Scenery image recognition and interpretation using fuzzy inference neural networks

Abstract In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K -means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.

[1]  John M. Gauch,et al.  Image segmentation and analysis via multiscale gradient watershed hierarchies , 1999, IEEE Trans. Image Process..

[2]  Hiroshi Nagahashi,et al.  Active region segmentation of color images using neural networks , 1998, Systems and Computers in Japan.

[3]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[4]  Bruce A. Draper,et al.  The schema system , 1988, International Journal of Computer Vision.

[5]  Y. Ohta.  Knowledge-based interpretation of outdoor natural color scenes , 1998 .

[6]  Lance M. Kaplan.  Extended fractal analysis for texture classification and segmentation , 1999, IEEE Trans. Image Process..

[7]  Li-Xin Wang.  Training of fuzzy logic systems using nearest neighborhood clustering , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[8]  Masao Sakauchi,et al.  A Construction of a New Image Database System which Realizes Fully Automated Image Keyword Extraction (Special Section on Machine Vision Applications) , 1993 .

[9]  Masafumi Hagiwara,et al.  Generalized Fuzzy Inference Neural Network using Self-Organizing Feature Map , 1997 .

[10]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[11]  Thomas M. Strat,et al.  Context-Based Vision: Recognizing Objects Using Information from Both 2D and 3D Imagery , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Minoru Asada,et al.  Scene Interpretation Using 3-D Information Extracted From Monocular Color Images , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Hiroshi Nagahashi,et al.  Boundary Detection of Color Images Using Neural Networks. , 1997 .

[14]  Masafumi Hagiwara,et al.  Fuzzy inference neural network , 1997, Neurocomputing.

[15]  Masafumi Hagiwara,et al.  Knowledge extraction from scenery images and the recognition using fuzzy inference neural networks , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[16]  Ichiro Yuyama,et al.  Image segmentation by region integration using initial dependence of the K-means algorithm , 1998 .

[17]  Masafumi Hagiwara,et al.  An image retrieval system by impression words and specific object names - IRIS , 2002, Neurocomputing.

[18]  Shokri Z. Selim,et al.  K-Means-Type Algorithms: A Generalized Convergence Theorem and Characterization of Local Optimality , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Edward J. Delp,et al.  Segmentation of textured images using a multiresolution Gaussian autoregressive model , 1999, IEEE Trans. Image Process..

[20]  Majid Mirmehdi,et al.  Feedback control strategies for object recognition , 1999, IEEE Trans. Image Process..

[21]  Sankar K. Pal,et al.  Self-organization for object extraction using a multilayer neural network and fuzziness measures , 1993, IEEE Trans. Fuzzy Syst..

[22]  Masayuki Mukunoki,et al.  Retrieval of Images Using Pixel-based Objects Models , 1994, IPMU.

[23]  Bir Bhanu,et al.  Closed-Loop Object Recognition Using Reinforcement Learning , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Tomio Echigo,et al.  Unsupervised segmentation of colored texture images by using multiple GMRF models and a hypothesis of merging primitives , 2000, Systems and Computers in Japan.