Fashion Search & Discovery

Fashion Search is an all-in-one solution for fashion e-shops, websites, price comparators and apps. It includes the following AI-powered solutions:

1. Object Detection & Fashion Tagging

Our Fashion Tagging automatically identifies and tags the fashion apparel in your images. It utilizes a hundred recognition models, hundreds of labels, and dozens of features, all linked into seamlessly interconnected flows, enabling you to add content 24/7. We continually enhance the quality and incorporate new fashion attributes like features, categories, and tags. Custom tags are also encouraged.

Standalone fashion tagging assigns tags to a single dominant fashion item in an image. However, when united with object detection, it’s capable of tagging all recognizable fashion apparel in an image.

2. Product Similarity & Search by Photo

These visual search solutions allow hyper-personalization of customer experience. Product Similarity identifies and proposes items similar to the one your customer is currently viewing, leading up to a 380% boost in clicks.

Search by Photo accepts user-uploaded images, detects fashion apparel in them, and automatically suggests similar items from your inventory. This applies to real-life photos, user-generated content, as well as influencer photos and other social media content.

There are several options:

• By default, Fashion Tagging and Search focus on the largest fashion object in the image. This mode is ideal for single-product photos and other images with dominant objects.
• However, you can opt to detect all fashion items using the detection endpoint, then individually tag and use them for separate visual searches.
• The tagging can also be enhanced with a meta endpoint describing the background, scene, view, and body part of the person wearing the items.

Ximilar’s Fashion AI can analyze a range of images, from product photos to real-life ones, including user-generated content and social media posts.

Images can be submitted in any standard format (see supported image formats at a link below) either as image URLs or as base64-encoded image data.

For reverse image searches, your image query should ideally contain a single dominant fashion item. These queries can utilize both single-product pictures or parts of more complex images, in which specific items will be detected.

The AI can also process and remove backgrounds from product photos in bulk for a more cohesive catalogue. Additionally, you can choose which image category, such as model-worn product images or standalone product images, will be automatically displayed.

Fashion Tagging labels your fashion items, assigning categories (e.g., skirts), subcategories (e.g., A-line skirts) and tags (for color, design, pattern, length, rise, style…). By default, it provides data for one main object in an image. Endpoint meta can also provide tags for the photography background, scene, or body part in the fashion image.

Fashion Search is an all-encompassing solution, wrapping all typical fashion AI services into one. It integrates:

• Fashion tagging, including Dominant colors
• Object detection for precise labelling and search of individual items
• Visual Search, recommending similar items from your collection

Both Fashion Tagging and Fashion Search include color analysis. The colors are supplied as tags and can serve for filtering and search on your website.

I only need a single fashion AI solution

All our fashion AI solutions can also be employed individually. Examples include product similarity, search by photo (reverse image search), fashion apparel detection, or color-based search.

Our company’s fashion detection operates with both product images and real-life photographs, including user-generated content or social media posts. The fashion apparel detected may be both standalone and worn by people.

Apparel visibility
To achieve the most accurate results, the fashion apparel you wish to detect should be clearly visible, with minimal overlapping objects or folds, and not worn by individuals in uncommon poses. However, if your collection comprises numerous photos with unconventional positions, we can readily tailor the solution to perfectly suit your use case.

Visual search and similarity search are always performed on a specific image collection.

Each image in this collection is processed exactly once during the collection synchronization run, and then discarded. Our AI then works with a representation of your images and compares them for similarity. That is why we do not store your images used for visual search. They are discarded immediately after processing.

The type and source of the images in your collection are up to you, as well as the frequency of the synchronization runs. Contact us via live chat or contact form for details.

We offer multiple options for dominant color extraction that you can select from. The outcome is provided in a structured format, usually JSON.

Dominant product vs. whole image

The product endpoint allows you to extract colors from a single dominant object in an image (product photo), whereas the generic endpoint extracts the dominant colors from the entire image, a mode typically used in stock photography.

Basic color for searching & filtering

This mode identifies one main color of the dominant object out of a total of 16 basic colors. The extracted color can be utilized as an attribute for filtering and searching fashion items.

Pantone palette: detailed color analysis

This mode provides a group of dominant colors, their hex codes, the closest Pantone name, and coverage of the image in %. It is ideal for similarity search (search by color).