Calculating points X,Y from a Bounding box for the original image size

[phpgiik]

I'm new to Face Model's bounding box values here, so I need some help. Based on the description Face Detection Model's response on this page https://www.clarifai.com/models/face-detection-image-recognition-model/a403429f2ddf4b49b307e318f00e528b#documentation, how would you calculate to arrive at top-left corner at (208 x, 83 y) and bottom-right corner at (175 x, 139 y)? If anyone can help me understand this calculation so I can draw a blurry box around the face on the original image.

given original image size 500 width, 333 height
Bounding Box:{
"top_row": 0.22296476,
"left_col": 0.6717238,
"bottom_row": 0.33909792,
"right_col": 0.74911636
}

the top-left coordinate of the image is (0.0, 0.0), and the bottom-right of the image is (1.0, 1.0)

[jared]

Hi @phpgiik - the calculations are essentially percentages that are measures from the (0,0) top-left corner of the image and you can interpret them as:

The Top Left Corner of the bounding box is 22% from the top and 67% from the Left
The Bottom Right Corner of the bounding box is 33% from the top and 75% from the left

The corresponding "pixel" coordinates of this box would be:

Top Left: (335, 74)
Bottom Right: (375, 110)

Let me know if you have any follow-up questions on this!

[davidniki02]

Hi, I've written an entire topic for the same issue - I hope it helps you especially if you use nodejs:
https://chatbotnewsdaily.com/guess-who-a-chatbot-for-face-detection-and-image-blurring-with-pure-node-js-2c3833835ea1

[phpgiik]

I found this example that draw a blur box on a base64 string on client http://jsfiddle.net/nwellcome/27QUM/
Have you found a solution that we can be able to draw a bounding box (I meant manipulating a graphic) on a base64string on Node's Server side without OS dependencies? I know this is a stupid question and it's impossible to alter/manipulate a base64string; but I'd love to know the solution. Right now, all I can do is get a bounding box from Clarify and draw it on HTML5 canvas 2dContext on Chrome/FF/IE. This works great on client with 3-4 lines of codes.

[sudha]

How can i calculate x,y, weight and higth values to draw rectangle in image with celebrity model boundrybox values