Despite the rapid increase in the number and applications of plankton imaging systems in marine science, processing large numbers of images remains a major challenge due to large variations in image content and quality in different marine environments. We constructed an automatic plankton image recognition and enumeration system using an enhanced Convolutional Neural Network (CNN) and examined the performance of different network structures on automatic plankton image classification. The procedure started with an adaptive thresholding approach to extract Region of Interest (ROIs) from in situ plankton images, followed by a procedure to suppress the background noise and enhance target features for each extracted ROI. The enhanced ROIs were classified into seven categories by a pre-trained classifier which was a combination of a CNN and a Support Vector Machine (SVM). The CNN was selected to improve feature description and the SVM was utilized to improve classification accuracy. A series of comparison experiments were then conducted to test the effectiveness of the pre-trained classifier including the combination of CNN and SVM versus CNN alone, and the performance of different CNN models. Compared to CNN model alone, the combination of CNN and SVM increased classification accuracy and recall rate by 7.13% and 6.41%, respectively. Among the selected CNN models, the ResNet50 performed the best with accuracy and recall at 94.52% and 94.13% respectively. The present study demonstrates that deep learning technique can improve plankton image recognition and that the results can provide useful information on the selection of different CNN models for plankton recognition. The proposed algorithm could be generally applied to images acquired from different imaging systems.

Deep learning has been proven to provide solutions for computational ghost imaging (CGI). However, in current CGI techniques, the quality of the reconstructed image is adversely affected by the position and intensity of the scattering medium. In this study, the feasibility of using a deep neural network (DNN) by using the hybrid simulated data to facilitate CGI through a scattering medium is demonstrated, particularly when the scattering medium is in front of an object. Under a specific order of the measurement matrix, the CGI measurement equation is introduced along with a disturbance factor of the scattering effect to generate simulation data, thereby representing imaging situations with the scattering medium at different positions. The selection of disturbance parameters is determined by the correlation between the simulation signal and the experimental signal. Then an end-to-end DNN is trained using experimentally obtained light intensity signals, and it shows that the quality of the reconstruction results is improved when there is a scattering medium in the emission path. The reported technique effectively solves the problem of CGI reconstruction under different scattering paths with a common DNN, and may have broad applications in fast adaptive CGI for new and uncertain scenarios.

Ghost imaging (GI) possesses significant application prospects in scattering imaging, which is a classic example of underdetermined conversion problem in optical field. However, even under the framework of single-pixel imaging (SPI), a challenge remains unresolved, i.e., structured patterns may be damaged by scattering media in both the emissive and receiving optical paths. In this study, an extendible ghost imaging, a numerical reproduction of the qualitative process using deep learning (DL)-based GI is presented. First, we propose and experimentally verify a brief degradation-guided reconstruction (DR) approach with a neural network to demonstrate the degradation principle of scattering, including realistic dataset simulations and a new training structure in the form of a convolutional neural network (CNN). Then, a novel photon contribution model (PCM) with redundant parameters is proposed to generate intensity sequences from the forward direction through volumetric scattering media; the redundant parameters are constructed and relate to the special output configuration in a lightweight CNN with two branches, based on a reformulated atmospheric scattering model. The proposed scheme recovers the semantics of targets and suppresses the imaging noise in the strong scattering medium, and the obtained results are very satisfactory for applications to scattering media of more practical scenarios and are available for various scattering coefficients and work distances of an imaging prototype. After using DL methods in computational imaging, we conclude that strategies embedded in optics or broader physical factors can result in solutions with better effects for unanalyzable processes.

Stabilized zoom systems possess the advantages such as the simplified system layout, improved system stability, enhanced imaging performance, and a high zoom speed. The complex system design to achieve high performances requires calculations or investigations of the initial system for optimization and improvements, and thus, specific design techniques are pursued. In this study, we propose an automatic optical design scheme of synthetic characteristics for the off-axis stabilized zoom systems, which using focal length variable (FLV) opto-electronic elements and with a high zoom ratio. The study aims at evaluating and synthetically achieving the zooming properties and the image quality balance of entire focus imaging. The multi-element stabilized zoom systems are characterized using the Gaussian brackets expressions and their optimal solution ranges for high zoom ratios are deduced to achieve non-defocusing imaging in specific stroke ranges of FLV elements. Then considering the analytical characterization of the off-axis-induced primary aberrations at multi-conjugate positions, we use a conic surface to deduce the basic expression of the nodal aberration. Thereby the nonlinear global merit function is established with a semi-empirical mathematical model based on nodal aberration theory and nonlinear zoom equation for maintaining the stability of focal length and image plane drift. And the theory of Pareto Optimality is employed in the process of verifying the superiority of the solutions. Finally, a series of solutions for a high zoom ratio and aberration compensation are implemented and the optimal configurations with conical surfaces for an off-axis stabilized zoom system are obtained.

In this study, we propose a method for training convolutional neural networks to make them identify and classify images with higher classification accuracy. By combining the Cartesian and polar coordinate systems when describing the images, the method of recognition and classification for plankton images is discussed. The optimized classification and recognition networks are constructed. They are available for in situ plankton images, exploiting the advantages of both coordinate systems in the network training process. Fusing the two types of vectors and using them as the input for conventional machine learning models for classification, support vector machines (SVMs) are selected as the classifiers to combine these two features of vectors, coming from different image coordinate descriptions. The accuracy of the proposed model was markedly higher than those of the initial classical convolutional neural networks when using the in situ plankton image data, with the increases in classification accuracy and recall rate being 5.3% and 5.1% respectively. In addition, the proposed training method can improve the classification performance considerably when used on the public CIFAR-10 dataset.

A four-group stabilized zoom system using two liquid lenses and two fixed lens groups is proposed. We describe the design principle, realization, and the testing of a 5.06:1 zoom system. The realized effective focal length (EFL) range is 6.93 mm to 35.06 mm, and the field of view (FOV) range is 8° to 40°. The system can zoom fast when liquid lens 1’s (L₁’s) optical power take the value from 0.0087 mm⁻¹ to 0.0192 mm⁻¹ and liquid lens 2’s (L₂’s) optical power take the value from 0.0185 mm⁻¹ to −0.01 mm⁻¹. Response time of the realized zoom system was less than 2.5 ms, and the settling time was less than 15 ms.The analysis of elements’ parameters and the measurement of lens performance not only verify the design principle further, but also show the zooming process by the use of two liquid lenses. The system is useful for motion carriers e.g., robot, ground vehicle, and unmanned aerial vehicles considering that it is fast, reliable, and miniature.