Abstract
We have recognized the regions of scene images for image recognition. First, the proposed segmentation method classifies images into several segments without using the Euclidian distance. We need several features to recognize regions. However, they are different for chromatic and achromatic colors. The regions are divided into three categories (black, achromatic, and chromatic). In this article, we focus on the achromatic category. The averages of the intensity and the fractal dimension features of the regions in the achromatic category are calculated. We recognize the achromatic region by using a neural network with suitable features. In order to show the effectiveness of the proposed method, we have recognized the regions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M Mukunoki M Minoh K Ikeda (1996) ArticleTitleA retrieval method of outdoor scenes using object sketch and an automatic index generation method (in Japanese) IEICE Trans J79-D-II 1025–1033
Singh M, Markou M, Singh S (2002) Colour image texture analysis: dependence on colour spaces. ICPR, pp 672–675
J Cheng Y Chen H Lu et al. (2004) ArticleTitleA spatial weighted color histogram for image retrieval IEICE Trans Inf Syst E87-D 246–249 Occurrence Handle10.1109/TITS.2004.838226
Zeng X, Chen Y, Nakao Z, et al. (2003) Image retrieval based on independent components of color histgrams. Proceedings of Knowledge-Based Intelligent information and Engineering Systems. Oxford, pp 1435–1442
H Iyatomi M Hagiwara (2002) ArticleTitleScenery image recognition and interpretation using fuzzy inference neural networks Pattern Recognition 35 1793–1806 Occurrence Handle1017.68139 Occurrence Handle10.1016/S0031-3203(01)00171-6
A Yamamura M Hagiwara (2002) ArticleTitleRecognition of scenery images considering positional relation using fuzzy inference neural networks IEE Jpn Trans 122-C 506–511
SZ Selim MA Ismail (1984) ArticleTitleK-means-type algorithm IEEE Trans Pattern Anal Mach Intell 6 IssueID1 81–87 Occurrence Handle0546.62037 Occurrence Handle10.1109/TPAMI.1984.4767478
S Sakaida Y Shishikui Y Tanaka et al. (1998) ArticleTitleAn image segmentation method by the region integration using the initial dependence of the K-means algorithm (in Japanese) IEICE Trans J81-D-II 311–322
Ball GH, Hall DI (1964) Some fundamental concepts and synthesis procedures for pattern recognition preprocessors. Proceedings of the International Conference on Microwaves, Circuit Theory and Information Theory. pp 281–297
K Takahashi K Abe (1999) ArticleTitleColor image segmentation using ISODATA clustering algorithm (in Japanese) IEICE Trans J82-D-II 751–762
S Ito S Omatu (2002) ArticleTitleKeywords specification for images using sandglass-type neural networks J Signal Process 7 61–68
Schroder M, Dimai A (1998) Texture information in remote sensing images: a case study. Workshop on Texture Analysis, Freiburg, Germany, pp 181–192
Nakayama H, Sone M, Takagi M (1986) Texture analysis of meteorological images by fractal dimension and lower order statistics. IPSJ SIG Technical Reports, CV 44(4)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 10th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2005
About this article
Cite this article
Ito, S., Yoshioka, M., Omatu, S. et al. An image recognition method by rough classification for a scene image. Artif Life Robotics 10, 120–125 (2006). https://doi.org/10.1007/s10015-005-0353-9
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10015-005-0353-9