论文信息 - Keywords Specification For Images Using Sandglass-Type Neural Networks

Keywords Specification For Images Using Sandglass-Type Neural Networks

We propose a keyword specification method for images, which can be used to retrieve an image by a keyword. In order to specify a keyword for a sub-region of the image, images are segmented in some regions. Here, we consider ten keywords to specify the regions. The image segmentation method consists of the maximum-distance algorithm, labeling, and merging the small regions. We provide training regions for each keyword. Important features of the keyword are selected using the Factor Analysis (FA). The features are compressed into a two-dimensional space using a Sandglass-type Neural Network (SNN). We train the SNN using the training dataset. Then 60 samples of the testing dataset are evaluated by keywords extraction.

Sigeru Omatu | Seiji Ito

[1] Maneesha Singh,et al. IMAGE RETRIEVAL USING SPATIAL CONTEXT , 2002 .

[2] Masafumi Hagiwara,et al. Scenery image recognition and interpretation using fuzzy inference neural networks , 2002, Pattern Recognit..

[3] Z SelimShokri,et al. K-Means-Type Algorithms , 1984 .

[4] Neill W. Campbell,et al. Interpreting image databases by region classification , 1997, Pattern Recognit..

[5] Yen-Wei Chen,et al. A Spatial Weighted Color Histogram for Image Retrieval , 2004, IEICE Trans. Inf. Syst..

[6] Yen-Wei Chen,et al. Image Retrieval Based on Independent Components of Color Histograms , 2003, KES.

[7] Eiji Watanabe,et al. A compression method for color images using multilayered neural networks , 2003, Systems and Computers in Japan.

[8] Masafumi Hagiwara,et al. Recognition of Scenery Images considering Positional Relation using Fuzzy Inference Neural Networks , 2002 .

[9] Ichiro Yuyama,et al. Image segmentation by region integration using initial dependence of the K-means algorithm , 1998, Systems and Computers in Japan.