Diffractive blur and low light levels are two fundamental challenges in producing high-quality photographs in under-display cameras (UDCs). In this paper, we incorporate phase masks on display panels to tackle both challenges. Our design inserts two phase masks, specifically two microlens arrays, in front of and behind a display panel. The first phase mask concentrates light on the locations where the display is transparent so that more light passes through the display, and the second phase mask reverts the effect of the first phase mask. We further optimize the folding height of each microlens to improve the quality of PSFs and suppress chromatic aberration. We evaluate our design using a physically-accurate simulator based on Fourier optics. The proposed design is able to double the light throughput while improving the invertibility of the PSFs. Lastly, we discuss the effect of our design on the display quality and show that implementation with polarization-dependent phase masks can leave the display quality uncompromised.

One of the most promising approaches for automated detection of guns and other prohibited items in aviation baggage screening is the use of 3D computed tomography (CT) scans. However, automated detection, especially with deep neural networks, faces two key challenges: the high dimensionality of individual 3D scans, and the lack of labelled training data. We address these challenges using a novel image-based detection and segmentation technique that we call the slice-and-fuse framework. Our approach relies on slicing the input 3D volumes, generating 2D predictions on each slice using 2D Convolutional Neural Networks (CNNs), and fusing them to obtain a 3D prediction. We develop two distinct detectors based on this slice-and-fuse strategy: the Retinal-SliceNet that uses a unified, single network with end-to-end training, and the U-SliceNet that uses a two-stage paradigm, first generating proposals using a voxel labeling network and, subsequently, refining the proposals by a 3D classification network. The networks are trained using a data augmentation approach that creates a very large training dataset by inserting weapons into 3D CT scans of threat-free bags. We demonstrate that the two SliceNets outperform state-of-the-art methods on a large-scale 3D baggage CT dataset for baggage classification, 3D object detection, and 3D semantic segmentation.

Under-panel cameras provide an intriguing way to maximize the display area for a mobile device. An under-panel camera images a scene via the openings in the display panel; hence, a captured photograph is noisy as well as endowed with a large diffractive blur as the display acts as an aperture on the lens. Unfortunately, the pattern of openings commonly found in current LED displays are not conducive to high-quality deblurring. This paper redesigns the layout of openings in the display to engineer a blur kernel that is robustly invertible in the presence of noise. We first provide a basic analysis using Fourier optics that indicates that the nature of the blur is critically affected by the periodicity of the display openings as well as the shape of the opening at each individual display pixel. Armed with this insight, we provide a suite of modifications to the pixel layout that promote the invertibility of the blur kernels. We evaluate the proposed layouts with photomasks placed in front of a cellphone camera, thereby emulating an under-panel camera. A key takeaway is that optimizing the display layout does indeed produce significant improvements.

Frequent pain monitoring in intensive care unit (ICU) settings has been shown to have achieved improvement in patient outcomes. Specifically, the nursing staff is required to assess the pain of the patients approximately every four hours, and make necessary pain medication adjustments. Shortage and overburdening of nursing staff is well acknowledged in many hospital settings worldwide. In this paper, we present a preliminary study on automatic recognition of facial expression of pain in ICU settings. There has been considerable work on computer based pain recognition for settings beyond the ICU, wherein, usually the entire face of the person is visible without occlusions. The ICU setting, however, brings along unique challenges for recognizing facial expression of pain – the patient’s face is often covered by a respirator mask, the face is partially occluded by accessories attached to the respirator, and the patient is occasionally in a transient state of consciousness. In this paper we investigate the use of computer vision techniques for recognizing pain from partially visible faces. To establish a proof-of-concept, we simulate the occlusions most likely to happen in an ICU setting by masking out the nose, cheeks, and mouth regions, and use only a narrow band around the eyes of the patient as an input to our method. We generate these simulated occlusions using data from the UNBC-McMaster pain expression archive −a previously used dataset for pain expression recognition based on fully visible faces. We investigate multiple feature representations by extracting features only on the basis of the eye-region and train classifiers to detect the presence of pain using leave-one-person-out cross validation. Our results suggest a potential viability of automatic pain monitoring in the ICU settings involving face occlusions.