scholarly journals SynthText3D: synthesizing scene text images from 3D virtual worlds

2020 ◽  
Vol 63 (2) ◽  
Author(s):  
Minghui Liao ◽  
Boyu Song ◽  
Shangbang Long ◽  
Minghang He ◽  
Cong Yao ◽  
...  
Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1919
Author(s):  
Shuhua Liu ◽  
Huixin Xu ◽  
Qi Li ◽  
Fei Zhang ◽  
Kun Hou

With the aim to solve issues of robot object recognition in complex scenes, this paper proposes an object recognition method based on scene text reading. The proposed method simulates human-like behavior and accurately identifies objects with texts through careful reading. First, deep learning models with high accuracy are adopted to detect and recognize text in multi-view. Second, datasets including 102,000 Chinese and English scene text images and their inverse are generated. The F-measure of text detection is improved by 0.4% and the recognition accuracy is improved by 1.26% because the model is trained by these two datasets. Finally, a robot object recognition method is proposed based on the scene text reading. The robot detects and recognizes texts in the image and then stores the recognition results in a text file. When the user gives the robot a fetching instruction, the robot searches for corresponding keywords from the text files and achieves the confidence of multiple objects in the scene image. Then, the object with the maximum confidence is selected as the target. The results show that the robot can accurately distinguish objects with arbitrary shape and category, and it can effectively solve the problem of object recognition in home environments.


2012 ◽  
Vol 2 (2) ◽  
pp. 15 ◽  
Author(s):  
Frederico Menine Schaf ◽  
Suenoni Paladini ◽  
Carlos Eduardo Pereira

<span style="color: #000000;"><span style="font-family: Times New Roman,serif;"><span style="font-size: x-small;">Recent evolutions of social networks, virtual environments, Web technologies and 3D virtual worlds motivate the adoption of new technologies in education, opening successive innovative possibilities. These technologies (or tools) can be employed in distance education scenarios, or can also enhance traditional learning-teaching (blended or hybrid learning scenario). It is known and a wide advocated issue that laboratory practice is essential to technical education, foremost in engineering. In order to develop a feasible implementation to this research area, a prototype was developed, called 3DAutoSysLab, in which a metaverse is used as social collaborative interface, experiments (real or simulated) are linked to virtual objects, learning objects are displayed as interactive medias, and guiding/feedback are supported via an autonomous tutoring system based on user's interaction data mining. This prototype is under test, but preliminary applied results indicate great acceptance and increase of motivation of students.</span></span></span>


Author(s):  
Hugo Paredes ◽  
Fernando Cassola ◽  
Leonel Morgado ◽  
Fausto de Carvalho ◽  
Silvia Ala ◽  
...  

2013 ◽  
Vol 45 (3) ◽  
pp. 1-38 ◽  
Author(s):  
John David N. Dionisio ◽  
William G. Burns III ◽  
Richard Gilbert

2014 ◽  
pp. 474-497
Author(s):  
Demetrios G Sampson ◽  
Pavlos Kallonis

3D Virtual Worlds provide realistic three-dimensional environments accessible through the web that can offer engaging, interactive, and immersive experiences. This can create new opportunities for teaching and learning. Yet, the possible use of 3D Virtual Worlds in formal education is a major challenge for school teachers, even for those who are experienced and keen on using digital technologies. In this chapter, the authors present a 3D Virtual Classroom Simulation appropriately designed and implemented using SLOODLE for supporting a module for teachers' continuing professional development based on the Synectics “making the strange familiar” instructional strategy, aiming towards acquiring appropriate competences for teaching within 3D Virtual Worlds and for developing innovative educational practices.


2015 ◽  
pp. 355-372
Author(s):  
Leman Figen Gül ◽  
Ning Gu ◽  
Mi Jeong Kim ◽  
Xiangyu Wang

With the advancement and increasing adoption of information and communication technologies, 3D virtual worlds, being a part of these revolutionary forces, have the potential to make a major contribution to design education as a new teaching and learning environment. Considering this changing trend, we have been employing 3D virtual worlds in the design curriculum over the past decade. To critically understand the impact of the technologies on design education, this chapter explores and demonstrates three different assessment methods of 3D virtual worlds in design education, through three case studies. The chapter also concludes with insights into the applications of virtual environments in collaborative design teaching.


Author(s):  
Ilaria Mascitti ◽  
Daniela Di Marco ◽  
Monica Fasciani

This chapter reflects on the educational potential of virtual worlds and draws on the results of ST.ART project - Street Artists in a virtual space (www.startproject.eu). ST.ART project innovative aspect embraces both the topic (street art) and the methodology (virtual platforms as e-learning and 3D virtual worlds) as well as the pedagogy applied that uses an inquiry-based method (learning by doing) to support a traditional deductive teaching pedagogy. This approach is not only related to the use of a relatively new technology but also to the educational, pedagogical, cultural, and motivational benefits derived from the chosen methodology. The chapter describes new insights and findings that emerged during the experimentation phase of the project and that were never anticipated when the project was first designed.


Author(s):  
Sean Goggins ◽  
Matthew Schmidt ◽  
Jesus Guajardo ◽  
Joi L. Moore

Teams meet in 3D virtual worlds more frequently than ever before, yet the tools for evaluating 3D collaboration environments are underdeveloped. To close the 3D collaboration tool evaluation gap, the authors integrate lessons from the gaming industry and distributed work research. They develop two complementary approaches. First, the individual user’s perspective using eye-tracking (ET) is addressed, and second, the collaborative experience of the group using a technique called All-Views-Qualitative-Analysis (AVQA) is evaluated. The latter integrates the points-of-view of all subjects in a small group collaborating on a creative work task in a 3 dimensional virtual world. The authors show how these techniques enable evaluation of 3D environment design from the perspective of human computer interaction theory and theories related to distributed work. The paper discusses why designers should seek ways to leverage the advantages of 3D collaboration technologies and avoid recreating mirrors of physical space in these environments.


Sign in / Sign up

Export Citation Format

Share Document