18 December 2025 in Photonics Research
Atmospheric turbulence (AT) severely degrades free-space communications, imaging, and sensing systems, driving critical demand for diagnostics of turbulence strength ( C
n
2 ). However, existing approaches face limited adaptability, high latency, and excessive power consumption for deployment. Here, we propose an orbital angular momentum (OAM)-mediated optoelectronic neural network (OOENN) that integrates a diffractive optical module for OAM spectrum feature extraction with a shallow electronic module for turbulence diagnostics, leveraging OAM spectrum data transformation. The optical module extracts turbulence-encoded features from distorted Laguerre–Gaussian (LG) beams and decomposes its output field into OAM spectrum data. These data are then fed into an electronic module that diagnoses turbulence strength using a minimal fully connected network with 9 input neurons and nonlinear activation. The OOENN performs feature extraction at light speed while enabling ultra-efficient electronic processing, thereby alleviating the latency and power constraints. Experimental results demonstrate diagnostics of five turbulence strengths within C
n
2 =10 −16 to 10 −12 m −2/3 , achieving 82.4% accuracy at 80 ms latency per diagnosis. This fusion of structured light fields with optoelectronic intelligence establishes a technological foundation for next-generation adaptive systems in turbulence-resilient optical communications, remote sensing, and quantum information transfer.
18 September 2023 in Optics Express
Wavefront coding (WFC) is an effective technique for extending the depth-of-field of imaging systems, including optical encoding and digital decoding. We applied physical prior information and frequency domain model to the wavefront decoding, proposing a reconstruction method by a generative model. Specifically, we rebuild the baseline inspired by the transformer and propose three modules, including the point spread function (PSF) attention layer, multi-feature fusion block, and frequency domain self-attention block. These models are used for end-to-end learning to extract PSF feature information, fuse it into the image features, and further re-normalize the image feature information, respectively. To verify the validity, in the encoding part, we use the genetic algorithm to design a phase mask in a large field-of-view fluorescence microscope system to generate the encoded images. And the experimental results after wavefront decoding show that our method effectively reduces noise, artifacts, and blur. Therefore, we provide a deep-learning wavefront decoding model, which improves reconstruction image quality while considering the large depth-of-field (DOF) of a large field-of-view system, with good potential in detecting digital polymerase chain reaction (dPCR) and biological images.
1 November 2021 in PLOS ONE
Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as color and shape, and few of them pay enough attention to semantics. In this paper, we propose a link-based semantic similarity search method, namely PictureSim, for effectively searching similar pictures by building a picture-tag network. The picture-tag network is built by “description” relationships between pictures and tags, in which tags and pictures are treated as nodes, and relationships between pictures and tags are regarded as edges. Then we design a TF-IDF-based model to removes the noisy links, so the traverses of these links can be reduced. We observe that “similar pictures contain similar tags, and similar tags describe similar pictures”, which is consistent with the intuition of the SimRank. Consequently, we utilize the SimRank algorithm to compute the similarity scores between pictures. Compared with content-based methods, PictureSim could effectively search similar pictures semantically. Extensive experiments on real datasets to demonstrate the effectiveness and efficiency of the PictureSim.
28 December 2020 in IEEE Access
This paper proposes an end-to-end Learnable Edge-Attention Map (LEAM) method to assist image inpainting. To achieve a better-recovered effect, we design an edge attention module, which extracts the feature information of the edge map and re-normalizes the image feature information when automatically updating the edge map. And the information of known regions is adopted to assist the decoder generates semantically consistent results. A dual-discriminator structure consisting of the local discriminator and global discriminator is proposed to generate realistic texture details and improve the consistency of the overall structure. Experiments show that our method can obtain higher image inpainting quality than the existing state-of-the-art approaches, which improves PSNR by 3.58%, SSIM by 2.27%, and reduce MAE by 9.21% on average.