Eiji Taira

Learn More
Slant correction is an indispensable technique for handwritten word recognition systems. Conventional slant correction techniques estimate the average slant angle of component characters and then correct the slant uniformly. Thus these conventional techniques will perform successfully under the assumption that each word is written with a constant slant.(More)
SUMMARY Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition(More)
Several systems based on bookshelf image analysis have been studied for automating bookshelf inspection in libraries and bookstores. In conventional systems, book boundaries are firstly detected for extracting each individual book by using some popular line detection technique, such as Hough transformation. Their detection accuracies, however, are sometimes(More)
Several systems based on bookshelf image analysis have been studied for automating bookshelf inspection in libraries and bookstores. In conventional systems, book boundaries are firstly detected for extracting individual book by using some popular line detection technique, such as Hough transform. Their detection accuracies, however, are sometimes(More)
In this paper, we propose a novel technique to extract individual book titles from bookshelf images for automating bookshelf inspection in libraries and bookstores. This technique is composed of two steps. In the first step, the component, such as book boundary and spine, and the local slant angle are optimally estimated at each horizontal position of a(More)
  • 1