Ying Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ying Tang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Masahiro Toyoura
University of Yamanashi, Kofu, Japan
3 shared publications - Xiaoyang Mao
University of Yamanashi
3 shared publications - Issei Fujishiro
Keio University
2 shared publications - Kenji Kashiwagi
Department of Ophthalmology, School of Medicine, University of Yamanashi, Chuo 409-3898, Japan
2 shared publications - Kentaro Go
University of Yamanashi
2 shared publications - Zhenyang Zhu
Department of Computer Science and Engineering, University of Yamanashi, Address, kofu, Yamanashi, 400-8510, Japan
2 shared publications
Latest Publications
- Open Access
- 12 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 190-199
CC-Glasses: Color Communication Support for People with Color Vision Deficiency Using Augmented Reality and Deep Learning
People who suffer from color vision deficiency (CVD) can face difficulties when communicating with others by failing to identify target objects referred by their color names. While most existing studies on CVD compensation have focused on the issue of color contrast loss. Although there are approaches can provide clues of color name to users, these techniques either require training, or cannot protect users’ privacy, i.e., the fact of having CVD. In this paper, based on augmented reality (AR) and deep learning technologies, we propose a novel system to provide supporting information to users affected by CVD for color communication assistance. The state-of-the-art deep neural network (DNN) model for referring segmentation (RS) is adopted to generate supporting information, and AR glasses are utilized for information presentation. To improve the performance of the proposed system further, a new dataset is constructed based on a novel concept called Color–Object Noun Pair. The results of evaluation experiments show that the new dataset can enhance the performance of the adopted DNN model, and the proposed system can help users affected by CVD successfully identify target objects by their color names.
- 12 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 190-199
Open AccessCC-Glasses: Color Communication Support for People with Color Vision Deficiency Using Augmented Reality and Deep Learning
People who suffer from color vision deficiency (CVD) can face difficulties when communicating with others by failing to identify target objects referred by their color names. While most existing studies on CVD compensation have focused on the issue of color contrast loss. Although there are approaches can provide clues of color name to users, these techniques either require training, or cannot protect users’ privacy, i.e., the fact of having CVD. In this paper, based on augmented reality (AR) and deep learning technologies, we propose a novel system to provide supporting information to users affected by CVD for color communication assistance. The state-of-the-art deep neural network (DNN) model for referring segmentation (RS) is adopted to generate supporting information, and AR glasses are utilized for information presentation. To improve the performance of the proposed system further, a new dataset is constructed based on a novel concept called Color–Object Noun Pair. The results of evaluation experiments show that the new dataset can enhance the performance of the adopted DNN model, and the proposed system can help users affected by CVD successfully identify target objects by their color names.
- Open Access
- 31 March 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2381
ALCC-Glasses: Arriving Light Chroma Controllable Optical See-Through Head-Mounted Display System for Color Vision Deficiency Compensation
About 250 million people in the world suffer from color vision deficiency (CVD). Contact lenses and glasses with a color filter are available to partially improve the vision of people with CVD. Tinted glasses uniformly change the colors in a user’s field of view (FoV), which can improve the contrast of certain colors while making others hard to identify. On the other hand, an optical see-through head-mounted display (OST-HMD) provides a new alternative by applying a controllable overlay to a user’s FoV. The method of color calibration for people with CVD, such as the Daltonization process, needs to make the calibrated color darker, which has not yet been featured on recent commercial OST-HMDs. We propose a new approach to realize light subtraction on OST-HMDs using a transmissive LCD panel, a prototype system, named ALCC-glasses, to validate and demonstrate the new arriving light chroma controllable augmented reality technology for CVD compensation.
- 31 March 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2381
Open AccessALCC-Glasses: Arriving Light Chroma Controllable Optical See-Through Head-Mounted Display System for Color Vision Deficiency Compensation
About 250 million people in the world suffer from color vision deficiency (CVD). Contact lenses and glasses with a color filter are available to partially improve the vision of people with CVD. Tinted glasses uniformly change the colors in a user’s field of view (FoV), which can improve the contrast of certain colors while making others hard to identify. On the other hand, an optical see-through head-mounted display (OST-HMD) provides a new alternative by applying a controllable overlay to a user’s FoV. The method of color calibration for people with CVD, such as the Daltonization process, needs to make the calibrated color darker, which has not yet been featured on recent commercial OST-HMDs. We propose a new approach to realize light subtraction on OST-HMDs using a transmissive LCD panel, a prototype system, named ALCC-glasses, to validate and demonstrate the new arriving light chroma controllable augmented reality technology for CVD compensation.
- Open Access
- 28 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 181458-181468
Generating Users’ Desired Face Image Using the Conditional Generative Adversarial Network and Relevance Feedback
In this study, we propose a novel method for generating an image of the target face by using the generative adversarial network (GAN) and relevance feedback. Combining GAN with relevance feedback compensates for the lack of user intervention in GAN and the low image quality in traditional methods. The feature points of face images, namely, the landmarks, are used as the conditional information for GAN to control the detailed features of the generated face image. An optimum-path forest classifier is applied to categorize the relevance of training images based on the user's feedback so that the user can quickly retrieve the training images that are most similar to the target face. The retrieved training images are then used to create a new landmark for synthesizing the target face image. The experimental results showed that users can generate images of their desired faces, including the faces in their memory, with a reasonable number of iterations, therefore demonstrating the potential of applying the proposed method for forensic purposes, such as creating the face images of criminals based on the memories of witnesses or victims.
- 28 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 181458-181468
Open AccessGenerating Users’ Desired Face Image Using the Conditional Generative Adversarial Network and Relevance Feedback
In this study, we propose a novel method for generating an image of the target face by using the generative adversarial network (GAN) and relevance feedback. Combining GAN with relevance feedback compensates for the lack of user intervention in GAN and the low image quality in traditional methods. The feature points of face images, namely, the landmarks, are used as the conditional information for GAN to control the detailed features of the generated face image. An optimum-path forest classifier is applied to categorize the relevance of training images based on the user's feedback so that the user can quickly retrieve the training images that are most similar to the target face. The retrieved training images are then used to create a new landmark for synthesizing the target face image. The experimental results showed that users can generate images of their desired faces, including the faces in their memory, with a reasonable number of iterations, therefore demonstrating the potential of applying the proposed method for forensic purposes, such as creating the face images of criminals based on the memories of witnesses or victims.
- Open Access
- 2 December 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Arriving light control for color vision deficiency compensation using optical see-through head-mounted display
Color vision deficiency (CVD), also known as color blindness, is commonly caused by genetic disorder. Unfortunately, as of 2018, there is not yet a cure for the condition. Contact lenses and glasses with color filter are possible solutions to CVD by applying uniform changes to user's field of view (FoV). On the other hand, optical see-through head-mounted display (OST-HMD) can provide a controllable overlay to user's FoV, which could help for making a better solution. To calibrate colors in FoV of a user with CVD, methods that often used, such as the daltonization process, need light reduce feature, which makes calibrated color darker. However, recent commercially available OST-HMDs don't have a controllable way to decrease the brightness of incoming light. In this paper, we present an approach for light subtraction of OST-HMD using a transmissive LCD panel. A prototype system for achieving a controllable overlay to user's FoV with OST-HMD by using scene camera, user-perspective camera, and the transmissive LCD panel was implemented.
- 2 December 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessArriving light control for color vision deficiency compensation using optical see-through head-mounted display
Color vision deficiency (CVD), also known as color blindness, is commonly caused by genetic disorder. Unfortunately, as of 2018, there is not yet a cure for the condition. Contact lenses and glasses with color filter are possible solutions to CVD by applying uniform changes to user's field of view (FoV). On the other hand, optical see-through head-mounted display (OST-HMD) can provide a controllable overlay to user's FoV, which could help for making a better solution. To calibrate colors in FoV of a user with CVD, methods that often used, such as the daltonization process, need light reduce feature, which makes calibrated color darker. However, recent commercially available OST-HMDs don't have a controllable way to decrease the brightness of incoming light. In this paper, we present an approach for light subtraction of OST-HMD using a transmissive LCD panel. A prototype system for achieving a controllable overlay to user's FoV with OST-HMD by using scene camera, user-perspective camera, and the transmissive LCD panel was implemented.