Azure Content Moderator, from Microsoft's Cognitive Services Decisioning tools available on Azure, provides automated image, text, and video moderation. The service provides detection of potential offensive and unwanted images, filtering of possible profanity and undesirable text, or moderation of adult and racy content in videos.

Image moderation - Enhance the user's ability to detect potentially offensive or unwanted images through machine learning-based classifiers, custom lists, and optical character recognition (OCR).
Text moderation - Use content filtering to detect potential profanity in more than 100 languages, flag text that may be deemed inappropriate depending on context (in public preview), and match text against your custom lists. Content Moderator also helps check for personally identifiable information (PII).
Video moderation - Enable machine-assisted detection of possible adult and racy content in videos. The video moderation service (in public preview) is available as part of Azure Media Services.
Human review tool - The best content moderation results come from humans and machines working together. Use the review tool when prediction confidence can be improved or tempered with a real-world context.

Content moderator enhances the user's ability to detect potentially offensive or unwanted images through machine-learning based classifiers, custom blacklists, and optical character recognition (OCR). It helps users detect potential profanity in more than 100 languages and match text against your custom lists automatically. Content Moderator also checks for possible personally identifiable information (PII). Each Text API call can contain up to 1,024 characters each. Scan images (minimum 128 pixels, maximum 4MB size) for adult and racy content, optical character recognition (OCR) and face detection. You can also match against custom image lists. Each API call is a transaction.

Azure Content Moderator

What is Azure Content Moderator?

Categories & Use Cases