Abstract
Within the framework of Internet of Things or when constrained in limited space, lensless imaging technology provides effective imaging solutions with low cost and reduced size prototypes. In this paper, we proposed a method combining deep learning with lensless coded mask imaging technology. After replacing lenses with the coded mask and using the inverse matrix optimization method to reconstruct the original scene images, we applied FCN-8s, U-Net, and our modified version of U-Net, which is called Dense-U-Net, for post-processing of reconstructed images. The proposed approach showed supreme performance compared to the classical method, where a deep convolutional network leads to critical improvements of the quality of reconstruction.
Highlights
As the manufacture of a lens strongly depends on the complex mechanical structure and polishing, coupled with expensive infrared and ultraviolet lenses, the cost of traditional optical lens systems is difficult to reduce
We used the deep convolutional networks to post-process images captured by the lensless device and reconstructed by the inverse matrix optimization method, and successfully proved the great potential and value of combining the deep learning with the traditional lensless technology
We proposed Dense-U-Net by combining the end-to-end U-Net with the denser link thought contained in DenseNet, which further improved the visual effect and image evaluation parameters of the output image
Summary
As the manufacture of a lens strongly depends on the complex mechanical structure and polishing, coupled with expensive infrared and ultraviolet lenses, the cost of traditional optical lens systems is difficult to reduce. Given the rapid development of the Internet of Things and the increasing importance of image and video data, imaging equipment is required to meet the demands in various applications, such as wearable imaging devices, space-constrained scenes, ultra-thin smartphones, and biological imaging, where thin, lightweight, low energy consumption and affordable cost would be considered as the key qualities of imaging equipment. Current mobile imaging modules are still far from meeting these demands due to the restrictions of the lens. One of the current solutions to deal with the mentioned problems is the adaptation of lensless imaging technology. Lensless imaging technology attempts to replace the physical lens with optical devices such as a spatial light modulator, diffraction optical element, coded mask to achieve the function of light transmission and scene focusing. The coded mask is an ideal solution to simplify manufacturing process, low cost, and easier integration with image sensors
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
