Recognize, Search & Enhance Images With AI

From ready-made to custom image recognition & visual search solutions under one API.

Get Custom AI Tailored to Your Images

Level up your image processing with custom solutions, combining existing & new features.

Build Computer Vision Models Without Coding

Create your own machine learning models and implement them easily into your website or app.
Try for free

Ready-to-use Visual AI

Learn more

Custom AI Solutions

Learn more

Computer Vision Platform

Learn more
Ximilar provides image recognition and visual search for websites, apps and other business and research uses. AI can identify individual items in an image and provide relevant similar suggestions.
Ximilar builds custom recognition, detection and image search solutions to businesses with specific image datasets, such as sports cards, TCGs and other memorabilia.
Create your own machine learning models for image recognition, object detection and image regression on Ximilar computer vision platform.

Ready-to-use Visual AI demos

Test Our Visual AI

Choose from off-the-shelf solutions for fashion, home decor, stock photos, collectibles, and more.

Fashion & Home Design
Stock Photos & Image Tools
Collectibles
Fashion Taging
Product Similarity
Search Fashion by Photo
Home Decor Tagging
Photo Tagging
Stock Photo Search
Background Removal
Dominant Colors
AI Recognition of Collectibles
Card Grader
Free demo to test the services for fashion tagging and card identification Click to Load Demo

FROM PATTERN RECOGNITION TO IMAGE SIMILARITY

Get Custom AI Tailored to Your Visual Data

Custom features — Your own labels, object categories, attributes, taxonomy, or language can be added to our solutions.

Semi-custom solutions — We can combine pre-trained & new modules for a tailored, budget-friendly solution.

New solutions for pioneers — We will craft an image or video processing system from scratch to help you pave the way.

How it works?
Visual AI by Ximilar can be customized with specific categories, objects, attributes, labels, whole taxonomies or even languages to fit specific use cases. In this case, object detection and image recognition are combined to spot and identify objects in a fluorescent microscopy image. Ximilar builds software for product recognition, tagging and description. The development time is minimised by combining existing AI modules with new solutions tailored to specific use cases. Ximilar's computer vision platform can be used to build new visual AI solutions for image and video processing, such as detection of objects on the shelves.

MACHINE LEARNING FOR EVERYONE

No-Code Computer Vision Platform

Use Ximilar App to test, build & deploy your own visual artificial intelligence. Manage your collections in App & connect via API.

Test

Sign up to App for free, upload your images & try how it works

Ximilar provides a free web-based app where anyone can create and train their own image classification models without the knowledge of coding. Sign up for free

Build No-code AI

Label data & create computer vision models without coding

Ximilar App can be used to test ready-to-use visual AI, build machine learning models, manage visual search collections and monitor API credit consumption. Learn more

Annotate Images

Efficient & quick bulk annotation of images in a team

Annotate by Ximilar is an advanced image annotation tool for teams, enabling you to draw polygons and bounding boxes, annotate images in bulk with smart suggestions from the AI photo recognition system, create projects and monitor their progress. Learn more

Combine

Combine ready-to-use and custom AI models into a modular Flow

At Ximilar computer vision platform, all image recognition, object detection, visual search or image enhancing models can be combined in complex hierarchical structures via Flows. Learn more

Connect

Connect via REST API for setup, integration or both

Set up your visual AI solutions in Ximilar App, get your API token and connect in a matter of minutes. Integration with your website or app is seamless and fast via REST API. API Documentation
image annotation
optical character recognition (OCR)
image classification
image based search
ML model testing
image upscaling
sports cards identification
deep learning
object detection
language models (LLMs) integration
facial detection
advanced image search
TCG card identification
sports cards grading
image labelling
photo enhancing
neural networks
data labelling
image segmentation

HUMAN EXPERTISE, AI CONSISTENCY

Get Your AI Solution From Industry Experts

We aim to make artificial intelligence accessible to businesses of all sizes by building a reliable, cost-effective no-code platform.
About us
background ximilar experts
Nessi, Ximilar
Nessi Image Annotation Expert
David, Ximilar
David Founder, Computer Vision Expert
Gabriela, Ximilar
Gabriela Fashion Stylist, Customer Care
Michal, Ximilar
Michal CEO, Machine Learning Engineer

15 Billion

Images recognized and counting

+380 %

Increased click rate on products

40+

Countries of origin of our clients

10+ Years

Hands-on experience in AI systems

USE AI WITH CONFIDENCE

Transparency & Security Come First

Use secure AI software with maximal data privacy. We store only training data on our own servers in the EU, with all data protected under GDPR.
background ximilar experts Dr. Reza Farshey
Dr. Reza Farshey CEO, Endogenie

We used Ximilar’s platform to build a model analyzing X-ray medical images. Even though the models are built on their platform, the data belong to our company. Support from Ximilar has been amazing, with a response time less than 24 hours. Overall, I am extremely happy with the service and product offerings from Ximilar.

Dr. Reza Farshey

Founder & CEO

background ximilar experts Damo Bowland, TCG Sync
Damo Bowland CEO, TCG Sync

Ximilar has been a fantastic partner for our card recognition needs. The backend system is highly reliable, and in the time we’ve been with Ximilar, we haven’t encountered a single issue. The team is incredibly responsive, always quick to address any queries we’ve had, and they consistently go above and beyond to ensure we fully understand and utilize their services. Their commitment to support and seamless performance earns them a well-deserved 5 stars. Highly recommended!

Damo Bowland

CEO

TCG Sync
background ximilar experts Zajzon Bodó
Zajzon Bodó CEO, Babyndex

Babyndex uses Ximilar’s Image Recognition and Annotate, which is excellent. I can easily set up their services myself. Ximilar has helped in improving accuracy and from that day on, it works perfectly.

Zajzon Bodó

Co-founder & CEO, Babyndex

background ximilar experts Filiberto Sosa
Filiberto Sosa CEO, Sizes and Colors

We integrate Ximilar’s visual AI into our online product discovery tool. With Ximilar’s visual search, we can tailor recommendations of newly arrived products to customers who are likely to be interested. Our system automatically notifies them, enhancing the overall customer experience. Our experience with Ximilar has been great.

Filiberto Sosa

CEO

Sizes and Colors - high tech for retail stores
background ximilar experts Amos Struck
Amos Struck Co-founder, StockPhotos

Way better similar results in our 10 million stock images. Customers can find visually similar pictures by uploading a photo. The integration was fast. We recommend it!

Amos Struck

Co-founder

background ximilar experts Pavel Macků
Pavel Macků CEO, Profimedia

The Ximilar technology has been working reliably for many years on our collection of 100M+ creative photos.

Pavel Macků

CEO

Previous
Next

CONNECT VIA REST API

Deploy, Connect & Conquer

Deploy latest models on click, connect via REST API, and integrate them into your system or infrastructure.

Go to API Documentation

Technology Stack

Python Client
Python
PHP
cURL
# pip install ximilar-client 
import base64
from ximilar.client import FashionTaggingClient

with open(__IMAGE_PATH__, "rb") as image_file:
    encoded_string =
base64.b64encode(image_file.read()).decode('utf
-8')

client = FashionTaggingClient("__API_TOKEN__")
response = client.detect_tags([{'_base64': encoded_string}])
import requests, json, base64

endpoint = 'https://api.ximilar.com/tagging/
fashion/v2/detect_tags'

headers = { 
    
    'Authorization': "Token __API_TOKEN__",
    'Content-Type': 'application/json' 

}
 
with open(__IMAGE_PATH__, "rb") as image_file:
    encoded_string =
base64.b64encode(image_file.read()).decode('utf
-8')

data = {
'records': [{'_base64': encoded_string}]
}

response = requests.post(endpoint,
headers=headers, data=json.dumps(data)).json()
$curl_handle = curl_init("https://
api.ximilar.com/tagging/fashion/v2/
detect_tags");

$data = ['records' => [ [ '_url' =>
'__PATH_TO_URL_IMAGE__' ], [ '_base64' => 
base64_encode(file_get_contents(__PATH_TO_IMAGE
__)) ] ] ];

curl_setopt($curl_handle,
CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($curl_handle, CURLOPT_POSTFIELDS,
json_encode($data));
curl_setopt($curl_handle,
CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl_handle, CURLOPT_FAILONERROR,
true);
curl_setopt($curl_handle, CURLOPT_HTTPHEADER,
array( "Content-Type: application/json",
"Authorization: Token __API_TOKEN__", "cache-
control: no-cache",) );

$response = curl_exec($curl_handle);
$error_msg = curl_error($curl_handle);
curl_close ($curl_handle);
curl --request POST \

  --url https://api.ximilar.com/tagging/
fashion/v2/detect_tags \

  --header 'Content-Type: application/json' \

  --header 'authorization: Token __API_TOKEN__'
\

  --data '{"records":[{"_url": "https://
bit.ly/2IymQJv"}]}'

Frequently Asked Questions

How image recognition works?

Image recognition allows computers to understand and classify images by analyzing their content. It helps with interpreting, tagging (enrichment with additional metadata), or categorization (sorting into groups) of images.

For example, if you train a dog vs. cat recognition model, and provide it with a folder of mixed pictures, it will be able to distinguish between cats and dogs, and thus sort the images into two separate folders.

It is used in various applications including medical diagnosis, autonomous vehicle systems (object recognition) or security systems (like facial recognition). The accuracy, speed, and efficiency of such systems continue to improve with advancements in artificial intelligence and machine learning techniques and depend on factors such as the quality of training datasets. Deep learning algorithms, particularly convolutional neural networks (CNNs), are commonly used for image categorization tasks.

Ximilar provides several off-the-shelf solutions for classifying specific image data, such as stock photos, home decor and furniture images, fashion photos, or trading and collectible cards. Custom models can be easily trained on our platform. Read the articles in our blog to learn about image recognition technology.


What is Visual Search?

Visual & similarity search technology can analyze the overall visual aesthetic of an image or detected object in an image, independent of the origin of images or metadata (such as keywords). It understands the concept of similarity according to your subjective perception. That is why it can provide the most relevant results to image queries, whether you look for the exact match or similar items.


Which collectibles can AI Recognition of Collectibles recognize?

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, as well as antique items.

For collectible cards, the service can identify whether it is a Trading Card Game (Pokémon, Magic The Gathering – MTG, Yu-Gi-Oh!, Lorcana, Flesh and Blood and so on) or a Sports Card (Baseball, Basketball, Hockey, Football, Soccer, or MMA), with several additional features (e.g., signature). It can be easily customized to evaluate images based on your criteria. The full taxonomy of the identification results with all supported games and sports can be found in our documentation page.

For comic books, the service can identify more than 1 million magazines, books and manga – via name, title, publisher, issue number and release date.

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


How Ximilar streamlines image processing tasks and reduces costs?

Ximilar’s systems significantly reduce image processing costs by automating repetitive tasks such as analyzing, tagging and sorting of images. This automation results in significant long-term savings, allowing for continuous 24/7 addition of new visual content without additional metadata.

We’re continually enhancing our platform, which enables us to both build services efficiently and quickly and also to modify existing solutions to suit your needs. We reduce costs and labour by utilizing a combination of pre-trained and new models.

Service use is billed via API credits, with a customizable monthly plan based on your consumption. Using our credit calculator helps you optimize cost-effectiveness. For sudden system loads, you can add extra credit packs to your monthly credit supply.

Once your solution is live, we can continually upgrade and enhance it, altering any component in the modular structure. Our feedback mechanisms help us understand which model performs best, allowing us to refine the solution. Also, our ready-to-use solutions are routinely updated to stay industry-relevant, and these upgrades come at no extra cost.


What are the typical Visual Search applications?

Visual search typically involves searching images or products using an image query, including photos from social media and user-generated content, like smartphone photos. Our Search by Photo combines this technology with detecting individual products in images. One such solution is Search Fashion by Photo.

The technology is frequently employed for similarity searches, particularly for product recommendations in e-commerce. It assesses image or detected object features, like colour, edges, or patterns, to suggest the most similar alternatives.

Another typical use is image & product matching. Since the technology can identify duplicates or nearly identical items in various images with different quality, it can help with curating product galleries and eliminating all unnecessary content.

Even though applications in e-commerce are the most common, visual search provides endless possibilities even in the industrial sector, scientific research or security systems.


Is Ximilar’s visual AI able to handle large datasets and complex images?

Ximilar’s AI solutions were built to handle large datasets containing millions of images. Our cloud doesn’t physically store your image collections for visual search. We process each image once during synchronization, extract descriptive data, and then immediately discard it, allowing for swift image processing. For instance, our largest collections, holding over 100 million images, require only a few hundred milliseconds to search for visually similar items.

Complex images containing more objects, patterns, topics, people or items, can be easily processed with our AI. For instance, our Fashion Search and Home Decor Search solutions automatically detect all fashion apparel or homeware in the images, providing categories and similar stock to each object individually. You can test these solutions in our public demo.

Custom image recognition and detection solutions rely on dedicated training image datasets, whose size depends on the complexity of the problem. For instance, training a model for cat and dog recognition may only require tens of images, while larger projects like our fashion recognition, with thousands of features and tags, necessitate datasets containing thousands of images.

We also enable asynchronous requests. Read more about them in the API Documentation.

 


How does Ximilar approach privacy and data protection issues?

Ximilar prioritizes data security and confidentiality. Our customers particularly value the following rules:

  • We don’t store user images, except for mutually agreed training datasets, secured on Amazon S3 with time-limited links.
  • The intellectual rights to generated image models are shared between you and Ximilar, and we are not authorized to use the models for other customers or internal purposes.
  • We adhere to European regulations, including GDPR, and our data center in Prague is multi ISO-certified.
  • We can sign NDAs and customize image access restrictions based on your needs.
  • Administrators access your image data only when necessary.
  • On-premises installation is possible for larger projects.

Feel free to reach out with questions about ethical considerations regarding privacy and data protection.


Which types of images and formats does Ximilar support?

You can send images in these supported formats to our API (in fields of _base64 or _url): jpg, jpeg, png, webp, heic, bmp, tiff, and jfif. If you upload a gif, only the first frame will be processed. Contact us for customization.


How fast and efficient is the image recognition process?

The speed typically ranges from 5 to 100 milliseconds per image for basic image classification and detection models. This timeframe varies based on factors such as input resolution, connectivity, and the speed of the image CDN used. Our platform’s models are generally very fast, and they can be fine-tuned for even greater efficiency on specialized hardware like GPUs and smartphones.


Go to FAQs