Fast labelling of natural scenes using enhanced knowledge

Pattern Analysis and Applications

Volumn 4, Issue 1, 2001, Pages 20-27

  Hayashi, Hiroki ^a   Kudo, Mineichi ^a   Toyama, Jun ^a   Shimbo, Masaru ^a  

^a HOKKAIDO UNIVERSITY   (Japan)

Author keywords

Image interpretation; Knowledge enhancement; Labelling; Local hill climbing; Natural scene; Region adjacency graph

Indexed keywords

EID: 0035532419     PISSN: 14337541     EISSN: None     Source Type: Journal    
DOI: 10.1007/s100440170021     Document Type: Article

References (20)

1. Binaghi E, Brivio PA, Ghezzi P, Rampini A, Zilioli E. A hybrid approach to fuzzy land cover mapping. Pattern Recognition Letters 1996; 17(13): 1399-1410
2. Olson CF. Connectionist networks for feature indexing and object recognition. Proceedings of Computer Vision '96 and Pattern Recognition, IEEE Press, 1996; 907-912
3. Kim JH, Yoon SH, Sohn KH. A robust boundary-based object recognition in occlusion environment by hybrid hopfield neural networks. Pattern Recognition 1996; 29(12): 2047-2060
4. Trytten DA, Tuceryan M. The construction of labeled line drawings pfrom intensity images. Pattern Recognition 1995; 28(2): 171-198
5. Liu HH, Young TY, Das A. A multilevel parallel processing approach to scene labeling problems. IEEE Trans Pattern Analysis and Machine Intelligence 1988; 10(4): 586-590
6. Prager JM. Extracting and labeling boundary segments in natural scenes. IEEE Trans Pattern Analysis and Machine Intelligence 1980; 2(1): 16-27
7. Yakimovsky Y, Feldman JA. A semantics-based decision theory region analyzer. Proceedings of International Joint Conference on Artificial Intelligence, 1973; 580-588
8. Tenenbaum JM, Barrow HG. Experiments in interpretation-guided segmentation. Artificial Intelligence 1977; 8(3): 241-274
9. Mota FA, Velasco FRD. A method for the analysis of ambiguous segmentations of images. IEEE Trans Pattern Analysis and Machine Intelligence 1986; 8(6): 755-760
10. Wright WA. Image labelling with a neural network. Proceedings of the 5th Alvey Vision Conference, 1989; 227-232
11. Modestino JW, Zhang J. A Markov Random Field model-based approach to image interpretation. IEEE Trans Pattern Analysis and Machine Intelligence 1992; 14(6): 606-615
12. Kim IY, Yang HS. Efficient image labeling based on Markov Random Field and error backpropagation network. Pattern Recognition 1993; 26(11): 1695-1707
13. Hayashi H, Kudo M, Toyama J, Shimbo M. An adjacency based fast image labeling of natural scenes. Preprint of Info-Hokkaido '98, Hokkaido Chapter of Information Processing Society of Japan, 1998; 141-142 (in Japanese)
14. Hayashi H, Kudo M, Toyama J, Shimbo M. An image segmentation based on coloristic and spatial information. Preprint of Info-Hokkaido '96, Hokkaido Chapter of Information Processing Society of Japan, 1996; 55-54 (in Japanese)
15. Haralick RM, Shanmugam K, Dinstein I. Texture features for image classification. IEEE Trans Systems, Man and Cybernetics 1973; 3: 610-621
16. Hannah I, Patel D, Davies R. The use of variance and entropie thresholding methods for image segmentation. Pattern Recognition 1995; 28(8), 1135-1143
17. Lu HQ, Aggarwal JK. Applying perceptual organization to the detection of man-made objects in non-urban scene. Pattern Recognition 1992; 25(8): 835-853
18. Liu Y, Huang TS. Determining straight line correspondences from intensity images. Pattern Recognition 1991; 24(6): 489-504
19. Duda RO, Hart PE. Use of the Hough transformation to detect lines and curves in pictures. Comm ACM 1972; 15: 11-15
20. Yuan J, Suen CY. An optimal O(n) algorithm for identifying line segments from a sequence of chain codes. Pattern Recognition 1995; 28(5): 635-646