Light Noise Research Articles

A video object segmentation-based fish individual recognition method for underwater complex environments

Currently, aquaculture methods tend to combine scale and intelligence, which saves manpower and improves the survival rate of seafood at the same time. High-precision and high-efficiency fish individual recognition can provide key technical support for fish disease detection, feeding habits, body condition, etc. In the realm of intelligent aquaculture, it provides robust data support for precision fish farming. However, the current research methods for individual fish recognition struggle to maintain the network model's focus on the fish body in real marine underwater complex environments (e.g., environmental background interference such as coral reefs, overlap between fish bodies, light noise, etc.), leading to unsatisfactory recognition results. To this end, this paper proposes a method for fish individual recognition in underwater complex environments based on video object segmentation, which consists of three parts, including a fish individual segmentation detection module, a fish individual recognition module, and an all-in-one visualization module. The work adopts a combination of deep learning methods and video object segmentation algorithms to solve the problem of low attention and poor detection accuracy of fish individuals in real underwater complex environments, which effectively improves the accuracy and efficiency of fish individual recognition, and analyzes and discusses the comparison of recognition effects using different weights. The results of the simulation experiments show that the key metric Rank1 value of the method achieves more than 96% accuracy on the public datasets DlouFish, WideFish, and the Fish-seg dataset produced in this paper, and improves over the state-of-the-art methods for fish individual recognition by 2.23%, 1.33%, and 1.25%, respectively.

A microchip based Z-cell absorbance detector integrating micro-lenses and slits for portable liquid chromatography

A miniaturized microchip-based absorbance detector was developed for portable high-performance liquid chromatography (HPLC) to test glycated hemoglobin (HbA1c). The microchip integrating a Z-shaped cell, two collimating micro-lenses and two ink-filled optical slits is small in size (30 mm × 15 mm × 7 mm). The Z-shaped cell has a cross-sectional size of 500 μm × 500 μm and a physical optical path length of 2 mm. Two collimating micro-lenses were inserted in empty grooves on both sides of the cell, one micro-lens for collimating the initial light and the other for focusing the transmitted light. Optical slits on each end of the cell were used to block the stray light. Therefore, this detector indicated a low stray light level (0.011 %) and noise level (2.5 × 10−4 AU). This detector was applied for the commercial HPLC system to detect HbA1c level, and showed a low limit of detection (0.5 μg/mL) and excellent repeatability (≤ 2.03 %). The sensitivity was enhanced by 3.4 times when the optical path length was increased from 0.5 mm to 2 mm and the stray light was blocked by optical slits. The miniaturized microchip-based absorbance detector developed shows a great potential for application in portable and compact HPLC.

Information-hiding cameras: Optical concealment of object information into ordinary images.

We introduce an information-hiding camera integrated with an electronic decoder that is jointly optimized through deep learning. This system uses a diffractive optical processor, which transforms and hides input images into ordinary-looking patterns that deceive/mislead observers. This information-hiding transformation is valid for infinitely many combinations of secret messages, transformed into ordinary-looking output images through passive light-matter interactions within the diffractive processor. By processing these output patterns, an electronic decoder network accurately reconstructs the original information hidden within the deceptive output. We demonstrated our approach by designing information-hiding diffractive cameras operating under various lighting conditions and noise levels, showing their robustness. We further extended this framework to multispectral operation, allowing the concealment and decoding of multiple images at different wavelengths, performed simultaneously. The feasibility of our framework was also validated experimentally using terahertz radiation. This optical encoder-electronic decoder-based codesign provides a high speed and energy efficient information-hiding camera, offering a powerful solution for visual information security.

Modeling and reduction of high frequency scatter noise at LIGO Livingston

The sensitivity of aLIGO detectors is adversely affected by the presence of noise caused by light scattering. Low frequency seismic disturbances can create higher frequency scattering noise adversely impacting the frequency band in which we detect gravitational waves. In this paper, we analyze instances of a type of scattered light noise we call ‘Fast Scatter’ that is produced by motion at frequencies greater than 1 Hz, to locate surfaces in the detector that may be responsible for the noise. We model the phase noise to better understand the relationship between increases in seismic noise near the site and the resulting Fast Scatter observed. We find that mechanical damping of the arm cavity baffles led to a significant reduction of this noise in recent data. For a similar degree of seismic motion in the 1– 3 Hz range, the rate of noise transients is reduced by a factor of ~50.

Construction of a light noise sensor for a Neonatal Intensive Care Unit

Construction of a light noise sensor for a Neonatal Intensive Care Unit

Environmental pollution and extreme weather conditions: insights into the effect on mental health.

Environmental pollution exposures, including air, soil, water, light, and noise pollution, are critical issues that may implicate adverse mental health outcomes. Extreme weather conditions, such as hurricanes, floods, wildfires, and droughts, may also cause long-term severe concerns. However, the knowledge about possible psychiatric disorders associated with these exposures is currently not well disseminated. In this review, we aim to summarize the current knowledge on the impact of environmental pollution and extreme weather conditions on mental health, focusing on anxiety spectrum disorders, autism spectrum disorders, schizophrenia, and depression. In air pollution studies, increased concentrations of PM2.5, NO2, and SO2 were the most strongly associated with the exacerbation of anxiety, schizophrenia, and depression symptoms. We provide an overview of the suggested underlying pathomechanisms involved. We highlight that the pathogenesis of environmental pollution-related diseases is multifactorial, including increased oxidative stress, systematic inflammation, disruption of the blood-brain barrier, and epigenetic dysregulation. Light pollution and noise pollution were correlated with an increased risk of neurodegenerative disorders, particularly Alzheimer's disease. Moreover, the impact of soil and water pollution is discussed. Such compounds as crude oil, heavy metals, natural gas, agro-chemicals (pesticides, herbicides, and fertilizers), polycyclic or polynuclear aromatic hydrocarbons (PAH), solvents, lead (Pb), and asbestos were associated with detrimental impact on mental health. Extreme weather conditions were linked to depression and anxiety spectrum disorders, namely PTSD. Several policy recommendations and awareness campaigns should be implemented, advocating for the advancement of high-quality urbanization, the mitigation of environmental pollution, and, consequently, the enhancement of residents' mental health.

Anti-noise computational ghost imaging based on wavelet threshold denoising

Noise can inevitably affect imaging quality of optical imaging system. In this paper, a method of computational ghost imaging (CGI) with better anti-noise performance is proposed by using wavelet threshold denoising (WTD). The simulation and experimental results show that this method exhibits better robustness against both the light source noise and the path noise. To explain this phenomenon, the decline rate of the correlation coefficients between speckle patterns (CCSP) under different noise levels are analyzed. As a post-processing method, our method is simple to implement and is applicable to both random speckle CGI and orthogonal modulated CGI, potentially broadening application prospects in practical applications of ghost imaging.

Feasibility of Deploying Home-Based Digital Technology, Environmental Sensors, and Web-Based Surveys for Assessing Behavioral Symptoms and Identifying Their Precipitants in Older Adults: Longitudinal, Observational Study.

Apathy, depression, and anxiety are prevalent neuropsychiatric symptoms experienced by older adults. Early detection, prevention, and intervention may improve outcomes. We aim to demonstrate the feasibility of deploying web-based weekly questionnaires inquiring about the behavioral symptoms of older adults with normal cognition, mild cognitive impairment, or early-stage dementia and to demonstrate the feasibility of deploying an in-home technology platform for measuring participant behaviors and their environment. The target population of this study is older adults with normal cognition, mild cognitive impairment, or early-stage dementia. This is an observational, longitudinal study with a study period of up to 9 months. The severity of participant behavioral symptoms (apathy, depression, and anxiety) was self-reported weekly through web-based surveys. Participants' digital biomarkers were continuously collected at their personal residences and through wearables throughout the duration of the study. The indoor physical environment at each residence, such as light level, noise level, temperature, humidity, or air quality, was also measured using indoor environmental sensors. Feasibility was examined, and preliminary correlation analysis between the level of symptoms and the digital biomarkers and between the level of symptoms and the indoor environment was performed. At 13 months after recruitment began, a total of 9 participants had enrolled into this study. The participants showed high adherence rates in completing the weekly questionnaires (response rate: 275/278, 98.9%), and data collection using the digital technology appeared feasible and acceptable to the participants with few exceptions. Participants' severity of behavioral symptoms fluctuated from week to week. Preliminary results show that the duration of sleep onset and noise level are positively correlated with the anxiety level in a subset of our participants. This study is a step toward more frequent assessment of older adults' behavioral symptoms and holistic in situ monitoring of older adults' behaviors and their living environment. The goal of this study is to facilitate the development of objective digital biomarkers of neuropsychiatric symptoms and to identify in-home environmental factors that contribute to these symptoms.

Surface Defect Detection of Aluminum Profiles Based on Multiscale and Self-Attention Mechanisms.

To address the various challenges in aluminum surface defect detection, such as multiscale intricacies, sensitivity to lighting variations, occlusion, and noise, this study proposes the AluDef-ClassNet model. Firstly, a Gaussian difference pyramid is utilized to capture multiscale image features. Secondly, a self-attention mechanism is introduced to enhance feature representation. Additionally, an improved residual network structure incorporating dilated convolutions is adopted to increase the receptive field, thereby enhancing the network's ability to learn from extensive information. A small-scale dataset of high-quality aluminum surface defect images is acquired using a CCD camera. To better tackle the challenges in surface defect detection, advanced deep learning techniques and data augmentation strategies are employed. To address the difficulty of data labeling, a transfer learning approach based on fine-tuning is utilized, leveraging prior knowledge to enhance the efficiency and accuracy of model training. In dataset testing, our model achieved a classification accuracy of 97.6%, demonstrating significant advantages over other classification models.

Beverage Deterioration Monitoring Based on Surface Tension Dynamics and Absorption Spectrum Analysis

Biochemical information sensing has always been one of the challenges in ubiquitous sensing research for mobile computing. Microorganisms will cause undetectable deterioration in drink production, such as wine and beverage, and microbial contamination is highly susceptible during storage like some liquors can be bottled for sometimes over ten years. Microbial culture methods are common for quality monitoring but unsuitable for real-time beverage quality monitoring. As far as we know, we are the first to use ubiquitous sensing for real-time microbial contamination detection. We designed a lightweight monitoring system called Microbe-Radar, which uses light signals to monitor real-time beverage quality. Microbe-Radar uses eight LEDs and a photodiode to detect fine-grained surface tension and absorption spectrum changes caused by microbial metabolites and growth during deterioration. Characteristic offset degree measurement and absorption spectrum dimension expansion are two critical technologies. Moreover, we implemented countermeasures against ambient light noise and sloshing interference. Microbe-Radar's surface tension and absorption spectrum measurement errors are only 0.89 mN/m and 2.4%, respectively, making identifying the contamination duration, microorganism content, and microorganism composition worthwhile. Experiments showed Microbe-Radar could determine potential issues with liquor quality when the liquid becomes health-threatening or even just contaminated, with an accuracy of 97.5%. Microbe-Radar can also be extended to beverage deterioration warning, with deterioration prediction accuracy of more than 90.6% for five beverages (milk, apple juice, etc.).

Concurrent exposure to light and traffic noise pollution augments behavioral deficits in rats: Protective effect of curcumin

The current study was aimed to explore the effect of light and traffic noise pollution exposure on behavioral and neurochemical deficits in adult male Wistar rats. We hypothesized that exposure to these pollutants alone or in combination may cause behavioral deficits in rats. Animals were allocated into different groups and were exposed to either varying light cycles (150 lx-5 lx, 14:10 h) or traffic noise with sound level 100 dBA for 6 h/day or both for 28 days. Concurrently, Curcumin (100 mg/kg; per oral; 28 days) was administered in varying light cycles and noise exposed animal groups to study the preventive effect. After the exposure time, the Morris water maze test, elevated plus maze test, novel object recognition test, locomotor activity test, and forced swimming test were conducted. The neurobehavioral results suggested that only combined exposure of light and noise pollution markedly impaired the learning as well as spatial and reference memory in rats. Furthermore, we found significant anxiety (less no. of open arm entries in EPM) and depressive-like behavior (increased immobility time) in light or/and traffic noise pollution exposed group animals in comparison to normal control groups. Curcumin treatment significantly prevented the behavioral anomalies in combined light and noise exposed rats. Furthermore, our results revealed augmentation of acetylcholinesterase, oxidative stress markers and interleukin (IL)-1β in the hippocampal region of noise and light-exposed groups which were markedly ameliorated by curcumin. In conclusion, our results suggest that curcumin significantly modulates light and noise pollution exposed behavioral and neurochemical anomalies in rats.

High-Precision Position Detection and Communication Fusion Technology Using Beacon Spread-Spectrum Modulation with Four-Quadrant Detector

In space laser communication, the wide divergence angle of beacon light leads to substantial spatial losses, compounded by background light and detector noise; this results in compromised precision in the detection of the beacon light position. To solve this problem, a high-precision detection technique and communication composite technology employing a four-quadrant detector (QD) with beacon spread-spectrum modulation are proposed. Pseudo-random sequences (PRNs) are employed to spread the beacon communication spectrum, with the spread-spectrum signal utilized to modulate the intensity of the transmitted beacon light at the transmitter end. At the receiver, QD photocurrent signals are cross-correlated with an identical PRN that is used for modulation. The strong auto-correlation properties of PRNs, which are uncorrelated with noise, enhance the output signal-to-noise ratio (SNR), enabling precise position detection and beacon communication under high-SNR conditions. Theoretical analysis is used to explore the effects of spreading gain on the sensitivity of system detection and the precision of position detection. The experimental results demonstrate that the beacon spread-spectrum modulation scheme effectively detects the position of the light spot. At a received optical power of −37 dBm and spreading sequence PRN depths of 1023, 127, and 31, the root-mean-square error (RMSE) values are 0.983 μm, 2.876 μm, and 7.275 μm, respectively. This corresponds to improvements of 14.96 dB, 10.29, dB, and 6.26 dB compared to direct detection precision (30.811 μm). Additionally, under an identical signal bandwidth, the sensitivity improves by 14.6 dB, 10.1 dB, and 6.4 dB, respectively. The proposed beacon spread-spectrum scheme mitigates the limitations of hardware reception sensitivity and position-detection precision, demonstrating its potential application in high-precision detection in long-distance interstellar laser communication.

Easy Rocap: A Low-Cost and Easy-to-Use Motion Capture System for Drones

Fast and accurate pose estimation is essential for the local motion control of robots such as drones. At present, camera-based motion capture (Mocap) systems are mostly used by robots. However, this kind of Mocap system is easily affected by light noise and camera occlusion, and the cost of common commercial Mocap systems is high. To address these challenges, we propose Easy Rocap, a low-cost, open-source robot motion capture system, which can quickly and robustly capture the accurate position and orientation of the robot. Firstly, based on training a real-time object detector, an object-filtering algorithm using class and confidence is designed to eliminate false detections. Secondly, multiple-object tracking (MOT) is applied to maintain the continuity of the trajectories, and the epipolar constraint is applied to multi-view correspondences. Finally, the calibrated multi-view cameras are used to calculate the 3D coordinates of the markers and effectively estimate the 3D pose of the target robot. Our system takes in real-time multi-camera data streams, making it easy to integrate into the robot system. In the simulation scenario experiment, the average position estimation error of the method is less than 0.008 m, and the average orientation error is less than 0.65 degrees. In the real scenario experiment, we compared the localization results of our method with the advanced LiDAR-Inertial Simultaneous Localization and Mapping (SLAM) algorithm. According to the experimental results, SLAM generates drifts during turns, while our method can overcome the drifts and accumulated errors of SLAM, making the trajectory more stable and accurate. In addition, the pose estimation speed of our system can reach 30 Hz.

A COMPREHENSIVE STUDY ON THE FUTURE OF CURTAIN DESIGN PATTERNS

The study, "A Comprehensive Study on the Future of Curtain Design Patterns," explores the evolving trends and technological advancements shaping the curtain industry. The research highlights key findings that reveal a shift towards sustainable and smart textiles, driven by consumer demand for eco-friendly and technologically integrated home furnishings. Patterns are moving away from traditional designs to embrace more abstract, geometric, and nature-inspired motifs, reflecting broader societal trends towards minimalism and biophilia. One of the significant discoveries is the impact of digital printing technology, which allows for greater customization and intricate designs that were previously unfeasible. This advancement is expected to revolutionize the market by offering consumers bespoke options that cater to individual tastes and spatial requirements. Additionally, the study identifies a growing preference for multifunctional curtains equipped with smart features, such as light control, temperature regulation, and noise reduction, enhancing the functionality of living spaces.The research also underscores the importance of sustainability, noting a rise in the use of organic materials and recycled fabrics. This trend aligns with the global movement towards reducing environmental footprints and promotes the adoption of circular economy principles within the textile industry. In summary, the study provides a forward-looking perspective on curtain design, emphasizing the interplay between technology, aesthetics, and sustainability. The findings suggest that future curtain designs will not only serve decorative purposes but also integrate advanced functionalities, catering to the evolving needs of modern consumers. This comprehensive analysis offers valuable insights for designers, manufacturers, and retailers aiming to stay ahead in a competitive and rapidly changing market.

Smart Farming with Sooty Tern Optimization based LS-HGNet Classification Model

Smart farming technologies enable farmers to use resources like water, fertilizer and pesticides as efficiently as possible. This paper discusses how Unmanned Aerial Vehicle (UAV) pictures can be used to automatically detect and count tassels, thereby advancing the advancement of strategic maize planting. The real state of affairs in cornfields is complicated, though, and the current algorithms struggle to provide the speed and accuracy required for real-time detection. This research employed a sizable, excellent dataset of maize tassels to solve this problem. This paper suggests using the bottom-hat-top-hat preprocessing technique to address the lighting irregularities and noise in maize photos taken by drones. The Lightweight weight-stacked hourglass Network (LS-HGNet) model is suggested for classification. The hourglass network structure of LS-HGNet, which is mostly utilised as a backbone network, has allowed significant advancements in the discovery of maize tassels. In light of this, the current work suggests a lighter variant of the hourglass network that also enhances the accuracy of tassel detection in maize plants. The additional skip connections used in the new hourglass network architecture allow minimal changes to the number of network parameters while improving performance. Consequently, the suggested LS-HGNet classifier lowers the computational burden and increases the convolutional receptive field. The hyperparameter tuning process is then carried out using the Sooty Tern Optimisation Algorithm (STOA), which helps increase tassel detection accuracy. Numerous tests were conducted to verify that the suggested approach is more accurate at 98.7% and more efficient than the most advanced techniques currently in use.

DDFL: Dual-Domain Feature Learning for nighttime semantic segmentation

Nighttime semantic segmentation has been playing a critical role in intelligent transportation, building safety and urban management. However, nighttime scenes present some challenges such as complex structures, multiple light sources, uneven lighting and blurry image noise, which severely degrade the segmentation quality of nighttime images. To address these challenges, we propose a Dual-Domain Feature Learning (DDFL) model for nighttime semantic segmentation. Our approach introduces three innovative ideas. First, we establish an exposure correction module to address the impact of lighting differences on the model’s learning, so as to maximally restore the pixel distortion and blurry areas caused by artificial light in nighttime scenes. Second, we incorporate frequency domain information into the nighttime segmentation task to give the model stronger discrimination ability. Finally, we introduce a dual-domain fusion module to complement the information of learning from the spatial and frequency domains in a cross-fusion manner, enabling the network to perceive semantic information while preserving details. The proposed model was experimentally tested on the Nightcity, Nightcity+ and BDD100k datasets. Our results demonstrate that our model outperforms mainstream models, achieving mIoU scores of 56.73%, 57.41% and 28.97%, respectively, under different lighting, image exposure levels, and resolutions. These results show that our model is capable of segmenting nighttime scenes efficiently in a high-quality way.

DTT-CGINet: A Dual Temporal Transformer Network with Multi-Scale Contour-Guided Graph Interaction for Change Detection

Deep learning has dramatically enhanced remote sensing change detection. However, existing neural network models often face challenges like false positives and missed detections due to factors like lighting changes, scale differences, and noise interruptions. Additionally, change detection results often fail to capture target contours accurately. To address these issues, we propose a novel transformer-based hybrid network. In this study, we analyze the structural relationship in bi-temporal images and introduce a cross-attention-based transformer to model this relationship. First, we use a tokenizer to express the high-level features of the bi-temporal image into several semantic tokens. Then, we use a dual temporal transformer (DTT) encoder to capture dense spatiotemporal contextual relationships among the tokens. The features extracted at the coarse scale are refined into finer details through the DTT decoder. Concurrently, we input the backbone’s low-level features into a contour-guided graph interaction module (CGIM) that utilizes joint attention to capture semantic relationships between object regions and the contour. Then, we use the feature pyramid decoder to integrate the multi-scale outputs of the CGIM. The convolutional block attention modules (CBAMs) employ channel and spatial attention to reweight feature maps. Finally, the classifier discriminates change pixels and generates the final change map of the difference feature map. Several experiments have demonstrated that our model shows significant advantages over other methods in terms of efficiency, accuracy, and visual effects.

Ghost imaging under direct sunlight conditions using FADOF

Sunlight background noise significantly hinders the operation of ghost imaging systems, posing a considerable challenge for target imaging under daytime sunlight conditions. This paper introduces a method to eliminate sunlight background noise using a Faraday anomalous dispersion optical filter (FADOF). A ghost imaging system based on FADOF is constructed, and experiments are conducted under strong background noise conditions. The system operates outdoors in direct sunlight, utilizing sunlight introduction system to introduce light into the detection path, directly reaching the detection end of the system. In this real sunlight noise condition, the ghost imaging system using FADOF filtering achieved nearly continuous and stable imaging throughout three summer days, contrasting with a system using a 10 nm filter that only functions properly after sunset. The research findings indicate that FADOF effectively enhances the ghost imaging system's resistance to background light noise, enabling continuous operation under conditions of strong background noise throughout the day.

An approach to ensure joint illumination & communication performance of a forward error corrected indoor visible light communication (VLC) system in presence of ambient light interference

Abstract In recent time of looming radio frequency (RF) spectrum crisis, visible light communication using lighting infrastructure emerged as a potential alternative at an indoor environment. This paper addresses the setback associated with ambient light interference in an indoor Visible Light Communication (VLC) system to ensure joint communication and illumination performance inside an office room. A novel VLC architecture with suitable white light emitting diode (WLED) luminaire arrangement is presented to minimize the dispersion of signal to interference plus noise ratio (SINR) across the room. Luminaires are categorized in two groups viz. data transmitting illuminants and illuminants for lighting purpose. The first group is dedicated to transmit data as well as serves the purpose of illumination. The other set creates only ambient illumination to achieve quality lighting attributes. The proposed forward error corrected receiver configuration discards the ambient light noise originated by the illuminants that serve the ambient illumination. Tail biting convolutional encoder and viterbi decoder are used at the encoding section of the transmitter and decoding section of the receiver respectively to improve bit error rate. Results obtained through MATLAB simulation shows better average bit error rate (BER) in the order of 10−8 measured at uniformly distributed 25 grid points over the working plane. At the same time achieved average horizontal illuminance with good uniformity comply with ISO recommendation.

DiffusionFR: Species Recognition of Fish in Blurry Scenarios via Diffusion and Attention

Blurry scenarios, such as light reflections and water ripples, often affect the clarity and signal-to-noise ratio of fish images, posing significant challenges for traditional deep learning models in accurately recognizing fish species. Firstly, deep learning models rely on a large amount of labeled data. However, it is often difficult to label data in blurry scenarios. Secondly, existing deep learning models need to be more effective for the processing of bad, blurry, and otherwise inadequate images, which is an essential reason for their low recognition rate. A method based on the diffusion model and attention mechanism for fish image recognition in blurry scenarios, DiffusionFR, is proposed to solve these problems and improve the performance of species recognition of fish images in blurry scenarios. This paper presents the selection and application of this correcting technique. In the method, DiffusionFR, a two-stage diffusion network model, TSD, is designed to deblur bad, blurry, and otherwise inadequate fish scene pictures to restore clarity, and a learnable attention module, LAM, is intended to improve the accuracy of fish recognition. In addition, a new dataset of fish images in blurry scenarios, BlurryFish, was constructed and used to validate the effectiveness of DiffusionFR, combining bad, blurry, and otherwise inadequate images from the publicly available dataset Fish4Knowledge. The experimental results demonstrate that DiffusionFR achieves outstanding performance on various datasets. On the original dataset, DiffusionFR achieved the highest training accuracy of 97.55%, as well as a Top-1 accuracy test score of 92.02% and a Top-5 accuracy test score of 95.17%. Furthermore, on nine datasets with light reflection noise, the mean values of training accuracy reached a peak at 96.50%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 90.96% and 94.12%, respectively. Similarly, on three datasets with water ripple noise, the mean values of training accuracy reached a peak at 95.00%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 89.54% and 92.73%, respectively. These results demonstrate that the method showcases superior accuracy and enhanced robustness in handling original datasets and datasets with light reflection and water ripple noise.