Who We Are
Quantian Technologies is an Artificial Intelligence (AI) products company specializing in Computer Vision. Our core product platform Eyerys is built around in-house designed computer vision and other AI algorithms. We currently have three focus areas:
- Smart staff tracking and field management
- Smart Surveillance enabling Smart Cities
- Smart transport focusing on road safety
Our AI Capabilities
Our AI, ML engineers are continuously building increasingly sophisticated AI tools and capabilities. These core components are then integrated by our architects to design and develop custom solutions for specific client needs. Check out few of these utilities yourselves though real time demos below.
Facial Recognition
Facial recognition, an important tenet of machine learning, is widely used to detect and identify human faces. Many new businesses utilizing this top-notch technology have been established lately. At Quantian, we build AI face recognition apps and models based on accurate training data.
Face Mask Detection
Quantian's face mask detection uses advanced facial markers recognition technology to instantly detect if the person is wearing a face mask. This is particularly important during times such as COVID when public health & safety is paramount.
Fake Image Detection
Quantian's fake image detection uses advanced facial markers recognition technology to instantly detect the image is fake or real. As images are one of the most common types of media share among users on social media. So, there is a need for monitoring of images contained in social media.
People Detection & Counting
Quantian's people counting algorithm recognizes people from a video feed both outdoors and indoors to automaically count the number of people in the frame. It works even with average feed quality of a typical CCTV camera. This has significantly wide use like in public events, factories, large commercial complexes, public spaces like parks and more.
Text Recognition
Whether it's recognition of car plates from a camera, or hand-written documents that should be converted into a digital copy, this technique is very useful. We use sophisticated LLM models to read PDFs and interpret natural language thus cutting down on data processing times.
Vehicle Number Plate Detector
Our solution recognize license number plates. In order to detect license number plates, we will use OpenCV to identify number plates and python pytesseract to extract characters and digits from the number plates.
Activity Monitoring
Human Pose Estimation is a general problem in Computer Vision where we detect the position and orientation of an object. This usually means detecting keypoint locations that describe the object as per requirement for specific positions.
Drowsiness Detection
Our solution to this problem is to build a detection system that identifies key attributes of drowsiness and triggers an alert when driver is drowsy before it is too late. In our drowsiness detector, we are monitoring the eye aspect ratio to see if the value falls but does not increase again, thus implying that the person has closed their eyes.
Object Detection & Counting
Automate image and video analysis with easy-to-use machine learning solutions to identify and count items, people, animals, objects — you name it.
Face Counting In a Frame
In crowded places, it can be difficult for systems to obtain an accurate count of the number of people by detecting faces, as faces may overlap or manual may counting may miss count the total number. Quantian Face counting technology uses AI to detect and count the number of faces in a frame, making it possible to provide a precise count of the number of people in a crowd.
Language Translation
Quantian's Language conversion application offers a RESTful API to translate a text from any language to any language. For the actual translation, it is using “Googletrans” which in turns uses Google Translator to get the target translation. The text with source and target language are delivered to the application via its RESTful API.
Voice Conversion
Quantian's voice cloning algorithm is deep learning algorithm allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a speech-to- text and text-to-speech model trained to generalize to new voices.