Traditional Image Processing Algorithms Research Articles

Machine vision-based detection of surface defects in cylindrical battery cases

Automotive 21700 series lithium batteries are prone to surface defects during production and transportation, thus affecting their performance, so we propose a full-surface defect detection method for battery cases based on the synthesis of traditional image processing and deep learning to address this problem. First, the mechanism of surface defects on a battery case is analysed, and the types of surface defects are summarized. A suitable platform for image acquisition is designed for the severely reflective surface. Since there is no publicly available defect dataset for cylindrical battery cases, a defect dataset is established, and the dataset is augmented and expanded via the traditional method and the ACGAN model. For the defects on the top of the battery case, a traditional image processing algorithm is used to combine the roundness and the area of the area pixels to make a comprehensive judgement. For the defects on the bottom and side of the battery case, after comparing and analysing a variety of deep learning networks, the YOLOv7 model is selected to address the data characteristics of the large experimental inputs and the small targeted defects. To improve the accuracy of the model to meet the needs of real-time detection in industry, the CA attention mechanism, the DYHEAD dynamic detector head, and the slicing-assisted super inference (SAHI) method are used, with a final map accuracy reaching 98.1 %, which is 2.7 % higher than that of the initial model. Compared with mainstream target detection algorithms, the algorithm in this paper has good detection performance for cylindrical battery case defect detection and can be better applied to real-time detection in industry.

Fabric Defect Detection Method Based on Multi-scale Fusion Attention Mechanisms

Abstract Fabric defect detection is extremely important for the development of the textile industry, but the existing traditional image processing algorithms are not good enough to detect fabric defects, and the detection efficiency and accuracy of the classical deep learning model is not satisfactory, so this paper proposes an improved fabric defect detection method based on multi-scale fusion of attention mechanism YOLOv7-PCBS. Based on the YOLOv7 network structure, some of the standard convolutions of the backbone network are replaced with Partial Convolution (PConv) modules, which reduces the amount of network computation and improves the network detection speed; add Coordinate Attention (CA) to enhance the ability of extracting the positional features of tiny defects in fabrics; reconfiguration of the SPPCSPC module to improve small target detection; optimization of Bidirectional Feature Pyramid Network (BiFPN) and design of Tiny- BiFPN for simple and fast multi-scale feature fusion; finally, a novel loss function SIoU with angular loss is introduced to facilitate the fitting of the true and predicted frames and enhance the accuracy of defect prediction. The results show that the algorithm achieves a mAP value of 94.4% on the detection of defects in solid-colored fabrics of six denim materials, which is an improvement of 15.1% compared to the original YOLOv7 algorithm, while the model achieves a frame rate of 59.5 per second. Compared with other traditional deep learning algorithms SSD and Faster-RCNN, the detection accuracies are improved by 21.6% and 15.2%, and the FPS values are improved by 78.1% and 101.0%, respectively. Therefore, the YOLOv7-PCBS fabric defect detection algorithm proposed in this paper makes the fabric defect detection results more accurate while realizing lightweight, which provides an important technical reference for the subsequent improvement of textile quality.

On-Line Measurement of Tracking Poses of Heliostats in Concentrated Solar Power Plants.

The tracking pose of heliostats directly affects the stability and working efficiency of concentrated solar power (CSP) plants. Due to occlusion, over-exposure, and uneven illumination caused by mirror reflection, traditional image processing algorithms showed poor performances on the detection and segmentation of heliostats, which impede vision-based 3D measurement of tracking poses of heliostats. To tackle this issue, object detection using deep learning neural networks are exploited. An improved neural network based on YOLO-v5 framework has been designed to solve the on-line detection problem of heliostats. The model achieves a recognition accuracy of 99.7% for the test set, outperforming traditional methods significantly. Based on segmented results, the corner points of each heliostat are found out using Hough Transform and line intersection methods. The 3D poses of each heliostat are then solved out based on the image coordinates of specific feature points and the camera model. Experimental and field test results demonstrate the feasibility of this hybrid approach, which provides a low-cost solution for the monitoring and measurement of tracking poses of the heliostats in CSP.

A globally sampled high-resolution hand-labeled validation dataset for evaluating surface water extent maps

Abstract. Effective monitoring of global water resources is increasingly critical due to climate change and population growth. Advancements in remote sensing technology, specifically in spatial, spectral, and temporal resolutions, are revolutionizing water resource monitoring, leading to more frequent and high-quality surface water extent maps using various techniques such as traditional image processing and machine learning algorithms. However, satellite imagery datasets contain trade-offs that result in inconsistencies in performance, such as disparities in measurement principles between optical (e.g., Sentinel-2) and radar (e.g., Sentinel-1) sensors and differences in spatial and spectral resolutions among optical sensors. Therefore, developing accurate and robust surface water mapping solutions requires independent validations from multiple datasets to identify potential biases within the imagery and algorithms. However, high-quality validation datasets are expensive to build, and few contain information on water resources. For this purpose, we introduce a globally sampled, high-spatial-resolution dataset labeled using 3 m PlanetScope imagery (Planet Team, 2017). Our surface water extent dataset comprises 100 images, each with a size of 1024×1024 pixels, which were sampled using a stratified random sampling strategy covering all 14 biomes. We highlighted urban and rural regions, lakes, and rivers, including braided rivers and coastal regions. We evaluated two surface water extent mapping methods using our dataset – Dynamic World (Brown et al., 2022), based on Sentinel-2, and the NASA IMPACT model (Paul and Ganju, 2021), based on Sentinel-1. Dynamic World achieved a mean intersection over union (IoU) of 72.16 % and F1 score of 79.70 %, while the NASA IMPACT model had a mean IoU of 57.61 % and F1 score of 65.79 %. Performance varied substantially across biomes, highlighting the importance of evaluating models on diverse landscapes to assess their generalizability and robustness. Our dataset can be used to analyze satellite products and methods, providing insights into their advantages and drawbacks. Our dataset offers a unique tool for analyzing satellite products, aiding the development of more accurate and robust surface water monitoring solutions. The dataset can be accessed via https://doi.org/10.25739/03nt-4f29 (Mukherjee et al., 2024).

Indicator and sign recognition in real electricity scenario

Abstract A multitude of instruments and equipment are contained within the electricity scenario, and their operation leads to fluctuations in a wide range of parameters. These changes are typically represented through indicators and signs. This study introduces an efficient and robust method for recognizing these indicators and signs, utilizing a variety of image processing techniques, including the computation of image mean and variance, as well as template matching. Given the plethora of indicators and signs present on substation equipment, it is crucial to discern the illumination status of indicators at different locations and relay this information to the system based on the indicator’s significance. Considering the indoor setting, which is relatively uncomplicated, this study employs the variance and mean of the indicator area image for judgment. As for identifiers, which often vary in shape and color, this study uses template matching for identification, subsequently reporting the operational status of the equipment marked by this area. Experimental results demonstrate that compared to deep learning methods, traditional image processing algorithms yield superior outcomes while significantly reducing computational costs and time.

A Method for Extracting Joints on Mountain Tunnel Faces Based on Mask R-CNN Image Segmentation Algorithm

The accurate distribution of joints on the tunnel face is crucial for assessing the stability and safety of surrounding rock during tunnel construction. This paper introduces the Mask R-CNN image segmentation algorithm, a state-of-the-art deep learning model, to achieve efficient and accurate identification and extraction of joints on tunnel face images. First, digital images of tunnel faces were captured and stitched, resulting in 286 complete images suitable for analysis. Then, the joints on the tunnel face were extracted using traditional image processing algorithms, the commonly used U-net image segmentation model, and the Mask R-CNN image segmentation model introduced in this paper to address the lack of recognition accuracy. Finally, the extraction results obtained by the three methods were compared. The comparison results show that the joint extraction method based on the Mask R-CNN image segmentation deep learning model introduced in this paper achieved the best joint extraction effect with a Dice similarity coefficient of 87.48%, outperforming traditional methods and the U-net model, which scored 60.59% and 75.36%, respectively, realizing accurate and efficient acquisition of tunnel face rock joints. These findings suggest that the Mask R-CNN model can be effectively implemented in real-time monitoring systems for tunnel construction projects.

A method for cabbage root posture recognition based on YOLOv5s

Efficient, non-destructive cabbage harvesting is crucial for preserving its flavor and quality. Current cabbage harvesting mainly relies on mechanized automatic picking methods. However, a notable deficiency in most existing cabbage harvesting devices is the absence of a root posture recognition system to promptly adjust the root posture, consequently impacting the accuracy of root cutting during harvesting. To address this issue, this study introduces a cabbage root posture recognition method that combines deep learning with traditional image processing algorithms. Preliminary detection of the main root Region of Interest (ROI) areas of the cabbage is carried out through the YOLOv5s deep learning model. Subsequently, traditional image processing methods, the Graham algorithm, and the method of calculating the minimum circumscribed rectangle are employed to specifically detect the inclination angle of cabbage roots. This approach effectively addresses the difficulty in calculating the inclination angle of roots caused by occlusion from outer leaves. The results demonstrate that the precision and recall of this method are 98.7 % and 98.6 %, respectively, with an average absolute error of 0.80° and an average relative error of 1.34 % in posture. Using this method as a reference for mechanical harvesting can effectively mitigate cabbage damage rates.

Enhancing museum experience through deep learning and multimedia technology

Amidst the swift progression of artificial intelligence (AI) technology, the museum sector has witnessed a notable inclination towards its adoption. This manuscript endeavours to amplify the interactive milieu of contemporary museum patrons by amalgamating a deep learning algorithm with multimedia technology. The crux of our investigation is the exploration of an adaptive convolutional neural network (CNN) to enrich the interactive engagement of museum visitors. Initially, we leverage the adaptive CNN for the image recognition chore pertaining to museum artifacts and exhibits, thereby facilitating automatic recognition and categorization. Furthermore, to surmount the constraints of conventional pooling algorithms in image feature extraction, we suggest an adaptive pooling algorithm, grounded in the maximum pooling algorithm paradigm. Subsequently, multimedia algorithms are amalgamated into the interactive apparatus, enabling visitors to immerse in exhibits and avail more profound information and experiences. Through juxtaposition with traditional image processing algorithms, the efficacy of our proposed algorithm within a museum ambiance is assessed. Experimental outcomes evince that our algorithm attains superior accuracy and robustness in artifact identification and classification endeavours. In comparison to alternative algorithms, our methodology furnishes more precise and comprehensive displays and interpretations, accurately discerning and categorizing a myriad of exhibit types. This research unveils innovative notions for the digital metamorphosis and advancement of modern museums. Through the incorporation of avant-garde deep learning algorithms and multimedia technologies, the museum visitor experience is elevated, proffering more enthralling and interactive displays. The elucidations of this manuscript hold substantial merit for the continual evolution and innovation within the museum industry.

P‐236: Late‐News Poster: Hard defect detection and classification for display panel products

Hard defect of display panel such as crack or chipping is one of the most critical defects that have fatal impacts on the product. Conventional deep‐learning‐based methods have difficulties in equipment control in practical point of view due to the vastness of training data and numerous parameters. Consequently, more simple and robust machine‐learning models jointly with traditional image processing algorithms with small number of parameters are increasingly required for the maintenance of inspection equipment. To resolve the issue, we proposed a novel image processing and decision tree classification algorithm that can be operated using smaller number of parameters than deep‐learning method. Firstly, panel image is fed into proposed image processing algorithm and converted into feature map to highlight the hard defect. After binary thresholding of the image, remaining pixels are specified as bounding box. Subsequently, features are extracted in the bounding box followed by classification into normal/defective panel. Additional RANSAC‐based outer edge inspection algorithm is processed. We conducted an experimental study using manufacturing data, and showed successful performance in hard defect detection and classification.

Scaled aggregation operations over three-dimensional extended intuitionistic fuzzy index matrices

Modern image processing techniques are improving beyond old methods, which include advanced approaches, for example deep learning. Convolutional Neural Networks (CNNs) are excellent at automatic feature extraction, whereas Generative Adversarial Networks (GANs) produce realistic images. Transfer learning uses pre-trained models, whereas semantic segmentation identifies pixels in images. Super-resolution, style transfer, and attention mechanisms can increase the quality of images and understanding. Adversarial defenses address purposeful manipulations, while 3D image processing handles three-dimensional data. These advancements make use of improved computational power and massive datasets to revolutionize image processing capabilities. Traditional image processing algorithms frequently fail to handle the complex and multidimensional structure of color images, particularly when dealing with uncertainty and imprecision. In this study, the 3D-EIFIM frame work is extented and scaled aggregation operations 3D-EIFIM tailored for image data are proposed. By representing each pixel as an entry of 3D-EIFIM and applying aggregation techniques to enable more effective image analysis, manipulation, and enhancement. The practical implications of this research are significant, as it can lead to advancements in fields such as computer vision, medical imaging, and remote sensing.

Evaluation of the corneal topography based on deep learning.

The current study designed a unique type of corneal topography evaluation method based on deep learning and traditional image processing algorithms. The type of corneal topography of patients was evaluated through the segmentation of important medical zones and the calculation of relevant medical indicators of orthokeratology (OK) lenses. The clinical data of 1,302 myopic subjects was collected retrospectively. A series of neural network-based U-Net was used to segment the pupil and the treatment zone in the corneal topography, and the decentration, effective defocusing contact range, and other indicators were calculated according to the image processing algorithm. The type of corneal topography was evaluated according to the evaluation criteria given by the optometrist. Finally, the method described in this article was used to evaluate the type of corneal topography and compare it with the type classified by the optometrist. When the important medical zones in the corneal topography were segmented, the precision and recall of the treatment zone reached 0.9587 and 0.9459, respectively, and the precision and recall of the pupil reached 0.9771 and 0.9712. Finally, the method described in this article was used to evaluate the type of corneal topography. When the reviewed findings based on deep learning and image processing algorithms were compared to the type of corneal topography marked by the professional optometrist, they demonstrated high accuracy with more than 98%. The current study provided an effective and accurate deep learning algorithm to evaluate the type of corneal topography. The deep learning algorithm played an auxiliary role in the OK lens fitting, which could help optometrists select the parameters of OK lenses effectively.

Quantitative analysis of the effect of illumination variations on image processing in machine vision inspection

Abstract When unavoidable light, age, expression, and gesture changes occur, the machine vision detection accuracy will be greatly reduced, especially the light change impact on image processing. Combining the reflection equation and frequency domain analysis to construct a light change model based on spherical harmonic function and process the image from four directions, namely, digital image conversion, median filtering, sharpening processing, and image global segmentation. Aiming at the shortcomings of traditional image processing algorithms, the light compensation based on the improved pulse-coupled neural network model is proposed, and the model is used to analyze the impact of light changes on image processing. Despite the changes in light conditions, this algorithm maintains above 0.95 in each subset and has the best overall performance, as shown by the results. When the light intensity is less than 41.88kLux, using the optimal threshold for background segmentation of adult green peppers with respect to a fixed threshold T=0.3 results in a significant reduction of the background segmentation error. When the light intensity is greater than 41.88kLux, the superiority of the optimal threshold is not obvious. The results of this research not only have a significant role in promoting the development of the field of computer vision but also can provide people with convenient and efficient services in all aspects of social life.

Image feature extraction algorithm based on visual information

Abstract Vision is the main sensory organ for human beings to contact and understand the objective world. The results of various statistical data show that more than 60% of all ways for human beings to obtain external information are through the visual system. Vision is of great significance for human beings to obtain all kinds of information needed for survival, which is the most important sense of human beings. The rapid growth of computer technology, image processing, pattern recognition, and other disciplines have been widely applied. Traditional image processing algorithms have some limitations when dealing with complex images. To solve these problems, some scholars have proposed various new methods. Most of these methods are based on statistical models or artificial neural networks. Although they meet the requirements of modern computer vision systems for feature extraction algorithms with high accuracy, high speed, and low complexity, these algorithms still have many shortcomings. For example, many researchers have used different methods for feature extraction and segmentation to get better segmentation results. Scale-invariant feature transform (SIFT) is a description used in the field of image processing. This description has scale invariance and can detect key points in the image. It is a local feature descriptor. A sparse coding algorithm is an unsupervised learning method, which is used to find a set of “super complete” basis vectors to represent sample data more efficiently. Therefore, combining SIFT and sparse coding, this article proposed an image feature extraction algorithm based on visual information to extract image features. The results showed that the feature extraction time of X algorithm for different targets was within 0.5 s when the other conditions were the same. The feature matching time was within 1 s, and the correct matching rate was more than 90%. The feature extraction time of Y algorithm for different targets was within 2 s. The feature matching time was within 3 s, and the correct matching rate was between 80 and 90%, indicating that the recognition effect of X algorithm was better than that of Y algorithm. It indicates the positive relationship between visual information and image feature extraction algorithm.

Image Processing Algorithm Design of Agricultural Internet of Things Platform Based on Big Data Analysis

Abstract To solve the problems of low signal to noise ratio (SNR), poor processing effect, and long processing times for traditional image processing algorithms, an image processing algorithm for the agricultural Internet of Things platform based on big data analysis was designed. The big data analysis method was used for agricultural low-quality image recognition, and the Internet of Things platform uses sparse representation and a complete dictionary of low-quality image denoising processing with an improved histogram equalization method to enhance the image denoising result and get a high-quality image. Through this, the image processing algorithm design of the agricultural Internet of Things platform was completed. Experimental results show that the algorithm has high SNR and a good image processing effect, and the image processing time is always below 0.7 s, which meets research expectations.

Plume detection and emission estimate for biomass burning plumes from TROPOMI carbon monoxide observations using APE v1.1

Abstract. This paper presents the automated plume detection and emission estimation algorithm (APE), developed to detect CO plumes from isolated biomass burning events and to quantify the corresponding CO emission rate. APE uses the CO product of the Tropospheric Monitoring Instrument (TROPOMI) on board the Copernicus Sentinel-5 Precursor (S5P) satellite, launched in 2017, and collocated active fire data from the Visible Infrared Imaging Radiometer Suite (VIIRS), the latter flying 3 min ahead of S5P. After identifying appropriate fire events using VIIRS data, an automated plume detection algorithm based on traditional image processing algorithms selects plumes for further data interpretation. The approach is based on thresholds optimized for data over the United States in September 2020. Subsequently, the CO emission rate is estimated using the cross-sectional flux method, which requires horizontal wind fields at the plume height. Three different plume heights were considered, and the ECMWF Reanalysis v5 (ERA5) data were used to compute emissions. A varying plume height in the downwind direction based on three-dimensional Lagrangian simulation was considered appropriate. APE is verified for observations over Australia and Siberia. For all fire sources identified by VIIRS, only 16 % of the data corresponded to clear-sky TROPOMI CO data with plume signature. Furthermore, the quality filters of APE resulted in emission estimations for 26 % of the TROPOMI CO data with plume signatures. Visual filtering of the APE's output showed a true-positive confidence level of 97.7 %. Finally, we provide an estimate of the emission uncertainties. The greatest contribution of error comes from the uncertainty in Global Fire Assimilation System (GFAS) injection height that leads to emission errors <100 %, followed by systematic errors in the ERA5 wind data. The assumption of constant emission during plume formation and spatial under-sampling of CO column concentration by TROPOMI yields an error of <20 %. The randomized errors from the ensemble ERA5 wind data are found to be less than 20 % for 97 % of the cases.

Fully automatic deep learning-based lung parenchyma segmentation and boundary correction in thoracic CT scans.

The proposed work aims to develop an algorithm to precisely segment the lung parenchyma in thoracic CT scans. To achieve this goal, the proposed technique utilized a combination of deep learning and traditional image processing algorithms. The initial step utilized a trained convolutional neural network (CNN) to generate preliminary lung masks, followed by the proposed post-processing algorithm for lung boundary correction. First, the proposed method trained an improved 2D U-Net CNN model with Inception-ResNet-v2 as its backbone. The model was trained on 32 CT scans from two different sources: one from the VESSEL12 grand challenge and the other from AIIMS Delhi. Further, the model's performance was evaluated on a test dataset of 16 CT scans with juxta-pleural nodules obtained from AIIMS Delhi and the LUNA16 challenge. The model's performance was assessed using evaluation metrics such as average volumetric dice coefficient (DSCavg), average IoU score (IoUavg), and average F1 score (F1avg). Finally, the proposed post-processing algorithm was implemented to eliminate false positives from the model's prediction and to include juxta-pleural nodules in the final lung masks. The trained model reported a DSCavg of 0.9791 ± 0.008, IoUavg of 0.9624 ± 0.007, and F1avg of 0.9792 ± 0.004 on the test dataset. Applying the post-processing algorithm to the predicted lung masks obtained a DSCavg of 0.9713 ± 0.007, IoUavg of 0.9486 ± 0.007, and F1avg of 0.9701 ± 0.008. The post-processing algorithm successfully included juxta-pleural nodules in the final lung mask. Using a CNN model, the proposed method for lung parenchyma segmentation produced precise segmentation results. Furthermore, the post-processing algorithm addressed false positives and negatives in the model's predictions. Overall, the proposed approach demonstrated promising results for lung parenchyma segmentation. The method has the potential to be valuable in the advancement of computer-aided diagnosis (CAD) systems for automatic nodule detection.

A Recipe for Unbiased Background Modeling in Deep Wide-field Astronomical Images

Unbiased sky background modeling is crucial for the analysis of deep wide-field images, but it remains a major challenge in low surface brightness astronomy. Traditional image processing algorithms are often designed to produce artificially flat backgrounds, erasing astrophysically meaningful structures. In this paper, we present three ideas that can be combined to produce wide-field astronomical data that preserve accurate representations of the background sky: (1) Use of all-sky infrared/submillimeter data to remove the large-scale time-varying components while leaving the scattered light from Galactic cirrus intact, with the assumptions of (a) the underlying background has little power on small scales, and (b) the Galactic cirrus in the field is optically thin on large scales; (2) Censoring of frames contaminated by anomalously prominent wings in the wide-angle point-spread function; and (3) Incorporation of spatial covariance in image stacking that controls the local background consistency. We demonstrate these methods using example data sets obtained with the Dragonfly Telephoto Array, but these general techniques are prospective to be applied to improve sky models in data obtained from other wide-field imaging surveys, including those from the upcoming Vera Rubin Telescope.

A Deep Neural Network-Based Intelligent Detection Model for Manufacturing Defects of Automobile Parts

Image defect detection of casting parts is a key part of the production process in the machinery manufacturing industry. The traditional methods are ineffective because traditional computer image processing methods require a large number of manual features to be set artificially, and the detection time is too long. In order to save human resources and improve the efficiency of image defect detection, this paper proposes a deep learning-based defect detection method for automobile parts. This paper selects EfficientNetB0 as the backbone framework of the target detection network, which significantly reduces the memory usage of the model and shortens the model inference time, while improving the model detection accuracy. Facing the problem of small samples of defect image dataset, we analyze the image characteristics of the dataset and introduce shape transformation and scale scaling as the basic online data enhancement method according to the industrial field image projection law. Then, it is expected to combine the traditional image processing algorithms according to the characteristics of casting parts with different depth distribution and multiple morphological changes, and develop a special image defect data enhancement method. This further improves the performance of the model and increases the detection accuracy of the algorithm by 22.3% without increasing the data.

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy.

This paper investigates the impact of the amount of training data and the shape variability on the segmentation provided by the deep learning architecture U-Net. Further, the correctness of ground truth (GT) was also evaluated. The input data consisted of a three-dimensional set of images of HeLa cells observed with an electron microscope with dimensions 8192×8192×517. From there, a smaller region of interest (ROI) of 2000×2000×300 was cropped and manually delineated to obtain the ground truth necessary for a quantitative evaluation. A qualitative evaluation was performed on the 8192×8192 slices due to the lack of ground truth. Pairs of patches of data and labels for the classes nucleus, nuclear envelope, cell and background were generated to train U-Net architectures from scratch. Several training strategies were followed, and the results were compared against a traditional image processing algorithm. The correctness of GT, that is, the inclusion of one or more nuclei within the region of interest was also evaluated. The impact of the extent of training data was evaluated by comparing results from 36,000 pairs of data and label patches extracted from the odd slices in the central region, to 135,000 patches obtained from every other slice in the set. Then, 135,000 patches from several cells from the 8192×8192 slices were generated automatically using the image processing algorithm. Finally, the two sets of 135,000 pairs were combined to train once more with 270,000 pairs. As would be expected, the accuracy and Jaccard similarity index improved as the number of pairs increased for the ROI. This was also observed qualitatively for the 8192×8192 slices. When the 8192×8192 slices were segmented with U-Nets trained with 135,000 pairs, the architecture trained with automatically generated pairs provided better results than the architecture trained with the pairs from the manually segmented ground truths. This suggests that the pairs that were extracted automatically from many cells provided a better representation of the four classes of the various cells in the 8192×8192 slice than those pairs that were manually segmented from a single cell. Finally, the two sets of 135,000 pairs were combined, and the U-Net trained with these provided the best results.

An Approach for Classification of Alzheimer’s Disease Using Deep Neural Network and Brain Magnetic Resonance Imaging (MRI)

Alzheimer’s disease (AD) is a deadly cognitive condition in which people develop severe dementia symptoms. Neurologists commonly use a series of physical and mental tests to diagnose AD that may not always be effective. Damage to brain cells is the most significant physical change in AD. Proper analysis of brain images may assist in the identification of crucial bio-markers for the disease. Because the development of brain cells is so intricate, traditional image processing algorithms sometimes fail to perceive important bio-markers. The deep neural network (DNN) is a machine learning technique that helps specialists in making appropriate decisions. In this work, we used brain magnetic resonance scans to implement some commonly used DNN models for AD classification. According to the classification results, where the average of multiple metrics is observed, which includes accuracy, precision, recall, and an F1 score, it is found that the DenseNet-121 model achieved the best performance (86.55%). Since DenseNet-121 is a computationally expensive model, we proposed a hybrid technique incorporating LeNet and AlexNet that is light weight and also capable of outperforming DenseNet. To extract important features, we replaced the traditional convolution Layers with three parallel small filters (1×1,3×3, and 5×5). The model functions effectively, with an overall performance rate of 93.58%. Mathematically, it is observed that the proposed model generates significantly fewer convolutional parameters, resulting in a lightweight model that is computationally effective.