OWD (Object Word Detection)

31/12/2021

Dec 31 , 2021 read

A solution to detect words and objects in a video thanks to AI and Machine Learning (NLP, Speech Analytics...).   

In a few words, the OWD solution lists all the moments (in sequence / second) where words are quoted and allows to indicate when a specific object appears in a video (car, lamp...) or all the sequences where the object in question appears. 

What are the use cases of OWD? 

  • For companies wishing to offer their clients advertisements related to objects and words appearing in the audio and visual of a video on their website. 
  • For a bacteriology laboratory that wants to be alerted when a specific object appears during the culture process, for example. 
  • For MOOC or e-learning platforms, if a student wants to access a specific sequence by entering the object name or the specific word. 
  • For e-commerce sites, to enable them to offer the customer a product that is related to the video and therefore also the advertisements. 
  • For import / export companies in the control of received goods (video controls for approval or refusal) 

This list is not exhaustive. 

Technical principles around the architecture :

Around the environment :

  • Web application (Python development language / Flask framework)
  • Object detection (AI - DL, Dataset: coco, API: OpenCV)
  • Word detection (API: speech recognition)

Recent blogs