ai powered

Image recognition &
visual search API
for your business

Video introduction Check it out — it’s easy

Visual AI That Helps in Many Areas

fashion

e-commerce

real-estate

stock photo

surveillance

medtech

industries

Ximilar Basics in 2 minutes

Find the Ideal Solution For Your Business

Image Similarity

Similarity search, analysis and comparison of photos & pictures. Suitable for duplicate photo matching or similar products recommendations.

Object Detection

Train your custom automatic object detection able to spot, mark & count objects of different types.

Categorization & Tagging

Train your own AI to categorize, tag and organize images automatically. Combine it with other services & use it via API or deploy offline.

Annotate

Advanced image annotation tool for detailed and quick annotation of large collections in a team. Draw boxes & polygons; track progress on the jobs.

Fashion Tagging

Auto-tagging of fashion items, such as footwear, accessories, jewellery, clothing and underwear. Extract all attributes from the picture and recommend the best products.

Flows

Chain & combine categorization, tagging, object detection, image similarity tasks, and ready-to-use services. Re-train, add or remove any part anytime.

Find your Visual AI solution See them all

Some of our Users

We have been using the evolving Ximilar technology for quite some time and it keeps pace with our needs.

Tom Bennett co-founder at Pond5

The Ximilar team is flexible and always tries to find a solution to maximally meet our requirements.

Ondřej Raškapartner at Miton

The Ximilar technology has been working reliably for several years on our collection of 50M+ creative photos.

Pavel MackůCEO of Profimedia

Pixmac used Ximilar already in 2010 and the technology has made a big leap since then. The cooperation has always been great.

Vita Valkaformer CEO at Pixmac

Way better similar results in our 5 million stock images. Customers can find visual similars by uploading a photo. The integration was fast. We recommend it!

Amos Struckco-founder at StockPhotos

Babyndex uses Annotate, which is excellent, and Image Recognition. This is the service that I could easily set up myself. Ximilar has helped in improving accuracy and from that day on, it works.

Zajzon Bodóco-founder at Babyndex

Developers First

We take care of the complexity behind and wrap it in a few lines of code.

full documentation

curl -H "Content-Type: application/json" -H "authorization: Token __API_TOKEN__" https://api.ximilar.com/recognition/v2/classify -d '{"task_id": "__TASK_ID__", "version": 2, "records": [ {"_url": "https://bit.ly/2IymQJv" } ] }'

# pip install ximilar-client
from ximilar.client import RecognitionClient

client = RecognitionClient(token="__API_TOKEN__")
task, status = client.get_task(task_id="__ID_TASK__")

# you can send image in _file, _url or _base64 format
# the _file format is intenally converted to _base64 as rgb image
result = task.classify([{"_url": "__URL_PATH_TO_IMG__"}, {"_file", "__LOCAL_FILE_PATH__"}, {"_base64": "__BASE64_DATA__"}])

import requests 
import json 
import base64 
 
endpoint = 'https://api.ximilar.com/recognition/v2/classify/' 
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 = { 
    'task_id': __TASK_ID__, 
    'records': [ {'_url': __IMAGE_URL__ }, {"_base64": encoded_string } ] 
} 
 
response = requests.post(endpoint, headers=headers, data=json.dumps(data))

$curl_handle = curl_init("https://api.ximilar.com/recognition/v2/classify");

$data = [
    'task_id' => __TASK_ID__,
    'records' => [
        [ '_url' => 'https://bit.ly/2IymQJv' ],
        [ '_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);

if ($error_msg) { // Handle error
    print_r($error_msg);
} else { // Handle response
    print_r($response);
}
curl_close ($curl_handle);