scispace - formally typeset
Search or ask a question

Showing papers on "Multimedia database published in 2017"


Patent
08 Jun 2017
TL;DR: In this paper, a multimedia photograph generating method is proposed, which consists of acquiring location information of a location where a photographing device is, and acquiring a photograph of a photographed object of the photographing devices, and then, after receiving an instruction of removing a background of the photograph, extracting a character image from the photograph as a foreground picture, searching out a picture and music that are matched with the location information from a multimedia database as a background picture and background music of the photographed photograph, and finally, mixing the foreground picture.
Abstract: The present invention provides a multimedia photograph generating method, apparatus and device, and a mobile phone. The multimedia photograph generating method comprises: firstly, acquiring location information of a location where a photographing device is, and acquiring a photograph of a photographed object of the photographing device; then, after receiving an instruction of removing a background of the photograph, extracting a character image from the photograph as a foreground picture, and according to the location information, searching out a picture and music that are matched with the location information from a multimedia database as a background picture and background music of the photograph; and finally, mixing the foreground picture, the background picture and the background music into a multimedia photograph. When a user is unsatisfied with the background effect of the photographed photograph, the character image can be automatically extracted from the photograph and the original background with a poor effect is removed, and the picture that is matched with the location information of the photographing location is searched out from the multimedia database, so that the optimization processing is simple and a user experience degree is high.

17 citations


Book ChapterDOI
11 Sep 2017
TL;DR: This paper introduces a database, which contains RGB images of meals together with the corresponding depth maps, 3D models, segmentation and recognition maps, weights and volumes, and presents a number of experiments on the new database.
Abstract: A healthy diet is crucial for maintaining overall health and for controlling food-related chronic diseases, like diabetes and obesity. Proper diet management however, relies on the rather challenging task of food intake assessment and monitoring. To facilitate this procedure, several systems have been recently proposed for automatic meal assessment on mobile devices using computer vision methods. The development and validation of these systems requires large amounts of data and although some public datasets already exist, they don’t cover the entire spectrum of inputs and/or uses. In this paper, we introduce a database, which contains RGB images of meals together with the corresponding depth maps, 3D models, segmentation and recognition maps, weights and volumes. We also present a number of experiments on the new database to provide baselines performances in the context of food segmentation, depth and volume estimation.

17 citations


Patent
08 Mar 2017
TL;DR: In this article, a sparse self-encoding neural network is used to generate a multimedia data operation behavior matrix according to operation behaviors of a history user group for more data in a preset multimedia database.
Abstract: Embodiments of the invention disclose a multimedia data processing method and device. The method comprises the following steps of generating a multimedia data operation behavior matrix according to operation behaviors of a history user group for more data in a preset multimedia database; computing concealed feature vectors respectively corresponding to the multimedia data and user feature vectors respectively corresponding to history users based on a sparse self-encoding neural network according to the multimedia data operation behavior matrix; and when a recommendation request corresponding to a target user is received and the history user group includes the target user, obtaining a plurality of multimedia data in personal operation behavior information of the target user and carrying out recommendation processing on the multimedia data in the personal operation behavior information according to the user feature vector corresponding to the target user and the concealed feature vectors respectively corresponding to the multimedia data in the personal operation behavior information. Through adoption of the method and the device, the recommended song can be guaranteed to be liked by the user, so that the recommendation effect is improved.

10 citations


Book ChapterDOI
05 Nov 2017
TL;DR: A formal framework based on position-color feature signatures is presented, enabling comprehensive simulations of users drawing a color sketch, and identifies potential bottlenecks of a flexible color-sketch retrieval model.
Abstract: In order to evaluate the effectiveness of a color-sketch retrieval system for a given multimedia database, tedious evaluations involving real users are required as users are in the center of query sketch formulation. However, without any prior knowledge about the bottlenecks of the underlying sketch-based retrieval model, the evaluations may focus on wrong settings and thus miss the desired effect. Furthermore, users have usually no clues or recommendations to draw color-sketches effectively. In this paper, we aim at a preliminary analysis to identify potential bottlenecks of a flexible color-sketch retrieval model. We present a formal framework based on position-color feature signatures, enabling comprehensive simulations of users drawing a color sketch.

6 citations


Patent
04 Jul 2017
TL;DR: In this paper, the authors present a multimedia file storage and viewing method, where the multimedia file is stored in the multimedia database with the access right, and thus the file cannot be randomly viewed.
Abstract: The embodiment of the application provides a multimedia file storage and viewing method, device and a mobile terminal. The method comprises the following steps: acquiring a multimedia file; writing the multimedia file to a multimedia database; extracting the feature information of the multimedia file; determining the access right level according to the feature information of the multimedia file; and configuring the access right level to the multimedia file in the multimedia database. According to the multimedia file storage and viewing method, device and the mobile terminal provided by the embodiment of the invention, the multimedia file is stored in the multimedia database with the access right, and thus the multimedia file cannot be randomly viewed.

5 citations


Patent
04 Jan 2017
TL;DR: In this article, a method for achieving visualized dynamic presentation of text is presented, which comprises the following steps that 1, semantic analysis is conducted on the specified text to generate multiple semantic models; 2, a multimedia database is constructed; 3, optimal matching materials of all the semantic models are found by retrieving the multimedia database, and the optimal matching material corresponding to all the Semantic models are integrated into a multimedia material set corresponding to the specified texts; 4, concentrated presentation is conducted.
Abstract: The invention discloses a method for achieving visualized dynamic presentation of text. The method comprises the following steps that 1, semantic analysis is conducted on the specified text to generate multiple semantic models; 2, a multimedia database is constructed; 3, optimal matching materials of all the semantic models are found by retrieving the multimedia database, and the optimal matching materials corresponding to all the semantic models are integrated into a multimedia material set corresponding to the specified text; 4, concentrated presentation is conducted on the multimedia material set. According to the method, the baldness of text description is effectively improved, the text is presented in a richer form, and the reasonable logic and a wide application prospect are achieved.

4 citations


DOI
25 Sep 2017
TL;DR: The proposed method uses a run-length histogram to record the position information of pixels, thereby efficiently improves the recognition rate and makes the technique suitable for a big-data multimedia database.
Abstract: Human faces can convey substantial information about a person, such as his or her age, race, identity, gender, and emotions. Such facial information can be obtained through techniques like human facial tracking and detection, facial recognition, gender classification, emotion recognition, as well as age estimation. Of these, gender classification is particularly important due to its diverse applications in the fields such as video surveillance and commercial advertising. In this thesis, we propose a method of gender classification based on run-length histograms. The proposed method uses a run-length histogram to record the position information of pixels, thereby efficiently improves the recognition rate and makes the technique suitable for a big-data multimedia database. The experimental results show that the proposed method can achieve better accuracy than a multi-scale based method can.

2 citations


Patent
31 May 2017
TL;DR: In this paper, the authors proposed a multimedia file output method for the technical field of internet which comprises the steps of obtaining a geographical position of a terminal, obtaining a multimedia files corresponding to the geographical position from a multimedia database, and outputting the multimedia file.
Abstract: The invention is suitable for the technical field of internet and provides a multimedia file output method and device The method comprises the steps of obtaining a geographical position of a terminal, obtaining a multimedia file corresponding to the geographical position from a multimedia database according to the geographical position and outputting the multimedia file The multimedia file output method disclosed in the embodiment of the invention can improve accuracy of multimedia file output, improves utilization rate of network resources and improves user experience at the same time

2 citations



Patent
08 Aug 2017
TL;DR: In this paper, the authors present a file processing method and device as well as an intelligent terminal for the automatic scanning of multimedia data, which comprises steps as follows: when multimedia files in a multimedia database are scanned, current scanning information of the multimedia database is acquired; recorded historical scanning information is acquired, and storage change information is obtained according to the determined current scan information and the historical scan information.
Abstract: An embodiment of the inventiondiscloses a file processing method and device as well as an intelligent terminal. The method comprises steps as follows: when multimedia files in a multimedia database are scanned, current scanning information of the multimedia database is acquired; recorded historical scanning informationof the multimedia database is acquired, and storage change information is obtained according to the determined current scanning information and the historical scanning information; if the storage change information does not meet a preset scanning condition, historical data volume of eachmultimedia file in the multimedia database is acquired, and a scanning result for the multimedia database is determined according to the historical data volumes. With theadoption of the embodiment, scanning management for the multimedia data can be completed better, the scanning time is saved, required software and hardware resources are scanned, and the scanning efficiency is improved.

1 citations


Patent
19 Oct 2017
TL;DR: In this paper, a multimedia file recommending device capable of matching entertainment file to user mood or state includes an input device to receive emotional value X sensed from or inputted by a user, a storage device, and a processor.
Abstract: A multimedia file recommending device capable of matching entertainment file to user mood or state includes an input device to receive emotional value X sensed from or inputted by a user, a storage device, and a processor. The storage device stores multimedia files each associated with an emotional value. The processor selects a multimedia file from the multimedia database according to default rules, wherein a difference between the emotional value associated with the selected multimedia files and the emotional value X falling within a preset range. A multimedia file recommending method is also provided.

Proceedings ArticleDOI
Arif Ghafoor1
30 Aug 2017
TL;DR: This tutorial presents the current-state-of-the art in multimedia database management systems and discusses various issues related to semantic modeling and indexing of multimedia information.
Abstract: In this tutorial we present the current-state-of-the art in multimedia database management systems. We discuss various issues related to semantic modeling and indexing of multimedia information. Various schemes to represent temporal synchronization requirements are explored and the current research challenges facing the multimedia database community are highlighted.