TY - JOUR
AU1 - Ito, Seiji
AU2 - Yoshioka, Michifumi
AU3 - Omatu, Sigeru
AU4 - Kita, Kouji
AU5 - Kugo, Kouichi
AB - 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.
TI - An image recognition method by rough classification for a scene image
JF - Artificial Life and Robotics
DO - 10.1007/s10015-005-0353-9
DA - 2005-01-01
UR - https://www.deepdyve.com/lp/springer-journals/an-image-recognition-method-by-rough-classification-for-a-scene-image-CzEyH2fEFr
SP - 120
EP - 125
VL - 10
IS - 2
DP - DeepDyve
ER -