Subsequent Feature Extraction Research Articles

Deep Learning Algorithm-Based Appearance Detection of Cigarette Strip Packs

Each local feature in the appearance image of cigarette packs is a key element to reflect the corresponding brand information. If only a single convolutional neural network is used, the context information of sequence data may be lost, resulting in an insufficient grasp of the overall information. In order to realize the deep-level feature extraction of the appearance of cigarette packs and realize the appearance detection of cigarette packs with higher accuracy and speed, a new method for the appearance detection of cigarette packs was proposed by combining the convolutional neural network and the cyclic neural network methods in the deep learning algorithm. The image acquisition card is used to collect the appearance images of cigarette packs, and contrast enhancement and rotation correction are performed on the collected images to effectively improve their quality and provide a good guarantee for subsequent feature extraction and detection. The preprocessed cigarette package image is input into the convolutional neural network to realize the deep-level feature extraction of the cigarette package appearance image. The cigarette package appearance features’ output from the convolutional neural network is input into the short-term and long-term memory unit, as well as the gate-controlled cyclic unit, of the corresponding recurrent neural network, in order to process time sequence information based on the efficient extraction of details from the image, retain the sequence and context information of the input data, and ultimately achieve accurate detection of the cigarette package appearance. Through experimental analysis, this method can effectively identify the appearance defects of cigarette packs, mark them immediately, and present them in an intuitive way, so that staff can quickly locate the problem and take corresponding measures. The method can detect appearance defects larger than [Formula: see text] with high accuracy. For various appearance defects, the detection rate can be guaranteed to be over 98%, providing strong support for quality control and product upgrading in the tobacco industry.

UNIFIED MULTIMODAL BIOMETRICS FUSION USING DEEP LEARNING FOR SECURING IOT

Advancements in multimodal biometrics, which amalgamate multiple biometric traits, hold promise for augmenting the accuracy and robustness of biometric identification systems. The focal point of this innovative study is the enhancement of multimodal biometrics identification, using face and iris images as the key biometric traits. This work taps into the expansive collection of face and iris images present in the WVU-Multimodal dataset for evaluation purposes. Our proposed approach employs “Convolutional Neural Network (CNN)” architectures, notable for their efficacy in computer vision tasks, to extract potent discriminative features from the input images. This work specifically incorporates three popular CNN architectures: ResNet-50, InceptionNet, XceptionNet, and fine-tuned CNN. To amalgamate the extracted features, investigate various fusion techniques in the security-centric industry: early fusion, and score-level fusion. Early fusion is an approach that merges the raw images of both face and iris at the input level to a single CNN model. Use the Gabor approach to enhance the image's quality and make the face and iris information more visible. This technique modifies the histogram equalization process for local regions, thus enabling better visibility and subsequent feature extraction. Our experimental evaluation employs performance metrics like accuracy, “Equal Error Rate”, and “Receiver Operating Characteristic” curves. In this work undertakes a comparative analysis to appraise the performance of the different CNN architectures and fusion techniques under scrutiny.

MT-SCnet: multi-scale token divided and spatial-channel fusion transformer network for microscopic hyperspectral image segmentation.

Hybrid architectures based on convolutional neural networks and Transformers, effectively captures both the local details and the overall structural context of lesion tissues and cells, achieving highly competitive segmentation results in microscopic hyperspectral image (MHSI) segmentation tasks. However, the fixed tokenization schemes and single-dimensional feature extraction and fusion in existing methods lead to insufficient global feature extraction in hyperspectral pathology images. Base on this, we propose a multi-scale token divided and spatial-channel fusion transformer network (MT-SCnet) for MHSIs segmentation. Specifically, we first designed a Multi-Scale Token Divided module. It divides token at different scale based on mirror padding and promotes information interaction and fusion between different tokens to obtain more representative features for subsequent global feature extraction. Secondly, a novel spatial channel fusion transformer was designed to capture richer features from spatial and channel dimensions, and eliminates the semantic gap between features from different dimensions based on cross-attention fusion block. Additionally, to better restore spatial information, deformable convolutions were introduced in decoder. The Experiments on two MHSI datasets demonstrate that MT-SCnet outperforms the comparison methods. This advance has significant implications for the field of MHSIs segmentation. Our code is freely available at https://github.com/sharycao/MT-SCnet.

SINGLE-CYCLE PULSE WAVEFORM RECOGNITION METHOD BASED ON SVM

The single-cycle pulse waves’ morphological characteristics can reflect rich physiological and pathological information about the human cardiovascular system, playing an important role in continuous blood pressure monitoring and cardiovascular disease risk warning. Pulse signals belong to weak physiological signals, and the acquisition process is easily affected by factors such as adjacent channel interference and motion artifacts, leading to abnormal cycles and affecting subsequent feature extraction. Therefore, based on support vector machines (SVM), a single-cycle pulse waveform recognition algorithm is proposed. Using a multi-channel pulse wave acquisition device to collect radial artery pulse signals from 150 subjects. Preprocess the signal to obtain a single-cycle pulse waveform. A total of 54 frequency domain and time-frequency domain feature parameters were extracted by using Fourier transform and wavelet transform to extract the frequency domain and time-frequency domain features. Use the principal components analysis (PCA) method to reduce parameter dimensions. Using the SVM for model training to achieve the classification of single-cycle effective pulse signals, pseudo noise and interference signals. The results show that the algorithm’s classification accuracy is 97.42%, indicating that the algorithm can effectively identify pulse signals, pseudo noise and interference signals, laying the foundation for modeling and suppressing interference signals in the next step.

Harnessing AI for precision tonsillitis diagnosis: a revolutionary approach in endoscopic analysis.

Diagnosing and treating tonsillitis pose no significant challenge for otolaryngologists; however, it can increase the infection risk for healthcare professionals amidst the coronavirus pandemic. In recent years, with the advancement of artificial intelligence (AI), its application in medical imaging has also thrived. This research is to identify the optimal convolutional neural network (CNN) algorithm for accurate diagnosis of tonsillitis and early precision treatment. Semi-supervised learning with pseudo-labels used for self-training was adopted to train our CNN, with the algorithm including UNet, PSPNet, and FPN. A total of 485 pharyngoscopic images from 485 participants were included, comprising healthy individuals (133 cases), patients with the common cold (295 cases), and patients with tonsillitis (57 cases). Both color and texture features from 485 images are extracted for analysis. UNet outperformed PSPNet and FPN in accurately segmenting oropharyngeal anatomy automatically, with average Dice coefficient of 97.74% and a pixel accuracy of 98.12%, making it suitable for enhancing the diagnosis of tonsillitis. The normal tonsils generally have more uniform and smooth textures and have pinkish color, similar to the surrounding mucosal tissues, while tonsillitis, particularly the antibiotic-required type, shows white or yellowish pus-filled spots or patches, and shows more granular or lumpy texture in contrast, indicating inflammation and changes in tissue structure. After training with 485 cases, our algorithm with UNet achieved accuracy rates of 93.75%, 97.1%, and 91.67% in differentiating the three tonsil groups, demonstrating excellent results. Our research highlights the potential of using UNet for fully automated semantic segmentation of oropharyngeal structures, which aids in subsequent feature extraction, machine learning, and enables accurate AI diagnosis of tonsillitis. This innovation shows promise for enhancing both the accuracy and speed of tonsillitis assessments.

Spatial Feature Enhancement and Attention-Guided Bidirectional Sequential Spectral Feature Extraction for Hyperspectral Image Classification

Hyperspectral images have the characteristics of high spectral resolution and low spatial resolution, which will make the extracted features insufficient and lack detailed information about ground objects, thus affecting the accuracy of classification. The numerous spectral bands of hyperspectral images contain rich spectral features but also bring issues of noise and redundancy. To improve the spatial resolution and fully extract spatial and spectral features, this article proposes an improved feature enhancement and extraction model (IFEE) using spatial feature enhancement and attention-guided bidirectional sequential spectral feature extraction for hyperspectral image classification. The adaptive guided filtering is introduced to highlight details and edge features in hyperspectral images. Then, an image enhancement module composed of two-dimensional convolutional neural networks is used to improve the resolution of the image after adaptive guidance filtering and provide a high-resolution image with key features emphasized for the subsequent feature extraction module. The proposed spectral attention mechanism helps to extract more representative spectral features, emphasizing useful information while suppressing the interference of noise. Experimental results show that our method outperforms other comparative methods even with very few training samples.

Mathematical Modelling for Neural Network-Based Textural Feature Extraction from Normalized Ocular Images for Improved Biometric Authentication

Biometric authentication systems have become increasingly prevalent in security and identity verification applications. Among various biometric traits, the ocular region, specifically the iris, offers a unique and stable source for individual identification. The intricate patterns within the iris are highly distinctive and remain consistent over a person's lifetime, making them ideal for biometric applications. In the field of biometric authentication, the ocular region has emerged as a robust and reliable source for identity verification due to its unique and stable features. This study focuses on enhancing the accuracy of biometric systems through neural network-based textural feature extraction from normalized ocular images. The proposed approach utilizes Mask Image Extraction (Hough circle) and an efficient U-Net model to achieve superior performance in biometric authentication. Initially, the ocular images are pre-processed to normalize lighting and orientation, ensuring consistency across the dataset. Mask Image Extraction, particularly using the Hough circle transform, is employed to isolate the region of interest (ROI) within the ocular images. This method accurately detects and segments the circular iris region, which is crucial for subsequent feature extraction. The core of the proposed system is the Efficient U-Net model, a variant of the standard U-Net architecture designed for enhanced efficiency and accuracy. The U-Net model is trained to extract intricate textural features from the segmented ocular regions. By leveraging its encoder-decoder structure, the U-Net captures both local and global features, resulting in a detailed and discriminative representation of the ocular texture. Experimental results demonstrate that the integration of Mask Image Extraction and the Efficient U-Net model significantly improves the accuracy of biometric authentication systems. The proposed method outperforms traditional approaches by providing more precise and reliable feature extraction, thereby enhancing the overall robustness and reliability of ocular-based biometric systems.

Self-Supervised Image Denoising of Third Harmonic Generation Microscopic Images of Human Glioma Tissue by Transformer-Based Blind Spot (TBS) Network.

Third harmonic generation (THG) microscopy shows great potential for instant pathology of brain tumor tissue during surgery. However, due to the maximal permitted exposure of laser intensity and inherent noise of the imaging system, the noise level of THG images is relatively high, which affects subsequent feature extraction analysis. Denoising THG images is challenging for modern deep-learning based methods because of the rich morphologies contained and the difficulty in obtaining the noise-free counterparts. To address this, in this work, we propose an unsupervised deep-learning network for denoising of THG images which combines a self-supervised blind spot method and a U-shape Transformer using a dynamic sparse attention mechanism. The experimental results on THG images of human glioma tissue show that our approach exhibits superior denoising performance qualitatively and quantitatively compared with previous methods. Our model achieves an improvement of 2.47-9.50 dB in SNR and 0.37-7.40 dB in CNR, compared to six recent state-of-the-art unsupervised learning models including Neighbor2Neighbor, Blind2Unblind, Self2Self+, ZS-N2N, Noise2Info and SDAP. To achieve an objective evaluation of our model, we also validate our model on public datasets including natural and microscopic images, and our model shows a better denoising performance than several recent unsupervised models such as Neighbor2Neighbor, Blind2Unblind and ZS-N2N. In addition, our model is nearly instant in denoising a THG image, which has the potential for real-time applications of THG microscopy.

An Algorithm for Initial Localization of Feature Waveforms Based on Differential Analysis Parameter Setting and Its Application in Clinical Electrocardiograms

In a biological signal analysis system, signals of the same type may exhibit significant variations in their feature waveforms. Biological signals are typically weak, which increases the complexity of their analysis. Furthermore, clinical biomedical signals are susceptible to various interferences from the human body itself, including muscle movements, respiration, and heartbeat. These interference factors further escalate the complexity and difficulty of signal analysis. Therefore, precise and targeted preprocessing is often required before analyzing these clinical biomedical signals to enhance the accuracy and reliability of subsequent feature extraction and classification. Here, we have established an effective and practical algorithm model that integrates preprocessing with the initial localization of target feature waveforms, achieving the following four objectives: 1. Determining the periodic positions of target feature waveforms. 2. Preserving the original amplitude and shape of target feature waveforms while eliminating negative interference. 3. Reducing or eliminating interference from other feature waveforms in the input signal. 4. Decreasing noise in the input signal, such as baseline drift, powerline interference, and muscle artifacts commonly found in biological signals. We have validated the algorithm on clinical electrocardiogram (ECG) data and the authoritative MIT-BIH open-source ECG database demonstrating its effectiveness and reliability.

Discrete Curvelet Transform Feature Extraction for Mangosteen Fruit Surface Damage Detection

Mangosteen (Garcinia mangostana L) is one of the commodities of Indonesian fruit and is used as an export primadona that became the basis of Indonesia to increase the currency of the country. The quality of the fruit can be seen from the surface, whether there is damage or not. The sorting that the farmers have been doing all this time is still using the conventional way, that is, with the sense of sight. This conventional method seems to be less effective because it takes a lot of energy, takes a long time, and there are different perceptions between farmers. To solve this problem, a method of surface quality extraction of mango fruit will be developed based on image processing. The initial stage of image processing is with the image size equation then the image is converted to grayscale mode, then a discrete curvelet transformation is performed. The next stage is the extraction of mean, energy, entropy, standard deviation, variance, sum, correlation, contrast, and homogeneity. The result of the subsequent feature extraction is used to enter a value at the classification stage. From some of these extractions it will be known which extraction has the highest accuracy value. The method of classification used is Linear Discriminant Analysis (LDA) with the method of K-Fold Cross Validation which in this study is divided into 4-fold cross validation. After testing on 120 images, the highest value of accuracy is with extraction of standard characteristics deviation of 91.7% and variance of 88.4%.

Adaptive denoising model for ship-radiated noise based on dynamic weighted filtering

Aiming at the problem of ship-radiated noise (S-N) denoising at low signal-to-noise ratio, adaptive denoising model for S-N based on dynamic weighted filtering is proposed. Firstly, improved variational mode decomposition with multi-strategy enhanced dung beetle optimizer (MEVMD) and the secondary MEVMD are proposed to deal with S-N which has the nonlinear and nonstationary characteristics. Secondly, density-based spatial clustering of applications with noise assisted by fluctuation dispersion entropy (FDBSCAN) is proposed to adaptively divide all modes into multiple groups according to the chaotic degree of the sequence. Finally, dynamic weighted filtering (DWF) is proposed to filter each group of mode components, and the final denoised signal is obtained through weighted reconstruction. The experiment of simulating chaotic signal proves the effectiveness of the proposed denoising model by seven evaluation indexes. The proposed denoising model has been verified in four kinds of S-N. It will contribute to the subsequent feature extraction and classification research for S-N.

Multi-channel and multi-featured extended orb with gabor filter and non-maximum suppression

This research paper presents an enhanced approach to feature extraction using the Oriented FAST and Rotated BRIEF (ORB) algorithm (Rublee et al., 2014). The proposed method leverages the power of Gabor filters (Mehrotra et al., 1992) in combination with Non-Maximum Suppression (Neuback and Van Gool, 2006) to improve the robustness and efficiency of feature detection in computer vision applications. The process begins with the acquisition of an RGB image, which is then transformed into seven single-channel images representing different color and intensity aspects: red, green, blue, hue, saturation, value, and grayscale. Each single-channel image is independently subjected to Gabor filtering, resulting in seven Gabor-filtered images. These images capture distinct texture and frequency information, enhancing the discriminative power of subsequent feature extraction. Subsequently, the Oriented FAST and Rotated BRIEF (ORB) algorithm is applied to each of the seven Gabor-filtered images to extract key points and descriptors. This step yields a comprehensive set of keypoints (Mallick et al., 2015) and descriptors, capturing rich local feature information across multiple image channels. To further refine the extracted features and eliminate redundant keypoints, Non-Maximum Suppression is employed independently on each single-channel image. This process effectively filters out overlapped and false keypoints, ensuring the selection of only the most salient features for downstream tasks. Experimental results demonstrate the efficacy of the proposed approach in improving feature detection performance compared to traditional methods. The combination of Gabor filtering and Non-Maximum Suppression enhances feature discriminability, robustness to noise, and resistance to image transformations, making it well-suited for various computer vision applications, including object recognition, image matching, and scene understanding.

Adaptive mask-based brain extraction method for head CT images.

Brain extraction is an important prerequisite for the automated diagnosis of intracranial lesions and determines, to a certain extent, the accuracy of subsequent lesion identification, localization, and segmentation. To address the problem that the current traditional image segmentation methods are fast in extraction but poor in robustness, while the Full Convolutional Neural Network (FCN) is robust and accurate but relatively slow in extraction, this paper proposes an adaptive mask-based brain extraction method, namely AMBBEM, to achieve brain extraction better. The method first uses threshold segmentation, median filtering, and closed operations for segmentation, generates a mask for the first time, then combines the ResNet50 model, region growing algorithm, and image properties analysis to further segment the mask, and finally complete brain extraction by multiplying the original image and the mask. The algorithm was tested on 22 test sets containing different lesions, and the results showed MPA = 0.9963, MIoU = 0.9924, and MBF = 0.9914, which were equivalent to the extraction effect of the Deeplabv3+ model. However, the method can complete brain extraction of approximately 6.16 head CT images in 1 second, much faster than Deeplabv3+, U-net, and SegNet models. In summary, this method can achieve accurate brain extraction from head CT images more quickly, creating good conditions for subsequent brain volume measurement and feature extraction of intracranial lesions.

Progressive Frequency-Guided Depth Model with Adaptive Preprocessing for Casting Defect Detection

This article proposes a progressive frequency domain-guided depth model with adaptive preprocessing to solve the problem of defect detection with weak features based on X-ray images. In distinct intuitive surface defect detection tasks, non-destructive testing of castings using X-rays presents more complex and weak defect features, leading to lower accuracy and insufficient robustness on the part of current casting defect detection methods. To address these challenges, the proposed method establishes four specialized mechanisms to improve model accuracy. First, an adaptive image contrast enhancement method is proposed to enhance the features of defects in casting images to promote subsequent feature extraction and prediction. Second, a subtle clue mining module based on frequency domain attention is proposed to fully extract the discriminative features of casting defects. Third, a feature refinement module based on progressive learning is proposed to achieve a balance between feature resolution and semantic information. Finally, a refined deep regression supervision mechanism is designed to improve defect detection accuracy under strict intersection-to-union ratio standards. We established extensive ablation studies using casting defect images in GDXray, conducted detailed comparative experiments with other methods, and performed experiments to analyze the robustness of the resulting models. Compared with other X-ray defect detection methods, our framework achieves an average +4.6 AP. Compared to the baseline, our proposed refined deep regression supervision mechanism results in an improvement of 5.3 AP.

Electromyography-Based Biomechanical Cybernetic Control of a Robotic Fish Avatar

This study introduces a cybernetic control and architectural framework for a robotic fish avatar operated by a human. The behavior of the robot fish is influenced by the electromyographic (EMG) signals of the human operator, triggered by stimuli from the surrounding objects and scenery. A deep artificial neural network (ANN) with perceptrons classifies the EMG signals, discerning the type of muscular stimuli generated. The research unveils a fuzzy-based oscillation pattern generator (OPG) designed to emulate functions akin to a neural central pattern generator, producing coordinated fish undulations. The OPG generates swimming behavior as an oscillation function, decoupled into coordinated step signals, right and left, for a dual electromagnetic oscillator in the fish propulsion system. Furthermore, the research presents an underactuated biorobotic mechanism of the subcarangiform type comprising a two-solenoid electromagnetic oscillator, an antagonistic musculoskeletal elastic system of tendons, and a multi-link caudal spine composed of helical springs. The biomechanics dynamic model and control for swimming, as well as the ballasting system for submersion and buoyancy, are deduced. This study highlights the utilization of EMG measurements encompassing sampling time and μ-volt signals for both hands and all fingers. The subsequent feature extraction resulted in three types of statistical patterns, namely, Ω,γ,λ, serving as inputs for a multilayer feedforward neural network of perceptrons. The experimental findings quantified controlled movements, specifically caudal fin undulations during forward, right, and left turns, with a particular emphasis on the dynamics of caudal fin undulations of a robot prototype.

Single-Cycle Pulse Signal Recognition Based on One-Dimensional Deep Convolutional Neural Network

Pulse signals carry comprehensive information regarding human cardiovascular physiology and pathology, providing a noninvasive and continuous method to assess cardiovascular health status in blood pressure monitoring. The blood pressure measurement method based on the pulse signal needs to extract the features of the single-cycle pulse signal, while the pulse signal pertains to the weak physiological signal of body surface. The acquisition process is susceptible to various factors leading to abnormal cycles, especially adjacent channel interference, affecting the subsequent feature extraction. To address this problem, this paper conducts an analysis of the formation mechanism of adjacent channel interference and proposes a single-cycle pulse signal recognition algorithm based on a one-dimensional deep convolutional neural network (1D-CNN) model. Radial pulse signals were collected from 150 subjects by pulse bracelet, and a dataset comprising 3446 single-cycle signals was extracted in total after denoising, single-cycle segmentation, and standardized preprocessing. The 1D-CNN model is trained to classify input signals into three categories: effective pulse signals, distortion, and interference signals. This classification is achieved by evaluating the waveform morphology of the signals within a single cycle. The results show that the overall classification accuracy of the algorithm on the test set is 98.26%, in which the classification accuracy of pulse waves is 99.8%, indicating that it can effectively recognize single-cycle pulse waves, which lays the foundation for subsequent continuous blood pressure measurement.

Enhancing Veracity: Empirical Evaluation of Fake News Detection Techniques

The relentless surge in the dissemination of fabricated news articles and misleading information poses a substantial threat to the veracity of information, trust in media sources, and the very foundations of democratic processes. In the contemporary landscape of information dissemination, the rampant propagation of false and misleading information has emerged as a paramount concern for both individuals and society at large. Consequently, the development of robust and efficient detection mechanisms has taken on a pivotal role in contemporary information ecosystems. The methodology employed encompasses three pivotal stages: initial data preprocessing, subsequent feature extraction involving the utilization of TF-IDF and Count Vectorization, and eventual classification that draws upon a diverse array of machine learning classifiers, in addition to deep learning models like Recurrent Neural Networks (RNN) and BERT networks. On a carefully selected dataset of instances of fake news, these models underwent rigorous testing and training. This research greatly aids in the continuous battle against disinformation by offering a methodical framework for identifying fake news. It also helps people and organisations make better decisions by shedding light on the relative merits of various deep learning and machine learning methods in this intricate and crucial context.

BILSTM-SimAM: An improved algorithm for short-term electric load forecasting based on multi-feature.

With the growing number of user-side resources connected to the distribution system, an occasional imbalance between the distribution side and the user side arises, making short-term power load forecasting technology crucial for addressing this issue. To strengthen the capability of load multi-feature extraction and improve the accuracy of electric load forecasting, we have constructed a novel BILSTM-SimAM network model. First, the entirely non-recursive Variational Mode Decomposition (VMD) signal processing technique is applied to decompose the raw data into Intrinsic Mode Functions (IMF) with significant regularity. This effectively reduces noise in the load sequence and preserves high-frequency data features, making the data more suitable for subsequent feature extraction. Second, a convolutional neural network (CNN) mode incorporates Dropout function to prevent model overfitting, this improves recognition accuracy and accelerates convergence. Finally, the model combines a Bidirectional Long Short-Term Memory (BILSTM) network with a simple parameter-free attention mechanism (SimAM). This combination allows for the extraction of multi-feature from the load data while emphasizing the feature information of key historical time points, further enhancing the model's prediction accuracy. The results indicate that the R2 of the BILSTM-SimAM algorithm model reaches 97.8%, surpassing mainstream models such as Transformer, MLP, and Prophet by 2.0%, 2.7%, and 3.6%, respectively. Additionally, the remaining error metrics also show a reduction, confirming the validity and feasibility of the method proposed.

Fundus Image Classification for the Early Detection of Issues in the DR for the Effective Disease Diagnosis

Diabetic Retinopathy and fundus images, “DR” could also refer to Digital Retinography, which involves the digital imaging of the retina. Digital retinography allows for the storage, retrieval, and transmission of retinal images for analysis and diagnosis. It plays a crucial role in screening for diabetic retinopathy and other eye diseases. The use of artificial intelligence and machine learning algorithms in the analysis of fundus images has gained traction in recent years. These technologies can assist healthcare professionals in the early detection and monitoring of diabetic retinopathy by analyzing patterns and abnormalities in the retinal images. This paper introduces a novel approach to image analysis, combining Local Semantic Object Feature Extraction (LsOFE) and Gray Level Co-occurrence Matrix (GLCM) metrics for robust object recognition and classification. The LsOFE process captures intricate local features, enhancing the representation of objects in images. The subsequent GLCM-based feature extraction provides detailed insights into texture characteristics. The final classification step, utilizing LsOFE features, demonstrates high precision, recall, and F1-Score for most images, showcasing the effectiveness of the proposed methodology. However, challenges are identified in the classification of specific images, suggesting areas for improvement and refinement. Overall, this research contributes a valuable framework for image processing, with the potential for broader applications in fields such as computer vision and pattern recognition. The results presented underscore the promising performance of the proposed approach, offering a foundation for further exploration and optimization in the realm of image analysis.

Soft X-ray image recognition and classification of maize seed cracks based on image enhancement and optimized YOLOv8 model

The current investigation on image recognition and internal crack detection of maize seeds primarily relies on visible light imaging. However, due to the low transmissivity of plant cells, even with image enhancement measures, the clarity of internal cracks in the images and the subsequent feature extraction process can be a trade-off. Soft X-rays possess exceptional penetration capability and offer better safety and convenience compared to hard X-rays, making them highly suitable for visualizing internal structures within plant tissues like maize seeds. In this paper, a non-invasive Imaging Technique for Image Enhancement is proposed, combining wavelet thresholding denoising, image standardization, bilateral filtering, and laplacian sharpening. This method is based on soft X-rays and successfully achieves image recognition of cracks present inside Zhengdan 958 maize seeds using an optimized YOLOv8 model. It effectively addresses challenges related to the limited light transmission of maize seeds, difficulty in crack localization, and algorithm generalization issues. The optimized YOLOv8 model demonstrates an average precision (AP) value that is 3.1% higher than that of the original model. Furthermore, by applying image enhancement, the AP value increases by 1.8%. The proposed method exhibits an average recognition accuracy of 99.66% for intact or broken seeds, an average precision of 99.87%, an average recognition recall of 99.48%, and an average single-frame image detection time of 7.49 ms in the single seed detection experiment.