Preparation of dense alumina (Al₂O₃) thin film through atomic layer deposition (ALD) provides a pathway to achieve the encapsulation of organic light emitting devices (OLED). Unlike traditional ALD which is usually executed at higher reaction n temperatures that may affect the performance of OLED, this application discusses the development on preparation of ALD thin film at a low temperature. One concern of ALD is the suppressing effect of ambient temperature on uniformity of thin film. To mitigate this issue, the pumping time in each reaction cycle was increased during the preparation process, which removed reaction byproducts and inhibited the formation of vacancies. As a result, the obtained thin film had both high uniformity and density properties, which provided an excellent encapsulation performance. The results from microstructure morphology analysis, water vapor transmission rate, and lifetime test showed that the difference in uniformity between thin films prepared at low temperatures, with increased pumping time, and high temperatures was small and there was no obvious influence of increased pumping time on light emitting performance. Meanwhile, the permeability for water vapor of the thin film prepared at a low temperature was found to reach as low as 1.5 × 10⁻⁴ g/(m²·day) under ambient conditions of 25 °C and 60% relative humidity, indicating a potential extension in the lifetime for the OLED.

Automatic fovea localization is a challenging issue. In this paper, we focus on the study of fovea localization and propose a robust fovea localization method. We propose concentric circular sectional symmetry measure (CCSSM) for symmetry axis detection, and region of interest (ROI) determination, which is a global feature descriptor robust against local feature changes, to solve the lesion occlusion problem using both structure features and morphological features. We propose the index of convexity and concavity (ICC) as the convexity-concavity measure of the surface and provide a quantitative evaluation tool for ophthalmologists to learn whether the occurrence of lesion within the ROI. We propose the weighted gradient accumulation map, which is insensitive to local intensity changes and can overcome the influence of noise and contamination, to perform refined localization. The advantages of the proposed method lies in two aspects. First, the accuracy and robustness can be achieved without typical sophisticated manner, i.e., blood vessel segmentation and parabola fitting. Second, the lesion occlusion is considered in our plan of fovea localization. Our proposed symmetry-based method is innovative in the solution of fovea detection, and it is simple, practical, and controllable. Experiment results show that the proposed method can resist the interference of unbalanced illumination and lesions, and achieve high accuracy rate in five datasets. Compared to the state-of-the-art methods, high robustness and accuracy of the proposed method guarantees its reliability.

The demand for applying the iris segmentation model on mobile devices has been growing rapidly. Most current segmentation networks have an enormous amount of parameters, hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification networks and ignore the inherent characteristic of segmentation. To address the challenge, we propose a lightweight segmentation network (LiSeNet) for iris segmentation of noisy images. Unlike previous studies that only focus on improving the accuracy of segmentation masks, LiSeNet can simultaneously obtain segmentation masks, parameterized pupillary and limbic boundaries of the iris, further enabling CNN-based iris segmentation to be applied in any regular iris recognition systems. We first propose a multiscale concatenate (MSC) Block, which connects multiple sizes of convolution kernels in a dense manner, gradually reduces the dimension of feature maps and uses the aggregation of them for image representation. Based on the MSC block, we develop a two-stage refinement encoder to aggregate discriminative features through subnetwork feature reuse and substage feature reassess, thus obtaining a sufficient receptive field and enhancing the model learning ability. To exploit object contextual information more efficiently, we further devise a grouped spatial attention to emphasize the important features and suppress irrelevant noises through a gating mechanism in the decoder. Extensive experiments on three challenging iris datasets show that LiSeNet, without any complicated postprocessing, achieves competitive or state-of-the-art performance with only 2.2M parameters, being 14 × smaller than the previous best method. Code will be publicly available.

Medical multiobjective image segmentation aims to group pixels to form multiple regions based on the different properties of the medical images. Segmenting the 3D cardiovascular magnetic resonance (CMR) images is still a challenging task owing to several reasons, including individual differences in heart shapes, varying signal intensities, and differences in data signal-to-noise ratios. This paper proposes a novel and efficient U-Net-based 3D sparse convolutional network named SparseVoxNet. In this network, there are direct connections between any two layers with the same feature-map size, and the number of connections is reduced. Therefore, the SparseVoxNet can effectively cope with the optimization problem of gradients vanishing when training a 3D deep neural network model on small sample data by significantly decreasing the network depth, and achieveing better feature representation using a spatial self-attention mechanism finally. The proposed method in this paper has been thoroughly evaluated on the HVSMR 2016 dataset. Compared with other methods, the method achieves better performance.

Instance segmentation is an important task in computer vision. In order to enhance the multi-level features expression ability of the segmentation networks, a novel module is proposed in this paper. Firstly, we design a weighted bi-directional feature fusion way by computing the weight distribution function of bi-directional feature pyramid network. Secondly, we propose a joint attention mechanism to effectively filter different levels of feature information by adopting serial and parallel ways to combine the channel attention and spatial attention modules. At the same time, the module uses dynamic convolution to stabilize the calculation speed while improve the 6.7% mean average precision of segmentation. The experiments on the COCO dataset demonstrate that the module can effectively improve the performance of the existing instance segmentation networks.