Nonimaging Optical Design with Supporting Quadric Method and Deep Neural Network

被引：0
作者：
Zhang H. [1 ]
Ma P. [1 ]
Chen J. [1 ]
Hu Y. [1 ]
Shou H. [1 ]
机构：
[1] Department of Physics, Science College, Zhejiang University of Technology, Hangzhou
来源：
Recent Patents on Engineering | 2022年 / 16卷 / 06期
基金：
中国国家自然科学基金;
关键词：
deep neural networks; free-form surface; freeform optical design; Nonimaging optics; optical typography; supporting quadric method;
D O I：
10.2174/1872212115666211007102718
中图分类号：
学科分类号：
摘要：
Background: The supporting quadric method (SQM) is a versatile method for designing freeform optics for desired irradiance redistribution, but the time of solution optimization increases rapidly with the refinement of the mapping grid. Objective: As the complexity of light distribution is getting higher and higher, time consumed will also increase exponentially. This paper proposes an idea of applying the deep neural network method to optical design. Methods: In this article, we established a special corresponding relationship and prepared a dataset, which underwent deep network learning and training. Finally, a hybrid design method of deep learning and optical design was realized and verified. Results: Compared with the traditional method, this method is more efficient. Here, we used a deep neural network(DNN) to accelerate the freeform optical design. After the DNN was trained by a sample set consisting of a uniform pattern and eight different Chinese characters represented by an array with 11 × 11, it can generate a character's reflector within few milliseconds. Conclusion: As proof of this new method, a character pattern reflector was manufactured and test-ed, and the experimental irradiance distribution was found close to the expectation, which means that the neural network has the excellent capability to memorize all of the learned characters. SQM combined with DNN has the potential to establish a particular “optical font library” and even offers a promising path for rapid freeform optical design to realize the function of “optical typography”. © 2022 Bentham Science Publishers.
引用
收藏
相关论文
共 20 条
[1]  
Xu M., Hua H., Xu M., Hua H., High dynamic range head mounted display based on dual-layer spatial modulation, Opt. Ex-press, 25, 19, pp. 23320-23333, (2017)
[2]  
Chen F., Wang K., Qin Z., Wu D., Luo X., Liu S., Design method of high-efficient LED headlamp lens, Opt. Express, 18, 20, pp. 20926-20938, (2010)
[3]  
Wu R., Feng Z., Zheng Z., Liang R., Benitez P., Minano J.C., Duerr F., Design of freeform illumination optics, Laser Photonics Rev, 12, (2018)
[4]  
Oliker V., Controlling light with freeform multifocal lens de-signed with supporting quadric method(SQM), Opt. Express, 25, 4, pp. A58-A72, (2017)
[5]  
Ma Y., Zhang H., Su Z., He Y., Xu L., Liu X., Li H., Hybrid method of free-form lens design for arbitrary illumination target, Appl. Opt, 54, 14, pp. 4503-4508, (2015)
[6]  
LeCun Y., Bengio Y., Hinton G., Deep learning, nature, 521, 7553, pp. 436-444, (2015)
[7]  
Liu W., Wang Z., Liu X., Zeng N., Liu Y., Alsaadi F.E., A survey of deep neural network architectures and their applications, Neurocomputing, 234, pp. 11-26, (2017)
[8]  
Cote G., Lalonde J.F., Thibault S., Toward Training a Deep Neural Network to Optimize Lens Designs, Frontiers in Optics / Laser Science, (2018)
[9]  
Hegde R.S., Accelerating optics design optimizations with deep learning, Opt. Eng, 58, (2019)
[10]  
Esteva A., Kuprel B., Novoa R.A., Ko J., Swetter S.M., Blau H.M., Thrun S., Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 7639, pp. 115-118, (2017)
12