection systems powered by AI depend on the type of data. We will develop a custom system based on your use case. To do so, we will need a dataset of training images from you (representing the images you typically work with). Then the system will be able to detect signatures or package, and analyze scratches or edges of the item. Contact us to discuss your use case.


Read more: Go to: