Skip to main content
Fig. 13 | EURASIP Journal on Image and Video Processing

Fig. 13

From: Line and circle detection using dense one-to-one Hough transforms on greyscale images

Fig. 13

50 best detected lines of the different algorithms in different conditions. Row 1: The SHT uses exhaustive one-to-many voting on Canny contour image (parameters of the Canny detector are σ=1, t 1=6, t 2=1 for column 1, σ=2, t 1=6, t 2=5 for column 2 and σ=1, t 1=3, t 2=1 for column 3). Row 2: the DHT (our method) uses dense voting weighted with the gradient norm, and three scales of estimation (same parameters for the three conditions). Row 3: the PPHT uses one-to-many scheme and adaptive random voting on Canny contour image. (Canny’s parameters vary like row 1; the threshold for line decision is 50 for column 1, 20 for column 2 and 10 for column 3). Row 4: the RHT uses many-to-one random voting scheme on Canny contour image. (Canny’s parameters vary like row 1)

Back to article page