Machine Learning

UX-Builder offers the broadest and deepest set of AI and machine learning services. We help organizations and individuals solve problems and challenges they might face on most of the day-to-day activities. Our services are divided into two ways:

The ML Kit on-device which runs offline.

The ML Kit on-device which runs offline.

Our Machine Learning Services

Text Recognition

Recognize and extract text from different types of documents, such as scanned paper documents, PDF files or images captured by a digital camera into editable and searchable data.


Best for recognizing sparse text in photos

Recognizes Latin characters

Low latency: use to process photos or frames of video in real time

Runs offline and data stays on the device

Image Labelling

Use Machine Learning to recognise the different entities in an image. You can recognise various entities like animals, plants, food, colors, fictional characters, etc with Image Labeling


400+ labels that cover the most commonly-found concepts in photos

Low latency: use to process photos or frames of video in real time

Runs offline and data stays on the device

Face Detection

Use Machine Learning algorithms to pick out specific, distinctive details about a face, and facial landmarks, now with Face Contours. See more Features below:


Recognize and locate facial features Get the coordinates of the eyes, ears, cheeks, nose, and mouth of every face detected.

Get the contours of facial features.

Recognize facial expressions Determine whether a person is smiling or has their eyes closed.

Barcode Scanning

With ML Kit barcode scanning API, you can read data encoded using most standard barcode formats. Barcode scanning happens on the device, and doesn not require a network connection.


Reads most standard format

Automatic format detection

Extracts structured data

Works with any orientation

Language ID

Automatic language identification has always been a challenging issue and an important research area in speech signal processing. It is the process of identifying a language from a random spoken utterance.


Broad language support. Identifies over one hundred different languages.

Romanized text support. Identifies Arabic, Bulgarian, Greek, Hindi, Japanese, Russian, and Chinese text in both native and romanized script.

On-device Translation

On-device Translation helps you translate text between more than 50 languages. It is intended for casual and simple translations. Translation quality depends on the source and target languages.


Broad language support Translate between more than 50 different languages.

Proven translation models Powered by the same models used by the Google Translate app offline mode.

Dynamic model management Keep on-device storage requirements low by dynamically downloading and managing language packs

Smart Reply

With ML Kit Smart Reply API, you can automatically generate relevant replies to messages. Smart Reply helps your users respond to messages quickly, and makes it easier to reply to messages on devices with limited input capabilities.


The Smart Reply model generates reply suggestions based on the full context of a conversation, not just a single message. This means the suggestions are more helpful to your users.

The on-device model generates replies quickly and does not require you to send users messages to a remote server.

Landmark Recognition

The Landmark recognition API helps you recognize well-known landmarks in an image. Simply pass an image, you get the landmarks that were recognized in it, along with the geographic coordinates and the region of the image. You can also retrieve Graph IDs


Recognizes well-known landmarks

Get Google Knowledge Graph entity ds

Low-volume use free

Object detection and tracking

Object Detection and Tracking API helps you detect and track objects in an image or live camera feed. You can classify detected objects, either by using the coarse classifier built into the API, or using your own custom image classification model.


Fast object detection and tracking Detect objects and get their locations in the image.

Optimized on-Device model.

Prominent object detection Automatically determine the most prominent object in an image.