Image Recognition

Custom image categorization, tagging or object detection with your own labels. Use sleek user interface to upload training images and then just click to train your machine learning model. ML/AI cannot be easier.
  • Recognize
  • Any image
  • Custom training set

Deep Image Categorization & Tagging

Machine learning gives computers the ability to learn without being explicitly programmed. You don’t need to be rocket scientist to create machine learning models with Ximilar App. Create a task to predict your categories or tags, upload your training image data to system and click one button.

It does not matter if you need to distinguish cats from dogs or compare types of cancer cells. Our ML/AI models can handle hundreds of labels & predict several images per second. And if you need a bigger throughput, contact us and we would show you the universe of possibilities delivered by AI.

If you have a more complex problem, you can divide it into individual image recognition models and then chain them back using our revolutionary concept of Flows.

coffee

beverage

sandwich

Tagging — Images are tagged with multiple labels per image, such as shoe, brown, label, stitching, leather, numbers. Labels correspond to various features or objects contained in a single picture.

Categorization — Every image belongs into a single category, such as drink or food. Every image should contain a single subject to be recognized by the categorization task.

Setup your Custom Recognition in 5 minutes

1Define

Define your categories and upload sample images.

Picture of Define

2Train

Define your categories and upload sample images.

Picture of Train

3Recognize

Define your categories and upload sample images.

Picture of Recognize

Try it yourself: Login to App

Custom Object Detection

In some cases, you don’t want to only assign categories or tags to your images but you want to detect objects. The main differences are that with detection, you get positions (bounding boxes) of the objects and also you can detect more than one object of the same type on one image. Accordingly, your training data need bounding boxes to mark the objects to detect, but our slick GUI will make this task a piece of cake. Or our professional content curators can help with that! From the machine learning perspective, object detection is more difficult than categorization/tagging, but it’s up to us.

Typical Use Cases for Detection

Human & Face Detection

Detect People or Faces and predict age, gender or more specific features in security camera footage.

Satellite Imagery Analysis

Detect vehicles or other recognizable object and count free parking spots or predict fires.

Consumer Item Matching

Autodetect consumer items in a photo and find them in your e-commerce outlet. Quick.

Production Quality Control

Detect anomalies and defect in your production line and count quality of the manufactured products.

Brand Tracking

Logo detection and brand visibility tracking in still photo camera photos or security footage.

Team of Editors

Do not want to play with data? We can build your own object detector. We will obtain data, our annotators will label images with bounding boxes. And then we will train and deploy your model.

Technology Stack

We use state of the art neural network models & machine learning techniques. Constantly trying to improve the technology so you always have the best quality available. Each model has millions of parameters which can be processed by CPU or GPU. Our intelligent algorithm picks from several models & uses the best performing.

  • Tensorflow-Logo
  • Docker-Logo
  • Nvidia-Logo
  • IbmCloud-Logo
  • Python-Logo

API Documentation

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

full documentation 
import requests 
import json 
import base64 
 
url = '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)) 
if response.raise_for_status(): 
    print(json.dumps(response.json(), indent=2)) 
else: 
    print('Error posting API: ' + response.text)
$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);
Make the leap forward Sign-up Now pricing