Cloudmersive

About Cloudmersive

Cloudmersive's Image Recognition and Processing API provides deep learning-based endpoints for analyzing images, including face detection with landmark identification (eyebrows, eyes, nose, lips, chin), face comparison and matching against a reference face, and age and gender classification. It also offers people and object detection, content moderation for Not Safe For Work/Racy classification, automatic image captioning, artistic AI-based image filters, and text extraction/OCR including document, receipt, and license plate reading, along with text location and segmentation within images.

Client libraries are available for C#/.NET/.NET Core, Java, Node.JS, Python, PHP, Ruby, Objective-C, and Drupal, with documentation provided via Swagger/OpenAPI specifications. The API can be accessed from the public cloud or deployed to a managed instance, private cloud, on-premises data center, PaaS environment (including Azure Kubernetes Service and Azure App Service), or government cloud region.

The product is aimed at developers and businesses needing to integrate image analysis capabilities such as facial recognition, content moderation, or OCR into their applications. A free tier of 600 API calls per month with no expiration is offered, and paid plans for individual capabilities such as Face Recognition, People and Object Detection, and Content Moderation are listed at $2,000 per month.

Key features

• Face detection with landmarks (eyes, nose, lips, chin, eyebrows)
• Face comparison and matching for identity verification
• Age and gender classification from photos
• Object and people detection in images
• Content moderation for Not-Safe-For-Work/racy images
• Text extraction and OCR from photos

Frequently asked questions