Detect lines inside an image or image set

keylines = obj.detect(img)
keylines = obj.detect(imgs)
[...] = obj.detect(..., 'OptionName',optionValue, ...)

Input

• img Input image (first variant), 8-bit grayscale.
• imgs Image set (second variant), cell array of images.

Output

• keylines Extracted lines for one or more images. In the first variant, a 1-by-N structure array. In the second variant of the method, keylines{i} is a set of keylines detected in imgs{i}. Each keyline is described with a KeyLine structure with the following fields:
  • angle orientation of the line.
  • class_id object ID, that can be used to cluster keylines by the line they represent.
  • octave octave (pyramid layer), from which the keyline has been extracted.
  • pt coordinates of the middlepoint [x,y].
  • response the response, by which the strongest keylines have been selected. It's represented by the ratio between line's length and maximum between image's width and height.
  • size minimum area containing line.
  • startPoint the start point of the line in the original image [x,y].
  • endPoint the end point of the line in the original image [x,y].
  • startPointInOctave the start point of the line in the octave it was extracted from [x,y].
  • endPointInOctave the end point of the line in the octave it was extracted from [x,y].
  • lineLength the length of line.
  • numOfPixels number of pixels covered by the line.

Options

• Scale scale factor used in pyramids generation. default 2
• NumOctaves number of octaves inside pyramid. default 1
• Mask optional mask matrix to detect only KeyLines of interest. It must be a logical or 8-bit integer matrix with non-zero values in the region of interest. In the second variant, it is a cell-array of masks for each input image, masks{i} is a mask for imgs{i}. Not set by default.

KeyLine is a struct to represent a line.

As aformentioned, it is been necessary to design a class that fully stores the information needed to characterize completely a line and plot it on image it was extracted from, when required.

KeyLine class has been created for such goal; it is mainly inspired to Feature2d's KeyPoint class, since KeyLine shares some of KeyPoint's fields, even if a part of them assumes a different meaning, when speaking about lines. In particular:

• the class_id field is used to gather lines extracted from different octaves which refer to same line inside original image (such lines and the one they represent in original image share the same class_id value)
• the angle field represents line's slope with respect to (positive) X axis
• the pt field represents line's midpoint
• the response field is computed as the ratio between the line's length and maximum between image's width and height
• the size field is the area of the smallest rectangle containing line

Apart from fields inspired to KeyPoint class, KeyLines stores information about extremes of line in original image and in octave it was extracted from, about line's length and number of pixels it covers.