We are pleased to announce that SentiSight.ai Computer Vision engine has been integrated into Eden AI API.
SentiSight.ai from Neurotechnology is a place where users can build AI models for image recognition using modern techniques. The platform allows for capabilities such as object detection and image classification. It is easy to use (no coding required) and automatically performs most image processing tasks.
Neurotechnology was founded to use neural networks for various applications such as biometric person identification, computer vision, robotics, and artificial intelligence. To meet the requirements of a variety of applications, Neurotechnology has developed many advanced algorithms based on computer vision. For example, SentiSight.ai has tools designed to support interactive learning of patterns without coding and faster labeling of images, reducing the user's effort in data exploration.
Eden AI offers SentiSight AI solutions on its platform (Object Detection, Explicit Content Detection, Image Detection, OCR) amongst several other technologies. We want our users to have access to multiple AI engines and manage them in one place so they can reach high performance, optimize cost and cover all their needs. There are many reasons for using multiple AI APIs :
We had the chance to talk to SentiSight.ai Team Lead and PhD Karolis Uziela, who agreed to answer some of our questions:
SentiSight.ai is developed by Neurotechnology, a company with more than 30 years of experience in high-precision algorithm development. The company mainly focuses on biometric algorithm development such as fingerprint, iris and face recognition. The company's algorithms have achieved top results in independent technology evaluations, including NIST MINEX, PFT, FRVT, IREX and FVC-onGoing. Neurotechnology research and development areas of interest also include image and video recognition algorithms, robotics, stock analytics, ultrasound and brain-computer interface research.
SentiSight.ai is a successor of Neurotechnology’s earlier product SentiSight SDK. Unlike its predecessor, SentiSight.ai is a web-based image recognition and labeling platform. The first version of SentiSight.ai was released in November 2018 with two goals in mind. The first goal was to create a user-friendly platform for training and using machine learning models for people who don’t necessarily have prior experience with machine learning and AI. The second goal was to create a platform for efficient and convenient image annotation, which could help even large AI companies to curate their data and prepare for machine learning pipelines. These two purposes are largely related and complementary to each other and nowadays SentiSight.ai is capable of serving them both.
SentiSight.ai models can be used in three different ways. The first option is to use them online via the web platform’s interface. This option is very useful for testing the newly trained models and for using the models for AI-assisted image annotation. The predictions made via the web interface can be downloaded in a .json format.
The second option which is probably most familiar to Eden AI users is to use SentiSight.ai models via cloud REST API. We provide code samples in several different languages as well as a Swagger specification.
The third option is to use SentiSight.ai models by downloading the “offline” version. The “offline” version contains a ready-to-launch script that starts a local REST API server, so you can make local REST API queries from the same device that runs the server or from any other device which is connected to that local device. The “offline” version is free to try for 30 days and if you want to continue using it after the trial period ends, you need to buy a license.
In addition to image recognition tools, SentiSight.ai offers many useful functionalities for image annotation project management, such as image annotators labeling time and efficiency tracking, user role management, advanced image filtering tools, etc. We also offer a smart labeling tool that can greatly speed up bitmap labeling.
Our most recent major addition to the SentiSight.ai platform was the functionality to train image segmentation models. Right now we are working on a major release after which our user interface will be even faster and smoother for our users.
Our customers can be divided into two categories: the ones who use SentiSight.ai for image annotation and the ones who use SentiSight.ai for image recognition tasks. The first customer segment includes image annotation companies and companies that carry out machine learning projects and are in need of a convenient and efficient tool for managing image annotation tasks. The second customer segment includes companies that are outside the machine learning field but would like to carry out machine learning projects. For these companies, we often offer custom projects where our experts develop a solution tailored to the company’s needs.
Eden AI is an ambitious project that helps users to get the best of what is on offer in the AI field. The major advantage of Eden AI is that its users are able to use machine learning models from multiple sources just by creating a single account and using a single interface. We like this idea very much and would like to make SentiSight.ai accessible in as many ways as possible.
To use SentiSight.ai on Eden AI, you'll need to access the documentation and call the API:
Eden AI is the future of AI usage in companies. Our platform not only allows you to call multiple AI APIs but also gives you :
You can see Eden AI documentation here.
In this article, we explain how the mapping between the input language and the languages supported by the providers is performed to facilitate access to one of our AI engines.