...
Verity API Gateway: The Verity API Gateway receives a page URL request, authenticates the client request and passes the URL to the Verity API.
Verity API: The Verity API initiates the request and then orchestrates the Content Extractor, Text and Image analyses systems to extract the page data and perform the analyses.
Content Extractor: The Content Extractor accepts page requests sent by the Verity API from a queue. The Content Extractor loads the page URL, downloads the page title, metadata, and HTML and saves it as a text string in the database. If a prominent image is identified for the page, the Content Extractor downloads and saves the image to the database with identification information for the associated page. The Content Extractor passes the Page URL and image information on for text and image analysis.
Text Analysis: The Text Analysis engine applies Natural Language Processing (NLP) for text classification (e.g. IAB and Threat categories) and information extraction (e.g. Keywords).
Image analysis: The Image Analysis engine houses GumGum’s core Computer Vision capabilities in a modular architecture. The Image Analysis component passes images through multiple data models to determine their classification information.
Verity Report: The Verity API retrieves the text and image classification results, applies weighting and merging logic to the results, and returns the final Verity page report to the client.
...
Video Analysis
Verity analyzes videos for the purposes of content-level contextual targeting and brand safety.
...
Transcribe Service – Applies automatic speech recognition (ASR) to convert speech to text.
OCR Service – Performs Optical Character Recognition (OCR) to detect text in video and convert the detected text into machine-readable text.
Verity Text Processing – Applies machine learning models to the video metadata, title, transcription text, and OCR text and provides a brand safety and contextual classification report.
...
Video Analysis Process
The Verity video analysis process involves the following core components:
...
Verity API Gateway: The Verity API Gateway receives a video URL request, authenticates the client request and passes the URL to the Verity API.
Verity API: The Verity API passes the request to the Video Transcribe component to orchestrate video transcription and optical character recognition.
Video Transcribe: Video Transcribe downloads the video from the request URL and stores the video. Verity API initiates a transcription job with the transcription service. If the video is in MU38 format it is transcoded prior to transcription. Once the transcription service finishes a job it sends the results back to the object storage service, triggering a notification to the Verity API.
Verity API/OCR service:The Verity API verifies if the transcription results contain a sufficient sample of words. If not, Verity API requests Video Transcribe to initiate an OCR job. Upon OCR job completion, Verity API receives a notification and retrieves the OCR text results. Verity API passes the concatenated text results (comprising transcription, OCR, Client metadata title and description) to Verity Text Processing.
Verity Text Processing: The Text Processing engine processes the video transcription, OCR, client metadata title and description by applying Natural Language Processing (NLP) for text classification (e.g. IAB Content Categories v2.0 and Threat categories) and information extraction (e.g. Keywords).
Verity Report: The Verity API accepts the text analysis results, applies result weighting and merging logic, then returns the final video analysis Verity Report to the client.
...
Brand Safety
Verity Machine learning predicts threat categories by applying data models trained on collections of various kinds of threatening content. Verity’s sophisticated Computer Vision machine learning can identify threatening scenes, such as natural disasters or accidents. Object detection picks out potentially threatening objects within an image, such as weapons, exposed skin or drinks.
...
Clients can set a unique threshold or risk-tolerance level for each threat category. For example, a healthcare provider may choose to set no threshold for the “Medical” threat category, yet higher thresholds for categories that are less suitable for ad placement (e.g., “Hate”, “Violence”, or “Obscene”).
...
Content Classification
Verity works by applying machine learning techniques to relevant content to assign contextual categories.
...