Face Detection and Verification Using Lensless Cameras

Tan, Jasper; Niu, Li; Adams, Jesse K.; Boominathan, Vivek; Robinson, Jacob T.; Baraniuk, Richard G.; Veeraraghavan, Ashok

doi:10.1109/tci.2018.2889933

Cited by 55 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensor captures linear measurements of the scene and the system requires careful calibration and computational algorithm to reconstruct the target scene. The lensless imaging system underlying FlatCam has been used in face detection [29], privacy protection [23] and fluorescence microscopy [1]. Recently, deep learning-based recovery methods have also been introduced for FlatCam in [17].…”

Section: Related Workmentioning

confidence: 99%

“…Lensless cameras have traditionally been developed and used for imaging high-energy radiations such as X-ray and Gamma ray, where fabricating lenses is either extremely expensive or physically unrealizable [8,9,12]. In the last few years, such lensless cameras have been proposed for imaging in visible and infrared wavebands as well; here, the absence of the lens provides advantages in thin form-factor imaging [5,6], better depth-of-field tradeoffs in microscopy [1,2], reduced cost in infrared/multi-spectral imaging [20,24], and provides the ability to do inference from coded measurements [24,29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Simple Framework for 3D Lensless Imaging with Programmable Masks

Zheng¹,

Hua²,

Sankaranarayanan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Lensless cameras provide a framework to build thin imaging systems by replacing the lens in a conventional camera with an amplitude or phase mask near the sensor. Existing methods for lensless imaging can recover the depth and intensity of the scene, but they require solving computationally-expensive inverse problems. Furthermore, existing methods struggle to recover dense scenes with large depth variations. In this paper, we propose a lensless imaging system that captures a small number of measurements using different patterns on a programmable mask. In this context, we make three contributions. First, we present a fast recovery algorithm to recover textures on a fixed number of depth planes in the scene. Second, we consider the mask design problem, for programmable lensless cameras, and provide a design template for optimizing the mask patterns with the goal of improving depth estimation. Third, we use a refinement network as a post-processing step to identify and remove artifacts in the reconstruction. These modifications are evaluated extensively with experimental results on a lensless camera prototype to showcase the performance benefits of the optimized masks and recovery algorithms over the state of the art.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Simple Framework for 3D Lensless Imaging with Programmable Masks

Zheng¹,

Hua²,

Sankaranarayanan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This paper revisits the original type of lensless camera, the pinhole, as the more ideal candidate for lensless photography. As shown in Table 1, while the amplitude and phase mask systems are equally low-cost, compact, and have great advantages in light throughput compared to the lensless pinhole camera, they require more precise calibration and reconstruction, and commonly produce lower perceived image quality, making them more suitable for machine vision or scientific imaging applications [57], instead of everyday photography.…”

Section: Backbone Pipelinementioning

confidence: 99%

Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography

Rego,

Chen,

et al. 2021

Preprint

View full text Add to dashboard Cite

The proposed Deep Camera Obscura (DCO) pipeline is a jointly optimized denoise + deblur pipeline that restores degraded lensless pinhole camera images suitable for perceptual viewing. Our pipeline is trained on synthetic data and utilizes domain knowledge of the optical point spread function to help improve image restoration for pinhole cameras. The resulting DCO pipeline can operate on 20 MP images with 1/30s exposure time.

show abstract

“…There has been subsequent work in extending FlatCam in terms of exploring applications in face-detection [9], privacy protection [10], and fluorescent microscopy [4]. More recent work has focused on mitigating inadequacies of the calibration and reconstruction procedure by including a deep neural network in the reconstruction pipeline [11].…”

Section: Lensless Imaging With Static Masksmentioning

confidence: 99%

SweepCam — Depth-Aware Lensless Imaging Using Programmable Masks

Hua¹,

Nakamura²,

Asif³

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Lensless cameras, while extremely useful for imaging in constrained scenarios, struggle with resolving scenes with large depth variations. To resolve this, we propose imaging with a set of mask patterns displayed on a programmable mask, and introduce a computational focusing operator that helps to resolve the depth of scene points. As a result, the proposed imager can resolve dense scenes with large depth variations, allowing for more practical applications of lensless cameras. We also present a fast reconstruction algorithm for scene at multiple depths that reduces reconstruction time by two orders of magnitude. Finally, we build a prototype to show the proposed method improves both image quality and depth resolution of lensless cameras.

show abstract

Face Detection and Verification Using Lensless Cameras

Cited by 55 publications

References 54 publications

A Simple Framework for 3D Lensless Imaging with Programmable Masks

A Simple Framework for 3D Lensless Imaging with Programmable Masks

Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography

SweepCam — Depth-Aware Lensless Imaging Using Programmable Masks

Contact Info

Product

Resources

About