Sep. 12, 2021
An application programming interface (API) is a set of functions and definitions that enables two different software applications or systems to communicate with each other. Without APIs, developers would need to write custom integrations and scripts in order for these systems to exchange information—a time-consuming and technically challenging process. Chooch’s computer vision API helps users get fast, highly accurate identifications of the objects and concepts in their visual content. Given an image or video, the Chooch computer vision API will return the requested output (e.g. the items or faces in an image), as well as the relevant pixel coordinates.
Chooch enables users to choose from dozens of pre-trained AI models, as well as to develop your own custom models for a wide variety of use cases. Without access to an API, users would have to export these models to any system that needs to perform AI inference. However, this approach has several downsides. First, the file size of AI models may be too large for certain systems (such as embedded and IoT devices). Second, the more systems to which you deploy a model, the harder it will be to keep track of them all and to update them when the model changes.
Instead, users can streamline their AI deployments by taking advantage of the Chooch computer vision API. Each system you deploy captures its own images or videos, and then sends them to a separate host machine running the AI model. Using Chooch’s computer vision API, these two systems can establish a standard protocol for communication. The host machine then takes the input image or video, runs it through the model, and sends the results back to the requester within a fraction of a second.
Ready to get started with an integration? Check out the documentation on the Chooch AI Computer Vision API