Thermoquaesitor Temperature Detector API enables applications to detect temperature from a thermal image based on palette color scale. It is a cross browsers REST API which get a JSON input with a still photo (as base64 encoded string).
It works also with an URL of the image together with the scale of temperatures (units may be Celsius, Kelvin or Fahrenheit) and returns a JSON string which contains predictions with a certain amount of probability (filtered for an output with minimum 50%), bounding boxes of maximum detected temperatures in the eyes zone of the human face with its top, left, width, and height values.
Thermoquaesitor outputs a base64 encoded string photo which is the original input photo with drawn bounding boxes upon it and with the maximum temperature values detected according to input temperature scale photo. For one still photo the API may return multiple predictions with different probability scores of detected temperatures of human faces.
Pricing packages count the predictions, so for one request, multiple predictions may be counted. Thermoquaesitor filters the results of predictions so only the predictions are displayed with a probability score higher than 50%. Of course, there are some limitations in order to get higher accuracy. It is recommended to use properly exposed, unobstructed JPEG photos at 1920x1080 (Full HD resolution) where the ratio between the height of the bounding box and height of the entire picture should be at least 1:15. For ratios like 1:16, 1:17, 1:18 and so on the accuracy is lower and the AI algorithm may not see the human face and the prediction score will below. The API does not store pictures. The quality and the angles of the camera are very important and it contributes to a higher detecting accuracy. It should have varifocal lenses, high shutter speed, and good infrared lighting beam.
Although this Temperature Detector API (currently a temperature detection SDK is not offered) is intended for software development and therefore developers, there is also here a temperature detector on human face thermal image online application that may be used to check the input and output JSON of the API.
Since February of this year, ProgrammableWeb has been tracking APIs that provide access to data related to the COVID-19 pandemic. This article highlights the available APIs. The World Health Organization now reports that the virus has infected over 40,000,000 people across more than 200 countries.
Sixteen APIs have been added to the ProgrammableWeb directory in categories including CRM, Coronavirus, and Weather. Highlights include the MyRadar API for nowcasting, an API for detecting human temperatures, and several NICE inContact APIs. Here's a rundown of the latest additions.