The Experts below are selected from a list of 97944 Experts worldwide ranked by ideXlab platform
Mohamed Zaki Ramadan - One of the best experts on this subject based on the ideXlab platform.
-
evaluating college students performance of arabic typeface Style Font size page layout and foreground background color combinations of e book materials
Journal of King Saud University: Engineering Sciences, 2011Co-Authors: Mohamed Zaki RamadanAbstract:Abstract The present study was conducted to explore students’ preference of Arabic typeface Style, Font size, page layout, and foreground/background color combinations of written materials. Legibility and readability guidelines described in the literature are written for Western readers; make it difficult for e-book providers to know exactly what recommendations to follow in Arabic. First, the participants completed the Font Style selection process from among all the Arabic Font Styles available in Windows. They were then asked to select the typeface Style (Simplified, Traditional, Kofi, and Nassekh) and Font size (10-, 12-, and 14-point) they preferred when reading e-passages. Finally, they read another group of e-passages in the typeface Style and Font size they had selected in one- and two-column formats with four foreground/background color combinations. To assess their reading speed and comprehension as well as their preferences, we asked questions about the information they had read. In Experiment 1, 49 participants preferred 170 Font Styles from a pool of 877 presented in 12-point Font size. In Experiment 2, 31 participants selected 14-pt Arabic simplified as a good readable Font Style for next experiment. In Experiment 3, 31 participants preferred to read Arabic materials in one column with black/white for foreground/background color combination. Participants were able to read the e-materials significantly faster and with better comprehension when they were presented in 14-pt Arabic simplified Font Style in one column with black/white for foreground/background color.
-
Evaluating college students’ performance of Arabic typeface Style, Font size, page layout and foreground/background color combinations of e-book materials
Journal of King Saud University - Engineering Sciences, 2011Co-Authors: Mohamed Zaki RamadanAbstract:The present study was conducted to explore students’ preference of Arabic typeface Style, Font size, page layout, and foreground/background color combinations of written materials. Legibility and readability guidelines described in the literature are written for Western readers; make it difficult for e-book providers to know exactly what recommendations to follow in Arabic. First, the participants completed the Font Style selection process from among all the Arabic Font Styles available in Windows. They were then asked to select the typeface Style (Simplified, Traditional, Kofi, and Nassekh) and Font size (10-, 12-, and 14-point) they preferred when reading e-passages. Finally, they read another group of e-passages in the typeface Style and Font size they had selected in one- and two-column formats with four foreground/background color combinations. To assess their reading speed and comprehension as well as their preferences, we asked questions about the information they had read. In Experiment 1, 49 participants preferred 170 Font Styles from a pool of 877 presented in 12-point Font size. In Experiment 2, 31 participants selected 14-pt Arabic simplified as a good readable Font Style for next experiment. In Experiment 3, 31 participants preferred to read Arabic materials in one column with black/white for foreground/background color combination. Participants were able to read the e-materials significantly faster and with better comprehension when they were presented in 14-pt Arabic simplified Font Style in one column with black/white for foreground/background color.
Ji Xiang - One of the best experts on this subject based on the ideXlab platform.
-
scs Style and content supervision network for character recognition with unseen Font Style
International Conference on Neural Information Processing, 2019Co-Authors: Wei Tang, Yiwen Jiang, Neng Gao, Ji XiangAbstract:There is a significant Style overfitting problem in traditional content supervision models of character recognition: insufficient generalization ability to recognize the characters with unseen Font Styles. To overcome this problem, in this paper we propose a novel framework named Style and Content Supervision (SCS) network, which integrates Style and content supervision to resist Style overfitting. Different from traditional models only supervised by content labels, SCS simultaneously leverages the Style and content supervision to separate the task-specific features of Style and content, and then mixes the Style-specific and content-specific features using bilinear model to capture the hidden correlation between them. Experimental results prove that the proposed model is able to achieve the state-of-the-art performance on several widely used real world character sets, and it obtains relatively strong robustness when the size of training set is shrinking.
-
ICONIP (5) - SCS: Style and Content Supervision Network for Character Recognition with Unseen Font Style
Communications in Computer and Information Science, 2019Co-Authors: Wei Tang, Yiwen Jiang, Neng Gao, Ji XiangAbstract:There is a significant Style overfitting problem in traditional content supervision models of character recognition: insufficient generalization ability to recognize the characters with unseen Font Styles. To overcome this problem, in this paper we propose a novel framework named Style and Content Supervision (SCS) network, which integrates Style and content supervision to resist Style overfitting. Different from traditional models only supervised by content labels, SCS simultaneously leverages the Style and content supervision to separate the task-specific features of Style and content, and then mixes the Style-specific and content-specific features using bilinear model to capture the hidden correlation between them. Experimental results prove that the proposed model is able to achieve the state-of-the-art performance on several widely used real world character sets, and it obtains relatively strong robustness when the size of training set is shrinking.
Keiji Yanai - One of the best experts on this subject based on the ideXlab platform.
-
Font Style transfer using neural Style transfer and unsupervised cross domain transfer
Asian Conference on Computer Vision, 2018Co-Authors: Atsushi Narusawa, Wataru Shimoda, Keiji YanaiAbstract:In this paper, we study about Font generation and conversion. The previous methods dealt with characters as ones made of strokes. On the contrary, we extract features, which are equivalent to the strokes, from Font images and texture or pattern images using deep learning, and transform the design pattern of Font images. We expect that generation of original Font such as hand written characters will be generated automatically by the proposed approach. In the experiments, we have created unique datasets such as a ketchup character image dataset and improve image generation quality and readability of character by combining neural Style transfer with unsupervised cross-domain learning.
-
neural Font Style transfer
International Conference on Document Analysis and Recognition, 2017Co-Authors: Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai, Seiichi UchidaAbstract:In this paper, we chose an approach to generate Fonts by using neural Style transfer. Neural Style transfer uses Convolution Neural Networks(CNN) to transfer the Style of one image to another. By modifying neural Style transfer, we can achieve neural Font Style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as Style images. Finally, we provide insight into the characteristics of Style transfer with Fonts.
Atsushi Narusawa - One of the best experts on this subject based on the ideXlab platform.
-
Font Style transfer using neural Style transfer and unsupervised cross domain transfer
Asian Conference on Computer Vision, 2018Co-Authors: Atsushi Narusawa, Wataru Shimoda, Keiji YanaiAbstract:In this paper, we study about Font generation and conversion. The previous methods dealt with characters as ones made of strokes. On the contrary, we extract features, which are equivalent to the strokes, from Font images and texture or pattern images using deep learning, and transform the design pattern of Font images. We expect that generation of original Font such as hand written characters will be generated automatically by the proposed approach. In the experiments, we have created unique datasets such as a ketchup character image dataset and improve image generation quality and readability of character by combining neural Style transfer with unsupervised cross-domain learning.
-
neural Font Style transfer
International Conference on Document Analysis and Recognition, 2017Co-Authors: Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai, Seiichi UchidaAbstract:In this paper, we chose an approach to generate Fonts by using neural Style transfer. Neural Style transfer uses Convolution Neural Networks(CNN) to transfer the Style of one image to another. By modifying neural Style transfer, we can achieve neural Font Style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as Style images. Finally, we provide insight into the characteristics of Style transfer with Fonts.
Wei Tang - One of the best experts on this subject based on the ideXlab platform.
-
scs Style and content supervision network for character recognition with unseen Font Style
International Conference on Neural Information Processing, 2019Co-Authors: Wei Tang, Yiwen Jiang, Neng Gao, Ji XiangAbstract:There is a significant Style overfitting problem in traditional content supervision models of character recognition: insufficient generalization ability to recognize the characters with unseen Font Styles. To overcome this problem, in this paper we propose a novel framework named Style and Content Supervision (SCS) network, which integrates Style and content supervision to resist Style overfitting. Different from traditional models only supervised by content labels, SCS simultaneously leverages the Style and content supervision to separate the task-specific features of Style and content, and then mixes the Style-specific and content-specific features using bilinear model to capture the hidden correlation between them. Experimental results prove that the proposed model is able to achieve the state-of-the-art performance on several widely used real world character sets, and it obtains relatively strong robustness when the size of training set is shrinking.
-
ICONIP (5) - SCS: Style and Content Supervision Network for Character Recognition with Unseen Font Style
Communications in Computer and Information Science, 2019Co-Authors: Wei Tang, Yiwen Jiang, Neng Gao, Ji XiangAbstract:There is a significant Style overfitting problem in traditional content supervision models of character recognition: insufficient generalization ability to recognize the characters with unseen Font Styles. To overcome this problem, in this paper we propose a novel framework named Style and Content Supervision (SCS) network, which integrates Style and content supervision to resist Style overfitting. Different from traditional models only supervised by content labels, SCS simultaneously leverages the Style and content supervision to separate the task-specific features of Style and content, and then mixes the Style-specific and content-specific features using bilinear model to capture the hidden correlation between them. Experimental results prove that the proposed model is able to achieve the state-of-the-art performance on several widely used real world character sets, and it obtains relatively strong robustness when the size of training set is shrinking.