Abstract
The processing of images representing natural scenes requires substantial elaboration at all levels: preprocessing, segmentation, recognition, and interpretation. These steps unmistakably influence the result quality of a vision system, so it must be endowed with some capabilities. We present here the vision problem in terms of internal organization and information management. The object is represented on a scale of categories and the task of the recognition algorithms is to find the most detailed category according to information extracted from the image. All tasks operate on one level. On this principle, we propose a model for the internal representation of a vision system, which tries to generalize the recognition of objects using categorization and cooperation.
Similar content being viewed by others
References
El kharki O, Sadgal M, Ait Ouahman A (1999) La Cartographie automatique à partir d’images aériennes (site de Rabat –Salé, Maroc). Première rencontre sur les systèmes électroniques et informatiques SEI’99, organisée par la FST de Fés-Saiss (Morocco), 13–14 October 1999
Walter V (1998) Automatic classification of remote sensing data for GIS database revision. In: IAPRS 32(4):545–552
Airault S, Jamet O (1995) Détection et restitution automatique du réseau routier sur images aériennes. Traitement du Signal 12(2):189–200
Edelman S, Dudevani-Bar S (1997) Visual recognition and categorization on the basis of similarities to multiple class prototypes. MIT Press, Cambridge, MA
Basri R (1996) Recognition by prototypes. Int J Comput Vis 19:147–168
Sadgal M, El Fazziki A (2000) Rôle De La Catégorisation Dans La Reconnaissance d’objets. MCSEAI’2000, Fès, Morocco, 1–3 November 2000
Sadgal M, El Fazziki A (2001) Un Modèle de Catégorisation dans les Systèmes de Vision. TELECOM’2001 & 2èmes JFMMA, Casablanca, 17–19 October 2001
El Kharki O, Ait Belaid M, Ait Ouahman A, Sadgal M, Bijaber N (2002) L’application de la télédétection et des systèmes d’information géographique à l’élaboration de la carte d’occupation du sol dans la province d’Oujda au Maroc. Journal Maghrebien de physique 2(1)
El Kharki O, Ait Belaid M, Ait Ouahman A, Sadgal M, Bijaber N (2002) Classification of multispectral image using ISODATA algorithm. AMSE J, paper no. 01315 (1B)
El Kharki O, Sadgal M, Ait Ouahman A, El Himdy A, Ait Belaid M (2000) Automatic cartography from aerial images (site of Salé, Morocco). Int Arch Photogramm Remote Sens XXXI0II(B2):179–183
Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psych Rev 94:115–147
Hummel J, Biederman I (1992) Dynamic binding in a neural network for shape recognition. Psych Rev 99:480–517
Edelman S (1999) Representation and recognition in vision. MIT Press, Cambridge, MA
Edelman S, Bülthoff HH (1992) Orientation dependence in the recognition of familiar and novel views of three-dimensional objects. Vis Res 32(12):2385–2400
Tarr M, Williams P, Hayward W, Gauthier I (1998) Three-dimensional object recognition is viewpoint-dependent. Nat Eurosci 1:275–277
Poggio T, Edelman S (1990) A network that learns to recognize 3D objects. Nature 343:263–266
Touzi R (1988) Analyse d’images radar en télédétection: améliorations radiométriques, filtrage du speckle et détection des contours. Thèse de doctorat no 258, Université Paul Sabatier, Toulouse, France
Tupin F, Maitre H, Mangin J-F, Nicolas J-M, Pechersky E (1998) Detection of linear structures in SAR images: application to road network extraction. IEEE Trans Geosci Remote Sens 36(2):434–453
Lopès A, Fjørtoft R, Ducrot D, Marthon P, Lemar’echal C (1999) Segmentation of SAR images in homogeneous regions. In: Chen CH (ed) Information Processing for Remote Sensing. World Scientific, Singapore
Wrobel B, Monga O (1987) Segmentation d’images naturelles : coopération entre un détecteur contour et un détecteur région. In Actes du Onzième colloque GRETSI, Nice, France
Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptron, madaline and back-propagation. Proceedings of the Institute of Electrical and Electronic Engineers 78:1415–1442
Ayache N, Faugera OD (1986) HYPER: a new approach for the recognition and positioning of two-dimensional objects. IEEE Trans PAMI 8(1):44–54
Mel B (1997) SEEMORE: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition. Neural Comp 9:777–804
Rosch E, Mervis CB, Gray WD, Johnson DM, Boyes-Braem P (1976) Basic objects in natural categories. Cognit Psych 8:382–439
Rosch E (1978) Principles of categorization. In: Rosch E, Lioyd B (eds) Cognition and categorization. Erlbaum, Hillsdale, NJ, pp 27–48
Erickson MA, Kruschke JK (1998) Rules and exemplars in category learning. J Exp Psych Gen 12(7):107–140
Deriche R (1990) Fast algorithms for low-level vision. IEEE Trans Pattern Anal Mach Intell 12(1):78–87
Comaniciu D, Meer P (1999) Mean shift analysis and applications. In: 7th International Conference on Computer Vision, Kerkyra, Greece, September 1999, pp 1197–1203
Derrode S, Pieczynski W (2002) SAR image segmentation using using generalized pairwise Markov chains. SPIE’s International Symposium on Remote Sensing, Crete, Greece, September 2002, pp 22–27
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sadgal, M., El Fazziki, A. & Ait Ouahman, A. Aerial image processing and object recognition. Vis Comput 21, 118–123 (2005). https://doi.org/10.1007/s00371-004-0275-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-004-0275-x