著者
Kenjiro Sugimoto Sei-ichiro Kamata
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.3, no.1, pp.12-21, 2015 (Released:2015-01-01)
参考文献数
42
被引用文献数
3 25

This paper presents an efficient constant-time algorithm for Gaussian filtering and also Gaussian derivative filtering that provides a high approximate accuracy in a low computational complexity regardless of its filter window size. The proposed algorithm consists of two key techniques: second-order shift properties of the Discrete Cosine/Sine Transforms type-5 and dual-domain error minimization for finding optimal parameters. The former enables us to perform filtering in fewer number of arithmetic operations as compared than some state-of-the-art algorithms without integral images. The latter enables us to find the optimal filter size that provides the most accurate filter kernel approximation. Experiments show that the proposed algorithm clearly outperforms state-of-the-art ones in computational complexity, approximate accuracy, and accuracy stability.
著者
Naoki Wada Mikio Shinya Michio Shiraishi
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.1, no.4, pp.328-332, 2013 (Released:2013-10-01)
参考文献数
3
被引用文献数
14

Interests in food safety have been growing and identification management has been recognized very important to improve qualities and safety of foods. This paper investigates pig face recognition to enable inexpensive marker-less pig identification management systems. Eigenspace methods are known to be effective to human face recognition, and we applied them to pig face recognition. From experimental results, we found that pig eyes are the most effective face part for recognition. We obtained 97.9% recognition rate for 16 categories with 16 samples/category training data, and some potential of the method was suggested.
著者
Takahiro Miura Ken-ichiro Yabu Kenichi Tanaka Kazutaka Ueda Tohru Ifukube
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.5, no.1, pp.8-16, 2017 (Released:2017-01-01)
参考文献数
38
被引用文献数
2

Because of rapid population aging, it is necessary to design interfaces that can decrease cognitive workload. The design implications and evaluation criteria for creating such senior-friendly or disability-friendly interfaces need to be established. One element related to memory function that can be manipulated in an interface is visuospatial working memory. However, there are few reports regarding the relationship between visuospatial working memory volume and age. In this paper, we aim to clarify how visuospatial working memory volume changes across the lifespan. We implemented a gamified application named VisuoSpats, which is based on the visual pattern span test, to measure visuospatial memory. The introduced gamification elements included points, leaderboards, and feedbacks. Three hundred and sixty-nine individuals aged 2 to 92 years old participated in this study. The results indicate that the median number of cells memorized was 7.0 (interquartile range: 5.0-9.0) across all age groups. Moreover, the number of cells memorized tends to increase as age increases until the age range of 21-25 years, and then decreases gradually with increasing age. Based on the comments by teenagers or seniors, the effective gamification elements of VisuoSpats could be competition elements such as points and ranking, or diagnostic factors, respectively.
著者
Junichi Sugita Tokiichiro Takahashi
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.1, no.4, pp.317-327, 2013 (Released:2013-10-01)
参考文献数
22
被引用文献数
1 4

We propose a method for generating pointillistic style images from input image considering the features of Seurat's pointillism. Georges-Pierre Seurat is a pioneer and prime exponent of neo-impressionist. He established a technique called pointillism based on scientific color theory. There are three important features of Seurat's pointillism: optical mixture, complementary color contrast and halo effect. The most important feature is the optical mixture. To implement the optical mixture faithfully, we present a pointillistic halftoning method for color halftoning on random dots by utilizing a spatial data structure of boundary sampling algorithm. In addition, we implement complementary color contrast and halo effect according to actual Seurat's painting steps.
著者
宇城 貴啓 今村 幸祐 橋本 秀雄
出版者
映像情報メディア学会
雑誌
映像情報メディア学会誌 : 映像情報メディア = The journal of the Institute of Image Information and Television Engineers (ISSN:13426907)
巻号頁・発行日
vol.55, no.6, pp.912-916, 2001-06-20
参考文献数
5
被引用文献数
3

画像の領域分割などのクラスタリング問題でしばしば用いられるK平均アルゴリズムは, 簡単な原理に基づき有効な結果を与えることが多いが, 初期値依存性があるため適切な初期値を与えなければ, クラスタリング結果に大きな影響を与えることがある.本論文では, 適切な初期値配置法を検討し, 繰り返し処理を行いながら適応的により良いクラスタを形成するクラスタリングアルゴリズムを提案する.提案法を動領域分割手法に適用した結果, 初期値による影響が少ないロバストなクラスタリング手法であることが確認できた.
著者
Hidehiko Shishido Yoshinari Kameda Yuichi Ohta Itaru Kitahara
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.5, no.3, pp.110-120, 2017 (Released:2017-07-01)
参考文献数
13
被引用文献数
5

This paper introduces a method that uses multiple-view videos to estimate the 3D position of a badminton shuttle that moves quickly and anomalously. When an object moves quickly, it is observed with a motion blur effect. By utilizing the information provided by the shape of the motion blur region, we propose a visual tracking method for objects that have an erratic and drastically changing moving speed. When the speed increases tremendously, we propose another method, which applies the shape-from-silhouette technique, to estimate the 3D position of a moving shuttlecock using unsynchronized multiple-view videos. We confirmed the effectiveness of our proposed technique using video sequences and a CG simulation image set.
著者
Tetsuya Watanabe Hirotsugu Kaga
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.5, no.1, pp.2-7, 2017 (Released:2017-01-01)
参考文献数
22
被引用文献数
3

To determine the optimum size of a braille font, we conducted an experiment in which a popular Japanese braille font was printed at various sizes on capsule paper and read and rated by late blind people. The results show that braille printed at 16 to 19-point sizes was read faster and rated higher than that printed at smaller or larger sizes. These optimum sizes mostly coincide with those found for young congenitally blind people. A new finding was that many reading errors that stemmed from mistaking the range of braille cells were observed at larger sizes, 20 to 22-point sizes. This means that enlarging the font size is not necessarily beneficial for late blind people and optimum sizes should be strictly selected when doing so.
著者
Ali S. Razavian Josephine Sullivan Stefan Carlsson Atsuto Maki
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.4, no.3, pp.251-258, 2016 (Released:2016-07-01)
参考文献数
39
被引用文献数
196

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.
著者
George Awad Cees G. M. Snoek Alan F. Smeaton Georges Quénot
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.4, no.3, pp.187-208, 2016 (Released:2016-07-01)
参考文献数
36
被引用文献数
1 20

Semantic indexing, or assigning semantic tags to video samples, is a key component for content-based access to video documents and collections. The Semantic Indexing task has been run at TRECVid from 2010 to 2015 with the support of NIST and the Quaero project. As with the previous High-Level Feature detection task which ran from 2002 to 2009, the semantic indexing task aims at evaluating methods and systems for detecting visual, auditory or multi-modal concepts in video shots. In addition to the main semantic indexing task, four secondary tasks were proposed namely the “localization” task, the “concept pair” task, the “no annotation” task, and the “progress” task. It attracted over 40 research teams during its running period. The task was conducted using a total of 1,400 hours of video data drawn from Internet Archive videos with Creative Commons licenses gathered by NIST. 200 hours of new test data was made available each year plus 200 more as development data in 2010. The number of target concepts to be detected started from 130 in 2010 and was extended to 346 in 2011. Both the increase in the volume of video data and in the number of target concepts favored the development of generic and scalable methods. Over 8 millions shots×concepts direct annotations plus over 20 millions indirect ones were produced by the participants and the Quaero project on a total of 800 hours of development data. Significant progress was accomplished during the period as this was accurately measured in the context of the progress task but also from some of the participants' contrast experiments. This paper describes the data, protocol and metrics used for the main and the secondary tasks, the results obtained and the main approaches used by participants.
著者
Shingo Nagasaka Yuki Uranishi Shunsuke Yoshimoto Masataka Imura Osamu Oshiro
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.3, no.4, pp.279-286, 2015 (Released:2015-10-01)
参考文献数
12
被引用文献数
3

This paper proposes a system that provides the sensation of touching virtual objects in a mobile touch panel using a retractable stylus and the mobile touch panel. The proposed system provides a sensation like the stylus is being inserted into the monitor, and that the user is actually touching the object in the screen when the user pushes a retractable stylus downward on the display. A DC motor is mounted in the retractable stylus, and this motor shrinks the length of the stylus based on feedback from a pressure sensor in the tip of the stylus. When the tip of the virtual stylus touches a virtual object, a voice coil motor in the stylus oscillates according to the surface of the virtual object. So the user experiences a sensation like touching the object on the monitor by using the proposed system.