We aim to realize a new and simple compensation method that robustly handles multiple-projector systems without recourse to the linearization of projector response functions. We introduce state equations, which distribute arbitrary brightness among the individual projectors, and control the state equations according to the feedback from a camera. By employing the color-mixing matrix with gradient of projector responses, we compensate the controlled brightness input to each projector. Our method dispenses with cooperation among multiple projectors as well as time-consuming photometric calibration. Compared with existing methods, our method is shown to offer superior compensation performance and a more effective way of compensating multiple-projector systems.

This paper presents an error-tolerant video retrieval method based on the shot composition sequence in a scene. Conventional video players in the home can not access interesting scenes directly because they offer only play, fast-forward, and rewind. What is needed is an easy-to-use video scene player that can directly access scenes important to the user. This paper presents an error-tolerant video retrieval method that assesses the shot composition sequence in each scene. Our method has three characteristics: (1) easy query generation since the regular interface is used for query generation; (2) similar video scene retrieval based on the sequence of symbols created by shot composition clustering to effectively identify scenes similar to the query; (3) fast similarity measurement based on sequences of symbols. An experiment shows that the proposed system can retrieve video scenes similar to the query quickly as well as allowing semantic retrieval to be constructed in a non-supervised way.

We present videopot, a desktop video search system designed for digital video files stored on personal computers. The core metric of this system is based on video-indexing technology and an automatic related-term collection framework. Digital files on local disks are crawled, and images of representative scenes are extracted from video files using video-indexing technology. Related terms, used as target information in the video search, are collected from both local files and Web pages using an automatic related-term collection algorithm. These images and terms are then stored in the metadata database. We describe a unique search result interface that helps users distinguish the target video. In the search results interface, the results of the video search are listed at two levels to let users search videos faster. The effectiveness of images on our interface derived from video-indexing is evaluated through a comparison with a conventional file search application

In this paper, we describe music monitoring in TV broadcasting based on content-based retrieval. A part of audio signals is sequentially extracted from TV broadcasting as a retrieval key, and a music DB that stores a great number of musical pieces is retrieved by this key based on content-based retrieval, and a musical piece is identified sequentially. In this way, we are able to carry out music monitoring. There are three necessary requirements important for realization of the music monitoring. They are robustness against non-stationary noise, real-time processing of large-scale music DB retrieval, and high granularity of the retrieval key. As a method of realizing robustness against non-stationary noise, we propose a partially similar retrieval method which improves retrieval accuracy by using the moment in which no superfluous noise is produced during the existence of non-stationary noise. In order to realize real-time processing of large-scale music DB retrieval, we adopt a coarse-to-fine strategy, and propose a spectral peaks hashing method which performs high-speed refining by using hashing. To calculate a hash value in this hashing, frequency channel numbers of the spectral peaks are used. In order to realize high granularity of the retrieval key, it is necessary to solve the problem of retrieval accuracy degradation associated with heightening the granularity. To improve this accuracy, we propose a detection-by-continuity method which uses music continuity. Moreover, by using music continuity to correct the starting point and the terminal point of a musical piece in TV broadcasting, the retrieval accuracy is improved further. In order to evaluate the effectiveness of the proposed methods, we performed experiments using a music DB which stores over 28,000 musical pieces (over 1800 hours) and TV broadcasting audio signals containing music and background music (BGM). The granularity of the retrieval key was set at about 0.5 seconds. Through these experiments, We verified that music monitoring was possible for over 90% of the total time of music and BGM used in TV broadcasting, and that real-time processing was possible.

This paper describes our practical query-by-humming system, SoundCompass, which is being used as a karaoke song selection system in Japan. First, we describe the fundamental techniques employed by SoundCompass such as normalization in a time-wise sense of music data, time-scalable and tone-shiftable time-series data, and making subsequences for efficient matching. Second, we describe techniques to make effective feature vectors based on real music data and do matching with them to develop accurate query-by-humming. Third, we share valuable knowledge that has been obtained through month's of practical use of Sound Compass. Fourth, we describe the latest version of the SoundCompass system that incorporates these new techniques and knowledge, as well as describe quantitative evaluations that prove the practicality of SoundCompass. The new system provides flexible and accurate similarity retrieval based on k-nearest neighbor searches with multi-dimensional spatial indices structured with multi-dimensional features vectors.

Proposes a variable filter, a new high-resolution Hough transform method. A voted value at the point ( rho , theta ) on the Hough space is transformed into a value distribution by the variable filter, and voting is performed according to the distribution. The shape and size of the variable filter changes dynamically with the quantization size and the line parameters ( rho , theta ). Statistical experiments show that the filter can improve extraction performance and reduce the mean error of extracted line parameters even with noisy images.>