Search

Light field (LF) cameras can capture a scene's information from all different directions and provide comprehensive image information. However, the resulting data processing commonly encounters problems of low contrast and low image quality. In this article, we put forward a content-adaptive light field contrast enhancement scheme using a focal stack (FS) and hierarchical structure. The proposed FS set contained 300 light field images, which were captured using a Lytro-Illum camera. In addition, we integrated the classical Stanford Lytro Light Field Archive and JPEG Pleno Database. Specifically, according to the global brightness, the acquired LF images were classified into four different categories. First, we transformed the original LF FS into a depth map (DMAP) and all-in-focus (AIF) image. The image category was preliminarily determined depending on the brightness information. Then, the adaptive parameters were acquired by the corresponding multilayer perceptron (MLP) network training, which intrinsically enhanced the contrast and adjusted the light field image. Finally, our method automatically produced an enhanced FS based on the DMAP and AIF image. The experimental comparison results demonstrate that the adaptive values predicted by our MLP had high precision and approached the ground truth. Moreover, compared to existing contrast enhancement methods, our method provides a global contrast enhancement, which improves, without over-enhancing, local areas. The complexity of image processing is reduced, and real-time, adaptive LF enhancement is realized. [ABSTRACT FROM AUTHOR]

The retinal vessels in the human body are the only ones that can be observed directly by non-invasive imaging techniques. Retinal vessel morphology and structure are the important objects of concern for physicians in the early diagnosis and treatment of related diseases. The classification of retinal vessels has important guiding significance in the basic stage of diagnostic treatment. This paper proposes a novel method based on generative adversarial networks with improved U-Net, which can achieve synchronous automatic segmentation and classification of blood vessels by an end-to-end network. The proposed method avoids the dependency of the segmentation results in the multiple classification tasks. Moreover, the proposed method builds on an accurate classification of arteries and veins while also classifying arteriovenous crossings. The validity of the proposed method is evaluated on the RITE dataset: the accuracy of image comprehensive classification reaches 96.87%. The sensitivity and specificity of arteriovenous classification reach 91.78% and 97.25%. The results verify the effectiveness of the proposed method and show the competitive classification performance. [ABSTRACT FROM AUTHOR]

For the first time, a novel NiFe2O4/paper-based magnetoelastic (ME) biosensor was developed for rapid, sensitive, and portable detection of human serum albumin (HSA). Due to the uniquely magnetoelastic effect of NiFe2O4 nanoparticles and the excellent mechanical properties of the paper, the paper-based ME biosensor transforms the surface stress signal induced by the specific binding of HSA and antibody modified on the paper into the electromagnetic signal. The accumulated binding complex generates a compressive stress on the biosensor surface, resulting in a decrease in the biosensor's static magnetic permeability, which correlates to the HSA concentrations. To improve the sensitivity of the biosensor, the concentration of NiFe2O4 nanofluid and the impregnated numbers of the NiFe2O4 nanofluid-impregnated papers were optimized. The experimental results demonstrated that the biosensor exhibited a linear response to HSA concentrations ranging from 10 μg∙mL−1 to 200 μg∙mL−1, with a detection limit of 0.43 μg∙mL−1, which is significantly lower than the minimal diagnosis limit of microalbuminuria. The NiFe2O4/paper-based ME biosensor is easy to fabricate, and allows the rapid, highly-sensitive, and selective detection of HSA, providing a valuable analytical device for early monitoring and clinical diagnosis of microalbuminuria and nephropathy. This study shows the successful integration of the paper-based biosensor and the ME sensing analytical method will be a highly-sensitive, easy-to-use, disposable, and portable alternative for point-of-care monitoring. [ABSTRACT FROM AUTHOR]

Flexible electronics devices with tactile perception can sense the mechanical property data of the environment and the human body, and they present a huge potential in the human health system. In particular, the introduction of ultra-flexible and self-powered characteristics to tactile sensors can effectively reduce the problems caused by rigid batteries. Herein, we report a triboelectric nanogenerator (TENG), mainly consisting of an ultra-flexible polydimethylsiloxane (PDMS) film with micro-pyramid-structure and sputtered aluminum electrodes, which achieves highly conformal contact with skin and the self-powered detection of human body motions. The flexible polyethylene terephthalate (PET) film was selected as spacer layer, which made the sensor work in the contact-separation mode and endowed the perfect coupling of triboelectrification and electrostatic induction. Moreover, the controllable and uniform micro-structure PDMS film was fabricated by using the micro-electro-mechanical system (MEMS) manufacturing process, bringing a good sensitivity and high output performance to the device. The developed TENG can directly convert mechanical energy into electric energy and light up 110 green Light-Emitting Diodes (LEDs). Furthermore, the TENG-based sensor displays good sensitivity (2.54 V/kPa), excellent linearity (R2 = 0.99522) and good stability (over 30,000 cycles). By virtue of the compact size, great electrical properties, and great mechanical properties, the developed sensor can be conformally attached to human skin to monitor joint movements, presenting a promising application in wearable tactile devices. We believe that the ultra-flexible and self-powered tactile TENG-based sensor could have tremendous application in wearable electrons. [ABSTRACT FROM AUTHOR]