VISIO INGENII is a medium enterprise providing machine learning & image processing solutions. We are a turn-key solutions company and have unmatched capabilities in the field of Machine Vision, Machine Learning, Artificial Intelligence and Robotics.

We have been providing the services and solutions for custom object detection and recognition solely based on our expertise in neural network-based training including face detection and recognition, people detection, behavioural analysis, medical imaging, fire and smoke detection.

We have succeeded in winning trust from our clients by providing some of these solutions (customized) for Border Security and Automatic Image Analysis/Video Surveillance scenarios. We also support organizations in their research and development activities by complementing as their extended research team.

Engineers and Scientists at VISIO INGENII have an excellent track record and industry knowledge in working with high-end technically complex projects thus ensuring there is next-generation innovation and cutting-edge application for real world problems.


Visio Ingenii has been applying its neural network approaches for more than 5 years and have successfully been able to achieve higher accuracies in the most challenging field i.e. Face Recognition and Object Detection. Given the premise, Visio Ingenii has used these approaches to build application and solutions to cater to even more complex issues such as

Fire Detection – identifying fire pattern and raising the corresponding level of severity. Pedestrian-Face Detection – identifying pedestrians and face detection Specific or defined object detection – Specific Object(s) detection and mining information against the detected object for the user to take necessary actions.

Although these methods may have been derived and inspired from the existing approaches such as

Tensor Flow Keras Regression YOLO Single Shot Detectors (SSD) Combination of RNN methods.

What makes our solution different, accurate and more effective is what our research has paid more attention to. These efforts have led us to design our very own “key features” or what we refer to it as “VI Points”. These points are designed to identify the key patterns in the presented image and collect necessary attributes to match it with the existing samples in the network and provide an output designed around user's preference.