Conclusions and future work<br><br>We're a "see-too" camera caraced out a transparent window with an image sensor placed ind ed edge of the window. Light rays from a scene is a scene to the head by the rough surface of the window into the acceptance angle of the image sensor, thereby allowing the means method to shad the the . We showed that with judicious choice of the geometric parameters, it isis e e to optimize for the image and angular field of view. Tha there is no lens in our system, there is no s ly s of optical focusing. In the future, it will will will be infor to explore the potential for the re-focusing. This this can bee if can's capture capture sa full light field information. Furthermore, by-applying deep neural networks it is is sitoe to the image sings for the process process application. We recently severed this idea for digit<br>classification using a lens-less camera . . . Similar techniques may be applied to right to high ly power-efficient, and yn techniques for what we call Application-Specific Imaging. ...
正在翻譯中..
