Krufka Stephen E, Barner Kenneth E, Aysal Tuncer Can
Electrical and Computer Engineering Department, University of Delaware, Newark, DE 19702, USA.
IEEE Trans Neural Syst Rehabil Eng. 2007 Jun;15(2):310-21. doi: 10.1109/TNSRE.2007.897029.
Methods to automatically convert graphics into raised-line images have been recently investigated. In this paper, concepts from previous research are extended to the vector graphics case, producing tactile pictures in which important features are emphasized. The proposed algorithm extracts object boundaries and employs a classification process, based on a graphic's hierarchical structure, to determine critical outlines. A single parameter is introduced into the classification process, enabling users to tailor graphics to their own preferences. The resulting outlines are printed using a Braille printer to produce tactile output. Critical outlines are embossed with raised dots of highest height while other lines and details are embossed with a lower height. Psychophysical experiments including discrimination, identification, and comprehension are utilized to evaluate and compare the proposed algorithm. Results indicate that the proposed method outperforms other methods in all three considered tasks. The results also show that emphasizing important features significantly increases comprehension of tactile graphics, validating the proposed method's effectiveness in conveying visual information.
最近人们对将图形自动转换为凸起线条图像的方法进行了研究。在本文中,先前研究中的概念被扩展到矢量图形的情况,生成了强调重要特征的触觉图片。所提出的算法提取对象边界,并基于图形的层次结构采用分类过程来确定关键轮廓。在分类过程中引入了一个单一参数,使用户能够根据自己的偏好定制图形。生成的轮廓使用盲文打印机打印以产生触觉输出。关键轮廓用最高高度的凸点压印,而其他线条和细节用较低高度压印。利用包括辨别、识别和理解在内的心理物理学实验来评估和比较所提出的算法。结果表明,所提出的方法在所有三个考虑的任务中都优于其他方法。结果还表明,强调重要特征显著提高了对触觉图形的理解,验证了所提出方法在传达视觉信息方面的有效性。