SUMMARYWe previously proposed a query-by-sketch image retrieval system that uses an edge relation histogram (ERH). However, it is difficult for this method to retrieve partial objects from an image, because the ERH is a feature of the entire image, not of each object. Therefore, we propose an object-extraction method that uses edge-based features in order to enable the query-by-sketch system to retrieve partial images. This method is applied to 20,000 images from the Corel Photo Gallery. We confirm that retrieval accuracy is improved by using the edge-based features for extracting objects, enabling the query-by-sketch system to retrieve partial images. key words: query-by-sketch image retrieval, object extraction, partial image retrieval, edge-based feature
The wheel of the railway runs while coming into contact on a rail. Therefore, wear occurs in both. When these wears progress, the vibration is amplified. It leads to various problems such as a ride comfort and a noise. Many researchers examined the contact of a wheel and the rail so far. However, as for the shape of the abrasion to be formed on the surface of a wheel and the rail by progress of the abrasion, it is difficult to observe the abrasion situation to change each moment. It is necessary to investigate the process of shape change on wheel and rail in order to examine the influence of wear progress. In this study, we focused on a Discrete Element Method (DEM) that was effective for the dynamic behavior analysis of the granular material. The rail was expressed by replacing the irregularities of the rail surface to particles. A wheel ran on the particles replaced as a rail. Possibility of DEM was examined by comparing the calculated results with the experimental results of repetitive running. As a result, both showed that the acceleration level of the wheel increase and decrease repeatedly. In addition, it was found that the suggested analytical method of this study might be obtained the results similar to the tendency by the experiment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.