Learn More
This paper examines a simultaneous estimation of both high resolution (high accuracy) 3D information and high-resolution image from multiple low-resolution stereo-pair images. The proposed method is based on the MAP (maximum a posteriori) framework and these two relevant problems (estimation of both high-resolution 3 D and intensity images) are incorporated(More)
This paper describes a method for the classification of bank notes. The algorithm has three stages, and classifies bank notes with v ery low error rates and at high speeds. To achiev e the v ery low error rates, the result of classification is check ed in the final stage by using different features to those used in the first two. High-speed processing is(More)
Character recognition in complex real scene images is a very challenging undertaking. The most popular approach is to segment the text area using some extra preknowledge, such as “characters are in a signboard”, etc. This approach makes it possible to construct a very timeconsuming method, but generality is still a problem. In this paper, we propose a more(More)
Automated teller machines obviously require functions for protecting themselves from crimes, because they must handle cash. This paper discusses self-defense-technologies based on image processing and recognition to realize such functions in the machines. The technologies include (i) banknote validation for preventing machines from receiving counterfeit(More)
A system for detecting fundus lesions caused by diabetic retinopathy from fundus images is being developed. The system can screen the images in advance in order to reduce the inspection workload on doctors. One of the difficulties that must be addressed in completing this system is how to remove false positives (which tend to arise nearby blood vessels)(More)
A novel method for auto-calibration of a PTZ (pan-tilt-zoom) camera network is proposed. The key idea on which it is based is to use pan-tilt motions generated by PTZ cameras themselves as calibration patterns. Generating and observing the pan-tilt motions of each camera makes it possible to estimate whole relative camera poses in a camera network. Cameras(More)