Abstract
This paper investigates the challenging issue of assigning given image-level annotations to precise regions on images. We propose a novel label to region assignment (LRA) technique called Fuzzy-based Contextual-cueing Label Propagation (FCLP) with four parts: First, an image is over-segmented into a set of atomic patches and the local visual information of color features and texture features are extracted. Second, fuzzy representation and fuzzy logic are used to model spatial invariants of contextual cueing information, especially for the imprecise position information and ambiguous spatial topological relationships. Third, labels are propagated inter images and intra images in visual space and in contextual cueing space. Finally, the fuzzy C-means clustering based on K-nearest neighbor (KNN-FCM) is utilized to segment the images into semantic regions and associate with corresponding annotations. Experiments on two public datasets demonstrate the effectiveness of the proposed technique.
Similar content being viewed by others
References
Bar M (2004) Visual objects in context. Nat Rev Neurosci 5:617–629
Biederman Iea (1974) On the information extracted from a glance at a scene. J Exp Psychol 103:597–600
Biederman I, Mezzanotte R, Rabinowitz J (1982) Scene perception: detecting and judging objects undergoing relational violations. Cognit Psychol 14(2)
Cao L, Li F (2007) Spatially coherent latent topic model for concurrent object segmentation and classification. ICCV pp 1–8
Chun MM (2000) Contextual cueing of visual attention. Trends Cognit Sci 4:170–178
Chun MM, Jiang Y (1998) Contextual cueing: implicit learning and memory of visual context guides spatial attention. Cognit Psychol 36:28–71
Davenport JL, Potter MC (2004) Scene consistency in object and background perception. Psychol Sci 15:559–564
Felzenszwalb P, Huttenlocher D (2004) Efficient graph-based imagesegmentation. IJCV 59(2):167–181
Galleguillos C, Rabinovich A, Belongie S (2008) Object categorization using co-occurrence, location and appearance. CVPR
Intraub H (1981) Rapid conceptual identification of sequentially presented pictures. J Exp Psychol Learn Mem Cogn 10:115–125
Jiang Y-G, Ngo C-W, Chang S-F(2009) Semantic context transfer across heterogeneous sources for domain adaptive video search. ACM Multimedia 155–164
Li J, Socher R, Fei-Fei L (2009) Towards total scene understaning: classification, annotation and segmentation in an automatic framework. CVPR
Liu X, Cheng B, Yan S, Tang J, Chua TS, Jin H (2009) Label to region by bi-layer sparsity priors. Proceedings of ACM Multimedia 115–124
Miyajima K, Ralescu A (1994) Spatial organization in 2D images. IEEE International Conference on Fuzzy Systems 100–105
Potter MC (1976) Short-term conceptual memory for pictures. J Exp Psychol Hum Learn Mem 2:509–522
Torralba A, Oliva A, Castelhano MS, Henderson JM (2006) Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. Psychol Rev 766–786
Yuan J, Li J, Zhang B (2007) Exploiting spatial context constraints for automatic image region annotation. ACMMM 595–604
Zahid N, Abouelala 0, Limouri M, Essaid A (2001) Fuzzy clustering based on K-nearest-neighbors rule. Fuzzy Set Syst
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhong, Sh., Liu, Y., Liu, Y. et al. Region level annotation by fuzzy based contextual cueing label propagation. Multimed Tools Appl 70, 625–645 (2014). https://doi.org/10.1007/s11042-011-0954-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-011-0954-3