Feature 02
Text, tied to its part.
Values and labels are read in English or Russian and filed under the part they belong to: its own text inside it, and its caption beside it.
What happens
A frozen PP-OCRv5 detector finds the lines of text on the close-up tiles, and its English or Cyrillic recogniser reads each line, whichever its script needs. Each line is given a role: a label, a value, a unit or a button’s text.
What SM1 records
- A part’s own text, read inside its box
- Its caption: the nearest free label beside it
- The role of each line on the screen
Why it matters
A number is only useful with what it measures. Filing each value under its part and caption keeps it searchable by name.
In the scene API
Find a part by what it says.
A search matches names, captions and text. Here the two values of filling unit 2, each with its caption and its text.
Plain HTTP and JSON, on the device beside the screens. The film shows the same requests, with the answers SM1 gave in that session.
GET /api/parts?q=filling+unit+2 [{"part": "Filling unit 2 right", "caption": "right", "text": "126.3", …}, {"part": "Filling unit 2 left", "caption": "left", "text": "136.5", …}]
Pilot programme
Your screens, as data.
Tell us about your control room: how many screens, which systems, and what you would like to know from them. Contact us to join our pilot programme.