We propose a new text layout that facilitates reading comprehension. By sequentially fading out characters sentence-by-sentence from the beginning of each paragraph, we highlight the paragraph structure of the entire text and the relative positions of the sentences. To evaluate the effectiveness of the paragraph-based faded text in a reading comprehension, we measure the comprehension, eye movements, and recognition for both the proposed method and a conventional standard method. In the proposed method, rates of correct answers to text comprehension questions are improved. Moreover, the proposed method leads to slower reading speeds and better recognition rates for the first sentences of paragraphs, which are displayed in a relatively thicker mode. With the paragraph-based faded text, the reader is naturally facilitated to pay attention to the first sentence of each paragraph, suggesting that this reading style could result in a more accurate text comprehension.

We propose a new electronic text format with a stepped-line layout to optimize viewing position and to improve the efficiency of reading Japanese text. Generally, the reader's eyes try to fixate on every phrase while reading Japanese text. To date, no method has been proposed to optimize the fixation position while reading. In case of spaced text such as English, the space characters provide the boundary information for eye movement, however, in case of Japanese text, reading speed decreases by inserting spaces between phrases. With the new stepped-line text format proposed in this report, a text line is segmented and stepped down between phrases, moreover, line breaks are present between phrases. To evaluate the effect of the stepped-line layout on the reading efficiency, we measured reading speeds and eye movements for both the new layout and a conventional straight-line layout. The reading speed for the new stepped-line layout is approximately 13% faster compared to the straight-line layout, whereas the number of fixations in the stepped-line layout is approximately 11% less than that in the straight-line layout. This is primarily achieved by a reduction in the number of regressions and an increase in the forward saccade length. Moreover, 91% of participants did not experience illegibility or incongruousness with the stepped-line layout reading, suggesting that the stepped-line layout is a new technique for improving the efficiency of eye movements while reading without any increase in cognitive load.

This paper presents a fast appearance-based full-text search method for historical newspaper images. Since historical newspapers differ from recent newspapers in image quality, type fonts and language usages, optical character recognition (OCR) does not provide sufficient quality. Instead of OCR approach, we adopted appearance-based approach, that means we matched character to character with its shapes. Assuming proper character segmentation and proper feature description, full-text search problem is reduced to sequence matching problem of feature vector. To increase computational efficiency, we adopted pseudo-code expression called LSPC, which is a compact sketch of feature vector while retaining a good deal of its information. Experimental result showed that our method can retrieve a query string from a text of over eight million characters within a second. In addition, we predict that more sophisticated algorithm could be designed for LSPC. As an example, we established the Extended Boyer-Moore-Horspool algorithm that can reduce the computational cost further especially when the query string becomes longer.

A new method for text retrieval that does not need segmentation is described. Segmenting the images in historical documents into individual characters is difficult. Therefore, the conventional OCR method, which uses segmentation, does not work well. Our method instead divides the text image into a sequence of small slits. The image region that corresponds to the query image region is retrieved by solving the matching problem of these sequences. Applying the eigenspace method to the slit images enables us to solve the matching problem efficiently. Moreover, using dynamic time warping (DTW) further improves the results. Our method has higher accuracy than the simple template matching method, and it has far higher efficiency in computational cost.

We propose a method to index baseball telecast for content-based video retrieval. In our approach, assumptions specific to baseball telecast are used to index video-recordings. In, the first stage of the system, we detect domain specific scene in a baseball video based-on image similarity. These scene, called basic scene in the paper, are the shots which include a single pitching in each. After extracting these scenes, we spot the exact location of pitching and batting action using continuous dynamic programming matching for fixed areas in the image. If the batter swing the bat, we determine the end point of the play from the camera view after batting to recognize the batting result. We also recognize the caption to verify/confirm the recognition result. We stored summarized version of the telecast with these indexes to form a video-database. To validate the approach, we parsed 53 throws in a baseball game using the system, and the percentages of correct spotting for pitching and batting are 96% and 89%, respectively. The validity of the indexing is examined in the report.

We are developing an intelligent presentation system. This type of system can handle live images of documents and drawings. In the system, documents are input using a computer-controlled camera; it can actively decide zoom parameters and glance directions of the camera in order to capture the whole document image in sufficient resolution. Scanned images are mosaiced into a large image. Then, links between document data and electronic data can be constructed by document analysis. In this research, we describe techniques in order to realize this type of system.

A situation-based selective video recording system for a short term memory aid is proposed. The system selectively records the images of events which happened in one's daily life based on sensor observation of the user situation. The user wears sensors to monitor the environment and the action of the user himself. Selected scenes viewed with a head-mounted camera are recorded with situation information. This paper reports the system overview and some field experiments.

This paper proposes a method of recognising Japanese sign language indirectly using a colored glove which has multiple color patches on its surface. Japanese sign language has finger alphabets and words which include a hand motion. In the proposed method, the finger alphabets are estimated from three parameters: the color combination of the visible patches, the dispersion of the visible patches, and the hand direction. The color combination is represented by the mean of the color histogram of the visible patches in an input image. Words which include a hand motion are estimated from the transition of characteristic hand structures which are detected from an image sequence by changes in the color combination of the visible patches. The experimental results show the validity of the proposed method.

We propose a qualitative analysis of group behaviour based on multi-scale region analysis. In the algorithm, histogram backprojection images of an input image sequence are analyzed with multi-scale filters to extract a hierarchical representation of the group structure in the sequence. The dynamics of the hierarchical description is interpreted from the temporal aspect of qualitative relations among groups. Occlusions are also detected with transition rules. A soccer game image sequence is chosen as an example of the analysis.>

One of the problems in sensor integration is how to design the integration strategy for the given task. The authors deal with model-based object recognition from uncertain geometric observations using uncertain object models. First, they decompose the recognition problem into a hierarchy of statistically well-defined subproblems depending on sensor uncertainties and model uncertainties. A recognition algorithm based on this approach is developed. Second, a method to preserve the consistency under model uncertainties is discussed. It is shown that information loss can be avoided by adding dummy variables to parameters in the integration. Finally, applications of the proposed method to 2D object recognition are demonstrated.>

A laser-beam reflection method was developed to reproduce the sound from old wax phonograph cylinders. Since this optical method is noncontacting and nondestructive, the sound even from repaired wax cylinders can be reproduced. In principle, the method is based on geometrical optics. However, the reflection phenomenon from the grooves of a wax cylinder does not exactly obey the law of geometrical optics because of the finite width of the illuminating beam. Severe problems concerning the properties of the reproduced sounds were found in developing the optical method; they were solved fairly well from quantitative investigations of the reproduced sound. As a result, the laser-beam reflection method is practical and powerful enough to reproduce the sound from all kinds of old wax cylinder.