Evaluate specified ROI and return confidence value for each location

[pts, confidences] = hog.detectROI(im, locations)
[...] = hog.detectROI(..., 'OptionName',optionValue, ...)

Input

• im 8-bit 1- or 3-channel image where objects are detected.
• locations cell array of 2-element points {[x,y],...} at which detector is executed. These are top-left corner of candidate points at which to detect objects.

Output

• pts Left-top corner points of detected objects boundaries. A cell array of points where objects are found of the form {[x,y], ...}. The width and height of boundaries are specified by the WinSize parameter. These are the filtered locations at which objects where actually detected.
• confidences vector of confidences for each of the candidate locations (prediction of the SVM classifier).

Options

• HitThreshold Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specfied in the detector coefficients (as the last free coefficient). But if the free coefficient is omitted (which is allowed), you can specify it manually here. default 0
• WinStride Window stride [w,h]. It must be a multiple of block stride. Not set by default in which case it uses CellSize.
• Padding Padding [w,h]. default [0,0]