This paper presents a tumor detection system for fully digital mammography. The processing scheme adopted in the proposed system focuses on the solution of two problems. One is how to detect tumors as suspicious regions with a very weak contrast to their background and another is how to extract features which characterize malignant tumors. For the first problem, a unique adaptive filter called the iris filter is proposed. It is very effective in enhancing approximately rounded opacities no matter what their contrasts might be. Clues for differentiation between malignant tumors and other tumors are believed to be mostly in their border areas. This paper proposes typical parameters which reflect boundary characteristics. To confirm the system performance for unknown samples, large scale experiments using 1212 CR images were performed. The results showed that the sensitivity of the proposed system was 90.5% and the average number of false positives per image was found to be only 1.3. These results show the effectiveness of the proposed system.

No abstract

No abstract

Auto exposure (AE) is an important function ofvideo cameras to adjust the image luminance. I n this paper, an exposure control system of the A E using color information is discussed. Curren,t A E systems detect special image conditions such as backlighting and excessive frontlighting in which the luminance of a main object deteriorates, and compensate the exposure in order to obtain the appropriate luminance of the main object.The compensation of backlighting / excessive frontlighting as characterized by adjusting luminance of the main object where it is appropriate, causing the background to become worse. However, in A E systems th)at h,ave been proposed so far, the compensation amounts are determined according to the degree of backlighting and excessive frontlighting, regardless of importance of the background. The exposure control system proposed an this paper uses "hue" and "chroma" of pixels to derive the importance of the background, and determines a compensation amount by fuzzy reasoning. Simulations of A E are carried out in conventionad systems and the proposed one. The performance of each system is tested through assessment experiments of human subjects for image samples of simulation results, and the proposed system is shown to be eficient for AE.

No abstract