HOW TO CALCULATE THE PRECISION AND RECALL AND IoU

Dear all,

I have the groundTruthlabel(g.mat) and prediction (tempSeg1.mat). all attached.

Anyone know how to calculate the precision, recall and IoU for my data?

I tried used this one but error.

[precision,recall] = bboxPrecisionRecall(idxx,tempSeg1)
Error using bboxPrecisionRecall
Expected boundingBoxes to be one of these types:

double, single, uint8, uint16, uint32, uint64, int8, int16, int32, int64

Instead its type was logical.

Error in bboxPrecisionRecall>validateNonTableInput (line 153)
validateattributes(bbox, {'numeric'},...
    
Error in bboxPrecisionRecall (line 110)
validateNonTableInput(boundingBoxes, 'boundingBoxes');

My data is 3D.

Answer 1

[Muskan]

Hi Akmal,

I understand that you are trying to calculate the precision, recall and IoU metrics and you are getting errors while doing that.

I also see from the ‘.mat’ files attached that the type of “tempSeg1” is logical while the expected input type should be either of double, single, uint8, uint16, uint32, uint64, int8, int16, int32, int64.

You can refer to the following documentation for a better understanding of the issue:

https://in.mathworks.com/help/vision/ref/bboxprecisionrecall.html

I hope the above information helps resolve your query.

Thanks