Yasuko Takahashi

Robust object detection under various environmental conditions

An algorithm for object detection is presented. This method is robust against brightness variation and does not depend on the position, size, background pattern, shape, or color of target objects. The method consists of three processes: (1) normalize the brightness of the target and reference images; (2) calculate features, called the normalized principal component features; and (3) construct a classifier by statistical learning. The method is applied to car detection in a parking lot. Under various conditions, at least 98 percent of the cars were detected correctly. Application to moving-car detection and person detection also is presented.

MVC real-time video encoder for full-HDTV 3D video

3D video technologies such as 3D cameras, displays, and video-processing have become more important for achieving high quality and immersive video services. We propose an H.264 MVC encoder architecture for real-time 3D video distribution and transmission. We also present the first-ever successful development of a full-HDTV real-time MVC encoder.

Automated detection of changes in sequential color ocular fundus images

A recent trend is the automatic screening of color ocular fundus images. The examination of such images is used in the early detection of several adult diseases such as hypertension and diabetes. Since this type of examination is easier than CT, costs less, and has no harmful side effects, it will become a routine medical examination. Normal ocular fundus images are found in more than 90% of all people. To deal with the increasing number of such images, this paper proposes a new approach to process them automatically and accurately. Our approach, based on individual comparison, identifies changes in sequential images: a previously diagnosed normal reference image is compared to a non- diagnosed image.

Log-derivative matching method for pattern comparison

A new pattern comparison method called LDM (log-derivative- matching) based on the calculus of object reflectance is proposed. We introduce a log-derivative operator for the local operator, and correlation for global integration. We show two facts about LDM: (1) Under a few assumptions on illumination change, our log-derivative operator minimizes the influence of illuminaton. (2) The LDM method can be used for pattern comparison. Experimental results and also a mathematical analysis show that the proposed method permits pattern matching even under strong shadow.