When the image is scanned using a stand type scanner, the lighting position change might cause a distortion of the image. It has been readjusted by reading a standard seat again so far. However, it took time. Moreover, after the manuscript setting, the correction is difficult. In this paper, we propose a method of shading correction of the deterioration for the lighting change. This method consists the lighting environment presumption using six specular ball arranged in surroundings of the manuscript, generation simulation of shadows on the manuscript and dynamic feedback to the shading correction. The effectiveness of the correction processing was shown by the simulation.

View full abstract

The image capturing conditions are not always enough, so the contrast of a captured images is sometimes not good. Therefore, it is popular to improve the contrast of images by contrast improving method. However, the conventional methods do not always generate good contrast images, because the methods do not use spatial features included in an input image. This paper proposes a method for contrast improvement based on differential gray-level features. The method generates a Look-Up-Table from the histogram based on the distributions of differential gray-levels and gradient of differential gray-levels by pixels. The experimental results show that the resultant images with good contrast were generated by the proposed method in comparison with by the conventional methods.

View full abstract

We propose a person identification system using retinal fundus images. The proposed procedure for identification is based on comparison of an input fundus image with reference fundus images in the database.This method is based on the measure of similarity defined as the cross-correlation coefficient calculated from the pixel values.Five-hundred-eighty fundus images including eighty-eight same-person's image pairs were used for the estimation of the proposed technique. The FRR (false rejection rate) and the FAR (false acceptance rate) were found to be 1.3×10^-4 and 2.0×10^-5, respectively. Thus this technique was useful for the biometrics.

View full abstract

This paper describes a new three-dimensional virtual environment simulator with force feedback. By adding the function of force feedback to Gazebo, a multi-robot simulator, it is expected that the more useful virtual environments have been realized. Experimental results of a robot arm model show that the proposed virtual environment is reasonable for robot simulations.

View full abstract