MediaPipe vs SentiSight.ai

MediaPipe gives developers libraries, tools, ready-to-run models and customizable APIs for adding AI and machine learning to applications. Its vision tasks include face and hand landmarks, gesture recognition, image classification and segmentation, object detection, and pose landmarks. Text tasks cover language detection, classification, embeddings, proofreading and summarization, with audio classification also available. MediaPipe Tasks supports Android, Web/JavaScript, Python and iOS; its cross-platform APIs are described as requiring as few as five lines of code for inference. The optimized on-device pipelines use CPU, GPU and TPU acceleration for real-time use cases. Developers can try web samples in MediaPipe Studio with text, webcam input or uploaded images. Model Maker supports transfer learning for compatible models, but it is deprecated and cannot change a model's original task. Solution API inputs are processed on-device and not sent to Google; usage and performance metrics are sent to Google. The framework can be built from source for Linux, macOS, Windows and Docker, with some configurations marked experimental.

SentiSight.ai is a web-based platform for labeling images and developing image-recognition applications. It supports classification, object detection, and segmentation models, with annotation tools for labels, boxes, polygons, points, polylines, and bitmaps. Smart labeling uses selected foreground and background points to extract an object from an image. Shared projects allow multiple users to label images, while project managers can track progress and time and manage roles and permissions. Image search can find images resembling an uploaded query or similar pairs within a dataset. Pre-trained models cover content moderation, goods classification, automatic hashtags, and people counting. Models can run in the web interface or through a REST API, or offline after downloading a model and setting up a local REST API server. Android and iOS apps make predictions from uploaded images or camera photos, but cannot train models or label images already uploaded. The service has a free plan and a 30-day trial. The Pay-as-you-go plan includes €5 monthly complimentary credits and €20 free credits for new users; listed usage rates include €1 / 1000 predictions, €1 / 1000 labels, and €3.6 / hour of training.