Original images without and with added noise (SNR = 13dB)

Contours detected with our approach [1], for the noiseless and the noisy image

Contours detected with the standard Canny edge detector [2], for the noiseless and the noisy image

Contours detected with a like-CARTOON multiscale edge detector [3], for the noiseless and the noisy image

Contours detected with a single scale contour detector with surround inhibition [4], for the noiseless and the noisy image

Contours detected with a multiscale contour detector with surround inhibition [5], for the noiseless and the noisy image

References




[1] G. Papari, P. Campisi, N. Petkov, A. Neri
A biologically motivated multiresolution approach to contour detection
To appear on: JASP 2006, Special Issue on Human Perception

[2] J.F. Canny
A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence 8 (6) (1986) 679–698.

[3] W. Richards, H.K. Nishihara, B. Dawson
CARTOON: A Biologically Motivated Edge Detection Algorithm
MIT A.I. Memo No. 668.

[4] C. Grigorescu, N. Petkov, M.A. Westenberg
Contour Detection Based on non-Classical Receptive Field Inhibition
IEEE Transactions on Image Processing, 12 (7) (2003) 729-739.

[5] G. Papari, P. Campisi, N. Petkov, A. Neri
A multiscale approach to conour detection by texture suppression
SPIE Image processing: algorithm and systems, 2006, Vol. 6064A, San Josè, CA.