Image Recognition Research Articles

Learning lightweight tea detector with reconstructed feature and dual distillation

Currently, image recognition based on deep neural networks has become the mainstream direction of research; therefore, significant progress has been made in its application in the field of tea detection. Many deep models exhibit high recognition rates in tea leaves detection. However, deploying these models directly on tea-picking equipment in natural environments is impractical; the extremely high parameters and computational complexity of these models make it challenging to perform real-time tea leaves detection. Meanwhile, lightweight models struggle to achieve competitive detection accuracy; therefore, this paper addresses the issue of computational resource constraints in remote mountain areas and proposes Reconstructed Feature and Dual Distillation (RFDD) to enhance the detection capability of lightweight models for tea leaves. In our method, the Reconstructed Feature selectively masks the feature of the student model based on the spatial attention map of the teacher model; it utilizes a generation block to force the student model to generate the teacher’s full feature. The Dual Distillation comprises Decoupled Distillation and Global Distillation. Decoupled Distillation divides the reconstructed feature into foreground and background features based on the Ground-Truth. This compels the student model to allocate different attention to foreground and background, focusing on their critical pixels and channels. However, Decoupled Distillation leads to the loss of relation knowledge between foreground and background pixels. Therefore, we further perform Global Distillation to extract this lost knowledge. Since RFDD only requires loss calculation on feature map, it can be easily applied to various detectors. We conducted experiments on detectors with different frameworks, using a tea dataset collected at the Huangshan Houkui Tea Plantation. The experimental results indicate that, under the guidance of RFDD, the student detectors have achieved performance improvements to varying degrees. For instance, a one-stage detector like RetinaNet (ResNet-50) experienced a 3.14% increase in Average Precision (AP) after RFDD guidance. Similarly, a two-stage model like Faster RCNN (ResNet-50) obtained a 3.53% improvement in AP. This offers promising prospects for lightweight models to efficiently perform real-time tea leaves detection tasks.

A novel embedded kernel CNN-PCFF algorithm for breast cancer pathological image classification

Early screening of breast cancer through image recognition technology can significantly increase the survival rate of patients. Therefore, breast cancer pathological image is of great significance for medical diagnosis and clinical research. In recent years, numerous deep learning models have been applied to breast cancer image classification, with deep CNN being a typical representative. Due to the use of multi-depth small convolutional kernels in mainstream CNN architectures such as VGG and Inception, the obtained image features often have high dimensionality. Although high dimensionality can bring more fine-grained features, it also increases the computational complexity of subsequent classifiers and may even lead to the curse of dimensionality and overfitting. To address these issues, a novel embedded kernel CNN principal component feature fusion (CNN-PCFF) algorithm is proposed. The constructed kernel function is embedded in the principal component analysis to form the multi-kernel principal component. Multi-kernel principal component analysis is used to fuse the high dimensional features obtained from the convolution base into some representative comprehensive variables, which are called kernel principal components, so as to achieve the purpose of dimensionality reduction. Any type of classifier can be added based on multi-kernel principal components. Through experimental analysis on two public breast cancer image datasets, the results show that the proposed algorithm can improve the performance of the current mainstream CNN architecture and subsequent classifiers. Therefore, the proposed algorithm in this paper is an effective tool for the classification of breast cancer pathological images.

Enhancing image recognition robustness in early weed detection through optimal training data curation

Abstract Using convolutional neural networks (CNNs) for image recognition is effective for early weed detection. However, the impact of training data curation, specifically concerning morphological changes during the early growth phases of weeds, on recognition robustness remains unclear. We focused on four weed species (giant ragweed [Ambrosia trifida L.], red morningglory [Ipomoea coccinea L.], pitted morningglory [Ipomoea lacunosa L.], and burcucumber [Sicyos angulatus L.]) with varying cotyledon and true leaf shapes. Creating 16 models in total, we employed four dataset patterns with different growth stage combinations, two image recognition algorithms (object detection: You Look Only Once [YOLO] v5 and image classification: Visual Geometry Group [VGG] 19), and two conditions regarding the number of species treated (four and two species). We evaluated the effects of growth stage training on weed recognition success using two datasets. One evaluation revealed superior results with a single class/species training dataset, achieving >90% average precision for detection and classification accuracy under most conditions. The other dataset revealed that merging different growth stages with different shapes as a class effectively prevented misrecognition among different species when using YOLOv5. Both results suggest that integrating different shapes in a plant species as a single class is effective for maintaining robust recognition success amid temporal morphological changes during the early growth stage. This finding not only enhances early detection of weed seedlings but also bolsters the robustness of general plant species identification.

High-precision identification of highly similar Pinelliae Rhizoma and adulterated Rhizoma pinelliae pedatisectae through deep neural networks based on vision transformers.

Pinelliae Rhizoma is a key ingredient in botanical supplements and is often adulterated by Rhizoma Pinelliae Pedatisectae, which is similar in appearance but less expensive. Accurate identification of these materials is crucial for both scientific and commercial purposes. Traditional morphological identification relies heavily on expert experience and is subjective, while chemical analysis and molecular biological identification are typically time consuming and labor intensive. This study aims to employ a simpler, faster, and non-invasive image recognition technique to distinguish between these two highly similar plant materials. In the realm of image recognition, we aimed to utilize the vision transformer (ViT) algorithm, a cutting-edge image recognition technology, to differentiate these materials. All samples were verified using DNA molecular identification before image analysis. The result demonstrates that the ViT algorithm achieves a classification accuracy exceeding 94%, significantly outperforming the convolutional neural network model's 60%-70% accuracy. This highlights the efficiency of this technology in identifying plant materials with similar appearances. This study marks the pioneer work of the ViT algorithm to such a challenging task, showcasing its potential for precise botanical material identification and setting the stage for future advancements in the field.

Research on single-phase grounding detection method in small-current grounding systems based on image recognition

In small-current grounding systems, the fault current during a single-phase grounding fault is small, and the transient process is complex, leading to challenges in line selection accuracy and reliability. This paper proposes a single-phase grounding line selection method based on transfer learning using the ResNet-50 model. Zero-sequence voltage and current waveforms at the fault moment are preprocessed and combined to generate training data for the model. Simulation results using PSCAD demonstrate that the proposed method achieves 99.77% validation accuracy, even under noisy conditions. These results confirm the method’s feasibility and reliability in identifying grounding faults in various conditions.

A facial and vocal emotion recognition system based on deep learning

The traditional teaching mode, mainly characterized by "cramming" instruction, often overlooks the absorption of knowledge by students during the teaching process. Even in recent years, the emerging "flipped classroom" model heavily relies on teachers' experience and expertise, making it challenging to quantify students' classroom learning states. Among young teachers lacking teaching experience, the replication of excellent teaching models faces difficulties. With the rapid development of artificial intelligence technology, deep learning and other AI techniques are increasingly applied to people's lives. Additionally, emotion computing technology is also becoming more sophisticated. In the field of education, the use of AI technology holds the potential to help teachers systematically and comprehensively assess teaching quality, promoting the sharing of high-quality educational resources nationally and globally. Existing emotion detection technologies often focus on single techniques such as image recognition or natural language processing, resulting in low accuracy in discerning human emotions and making it difficult to accurately identify emotional changes in complex scenarios such as classrooms. Furthermore, there is a lack of comprehensive emotional statistical analysis methods for audio and visual data. In light of these, we have designed and implemented a multi-modal emotion recognition and analysis system. Through testing in classroom settings, this system has the potential to assist classroom teaching and enhance teaching quality.

A Recyclable Waste Image Recognition System with YOLOv8 for Children's Environmental Education

A Recyclable Waste Image Recognition System with YOLOv8 for Children's Environmental Education

Vision transformer introduces a new vitality to the classification of renal pathology

Recent advancements in computer vision within the field of artificial intelligence (AI) have made significant inroads into the medical domain. However, the application of AI for classifying renal pathology remains challenging due to the subtle variations in multiple renal pathological classifications. Vision Transformers (ViT), an adaptation of the Transformer model for image recognition, have demonstrated superior capabilities in capturing global features and providing greater explainability. In our study, we developed a ViT model using a diverse set of stained renal histopathology images to evaluate its effectiveness in classifying renal pathology. A total of 1861 whole slide images (WSI) stained with HE, MASSON, PAS, and PASM were collected from 635 patients. Renal tissue images were then extracted, tiled, and categorized into 14 classes on the basis of renal pathology. We employed the classic ViT model from the Timm library, utilizing images sized 384 × 384 pixels with 16 × 16 pixel patches, to train the classification model. A comparative analysis was conducted to evaluate the performance of the ViT model against traditional convolutional neural network (CNN) models. The results indicated that the ViT model demonstrated superior recognition ability (accuracy: 0.96–0.99). Furthermore, we visualized the identification process of the ViT models to investigate potentially significant pathological ultrastructures. Our study demonstrated that ViT models outperformed CNN models in accurately classifying renal pathology. Additionally, ViT models are able to focus on specific, significant structures within renal histopathology, which could be crucial for identifying novel and meaningful pathological features in the diagnosis and treatment of renal disease.

Research on fiber OTDR signal recognition and classification based on the ViT model

In the field of event recognition for phase-sensitive optical time-domain reflectometry (-OTDR), convolutional neural networks (CNNs) have been the mainstream tool. However, Transformer models, with their self-attention mechanism, have provided a new perspective for image recognition tasks. This paper proposes a -OTDR event recognition method based on the Transformer model and experimentally demonstrates its significant advantages over CNNs. The method utilizes an attention-based feature extraction approach to recognize distributed fiber optic sensing signals in a phase-sensitive optical time-domain reflectometer (-OTDR). In perimeter defense applications, various interferences and noise severely affect the recognition of -OTDR sensing signals, leading to false alarms, making accurate signal recognition both challenging and necessary. Extracting signal features and using machine learning classification models to recognize signals has been a research hotspot in recent years. The effectiveness of feature extraction is crucial to classification performance. This project introduces a temporal-spatial dual attention mechanism into the feature extraction of fiber optic sensing signals to improve the accuracy and robustness of signal recognition.

Research on fresh image recognition algorithms based on machine learning

The identification of fresh images tackles issues related to accurate classification, speed and flexibility enhancement, and perhaps superior food safety evaluation. In this work, the type and freshness identification (TFI) system is based on ML (machine learning). The research suggests ML techniques for identifying various meats (pork, chicken, beef, etc) flaws and differentiating between fresh and decomposing meats to decrease labour expenses, manufacturing time, and worker effort. An efficient TFI system is suggested in this work using machine learning (ML) techniques. We gather various meat samples to effectively identify the type and freshness of the meat. Pre-processing of raw images is conducted to standardize the raw data samples. In the feature extraction process, features from the normalized data are extracted to confirm the quality of the data. The retrieved data is divided into categories for fresh meat and non-fresh meat. The suggested approach is used to evaluate TFI efficiency using a Python program. In conclusion, it was discovered that this study outperformed in improving the TFI performance

Method of intelligent agricultural pest image recognition based on machine vision algorithm

In recent years, people have paid increasing attention to smart agriculture. Its core technology is to combine information technology such as computer vision with agricultural production. In agricultural production, the occurrence of pests and diseases can seriously affect agricultural production. Therefore, in agricultural production, the diagnosis and identification of agricultural pests and diseases is the key to improve crop yield. Traditional machine vision methods often rely on feature extraction and classifier design, lack of strong learning and generalization ability, and can not effectively control crop diseases and pests in a timely manner. In order to solve this problem, this paper designs an agricultural pest recognition system based on machine vision algorithm of fuzzy recognition theory, and applies it to agricultural pest recognition. Compared with the traditional machine vision method, this method has obvious advantages, and can effectively improve the monitoring and early warning ability of crop diseases and pests. The experimental results show that the highest recognition rate of the machine vision optimization algorithm based on fuzzy recognition theory is 98.06%, and the lowest recognition error rate is 5.83%. It can be seen that the machine vision recognition algorithm based on fuzzy recognition theory has good recognition effect and can be used in agricultural pest recognition system to help farmers carry out agricultural production and reduce economic losses caused by diseases and pests.

Machine vision-assisted genomic prediction and genome-wide association of spleen-related traits in large yellow croaker infected with visceral white-nodules disease

High-resolution and high-throughput genotype-to-phenotype studies in fish are rapidly advancing, driven by innovative technologies that aim to address the challenges of modern breeding models. In recent years, machine vision and deep learning techniques, particularly convolutional neural networks (CNNs), have achieved significant success in image recognition and segmentation. Moreover, qualitative and quantitative analysis of disease resistance has always been a crucial field of research in genetics. This motivation has led us to investigate the potential of large yellow croaker visceral white-nodules disease (VWND) in encoding information on disease resistance for the task of accession classification. In this study, we proposed an image segmentation framework for the feature extraction of the spleen after VWND infection based on machine vision. We utilized deep CNNs and threshold segmentation for automatic feature learning and object segmentation. This approach eliminates subjectivity and enhances work efficiency compared to using hand-crafted features. Additionally, we employed spleen-related traits to conduct genome-wide association analysis (GWAS), which led to the identification of 24 significant SNPs and 10 major quantitative trait loci. The results of function enrichment analysis on candidate genes also indicated potential relationships with immune regulation mechanisms. Furthermore, we explored the use of genomic selection (GS) technology for phenotype prediction of extreme individuals, which further supports the predictability of spleen-related phenotypes for VWND resistance in large yellow croakers. Our findings demonstrate that artificial intelligence (AI)-based phenotyping approaches can deliver state-of-the-art performance for genetics research. We hope this work will provide a paradigm for applying deep learning and machine vision to phenotyping in aquaculture species.

Handwritten Digit Recognition by Deep Learning

This paper evaluates recent advances in handwritten digit recognition models, focusing on strategies developed and deployed in practical applications. The project utilizes both traditional and deep learning approaches, employing architectures such as Convolutional Neural Networks (CNNs). This paper explores the comparative performance of various models, discusses their deployment in real-world scenarios, and highlights future prospects for enhancing handwritten digit recognition technology. Keywords: Handwritten Digit Recognition, Multi-Layer Perceptron (MLP), Convolutional Neural Networks (CNN), AlexNet, Deep Learning for Image Classification, Neural Networks, Image Preprocessing, Data Augmentation, Feature Extraction, Image to Grayscale Conversion, Image Normalization, Training and Validation, Accuracy Metrics, Model Evaluation, Transfer Learning, Classification Algorithms, Real- Time Processing, Computer Vision, Image Recognition.

Proposed methods of image recognition depend on the PCA

This paper suggest two method of recognition, these methods depend on the extraction of the feature of the principle component analysis when applied on the wavelet domain(multi-wavelet). First method, an idea of increasing the space of recognition, through calculating the eigenstructure of the diagonal sub-image details at five depths of wavelet transform is introduced. The effective eigen range selected here represent the base for image recognition. In second method, an idea of obtaining invariant wavelet space at all projections is presented. A new recursive from that represents invariant space of representing any image resolutions obtained from wavelet transform is adopted. In this way, all the major problems that effect the image and change its characteristic are solved through calculating invariant eigen range of the recursive resolution forms of all sub-images coefficient. These approaches employed here as multi-wavelet transform identifier with minimum Mahalanobis distance. All method recognition proposed in this paper are applied on different images. Different tables of image recognition resulted in accurate and fast.

All-In-One Optoelectronic Transistors for Bio-Inspired Visual System.

Visual perception has profound effects on human decision-making and emotional responses. Replicating the functions of the human visual system through device development has been a constant pursuit in recent years. However, to fully simulate the various functions of the human visual system, it is often necessary to integrate multiple devices with different functions, resulting in complex, large-volume device structures and increased power consumption. Here, an optoelectronic transistor with comprehensive visual functions is introduced. By coupling diverse photoreceptive properties of the channel and electrical regulation through charge injection/ferroelectric switching from the hafnium-based gate, the devices can simulate functions of both photoreceptors in the retina and synapses in the visual cortex. A device array is constructed to confirm the perceptual functions of cone and rod cells. Subsequently, color discrimination and recognition for color images are achieved by combining the tunable perception and synapse functions. Then an intelligent traffic judgment system with this all-in-one device is developed, which is capable of making judgments and decisions regarding traffic signals and pedestrian movements. This work provides a potential solution for developing compact and efficient devices for the next-generation bio-inspired visual system.

Synaptic Feature of Quantum Dot Light-Emitting Diodes for Visualization of Learning Process.

Brain-inspired electronics with synaptic functions hold significant promise for advancing artificial intelligent applications. In this study, we demonstrate the synaptic feature of quantum-dot light-emitting diodes (QLEDs), which can convert electrical pulses into synapse-like light signals (the brightness gradually increases as the electrical pulses are prolonged). These features are analogous to learning and forgetting in biological synapses. The enhancement of brightness can be attributed to the reduction of charge transfer from the quantum dots to ZnO electron transport layer and resistive switching effect. With an integrated complementary metal-oxide-semiconductor (CMOS) drive, arrayed synaptic QLEDs can simulate the visualization of brain-like learning processes, which can reduce the noise toward high image recognition rate (>95.0%) by deep neural networks. Our findings introduce a novel brain-inspired optoelectronic approach with potential applications in optical neuromorphic systems.

IC-IE-AKS-O: an automatic recognition method for coastal slope landslide areas

Automatically and accurately identifying the deformation zone of coastal slope landslides is crucial for exploring the mechanism of landslides and predicting landslide disasters. To this end, this study proposes an integrated automatic recognition method combining Image Clipping (IC), Image Information Enhancement (IE), Adaptive K-means Clustering Segmentation (AKS), and Optimization (O): IC-IE-AKS-O, which achieves precise extraction of the deformation area in coastal slope landslide images. Firstly, due to the more complex natural environment of field slopes, to extend the monitoring duration, we introduce a hierarchical operation algorithm based on the HSV color model, which effectively mitigates the impact of sunlight, rain, and foggy weather on image recognition accuracy. Secondly, this study proposes a 2D landslide image segmentation technique that combines K-means clustering with global threshold segmentation for landslide images, enabling the segmentation of small image regions with precision. Finally, we combine image information enhancement technology with image segmentation technology. To verify its effectiveness, we identify a landslide image of a coastal slope in Pingtan. The method displays an average relative error of 5.20% and 5.14% in the X and Y directions, respectively. Its advantages are threefold: (1) The combination of image information enhancement and segmentation techniques can more accurately identify landslide areas that appear blurred in the image; (2) expanding the temporal dimension of coastal slope monitoring; (3) providing excellent boundary conditions and segmentation results. The practical application of this method ensures the stable and accurate operation of the coastal slope monitoring system, providing a safeguard for the sustainable development of marine safety.

Color Recognition Achieved in Multiwavelength Controlled Plasmonic Optoelectronic Memristor for Neuromorphic Visual System

AbstractAn optoelectronic synaptic device with the color‐recognition ability is highly desired for achieving the high‐efficient neuromorphic color visual system. In order to realistically implement the functionality of retina (i.e., bipolar cells and cones photoreceptors), the exploration of multiwavelength controlled optoelectronic synaptic devices with fully light tunable ability would be sorely needed. Here, a multiwavelength controlled plasmonic optoelectronic memristor based on the size‐dependent localized surface plasmon resonance (LSPR) of metallic nanostructures is developed. The distinguishable red (R), green (G), and blue (B) light response behaviors can be achieved in this single device, which enables the realization of color image perception and memory functions. The RGB light‐strengthened synaptic plasticity can be depressed by ultraviolet light stimulations, relying on the effects of LSPR and optical excitation in WOx:Ag nanocomposites. Moreover, the visual attention for color (color discrimination) is realized in this memristor, which promotes the improvement of recognition accuracy during the color image recognition process. A new approach in developing multiwavelength controlled synaptic devices is provided here for highly efficient neuromorphic vision.

Research on identification and detection of coal and gangue based on infrared thermal imaging technology and improved YOLOv8n

ABSTRACT Considering that traditional image recognition methods for coal and gangue are susceptible to environmental factors such as light and dust, this paper proposes an image recognition and detection method for the coal and gangue based on infrared thermal imaging technology and an improved YOLOv8n. First, we established a thermal infrared imaging platform for coal and gangue. We used the YOLOv8n model to analyze the differences between coal and gangue at various temperatures, determining the optimal temperature for effective recognition of the coal and gangue. Next, to facilitate the practical deployment of the detection model for coal and gangue, we incorporated the Ghost module into the original YOLOv8n model to reduce its complexity and storage requirements. Unfortunately, incorporating the Ghost module led to a slight decrease in the model’s detection performance. Next, we introduced the DAttention module into the model to enhance its feature extraction capabilities. At the same time, we replaced the CIoU loss function with DIoU, which further improved the model’s performance metrics. Finally, we compared the improved YOLOv8n model with Faster-RCNN model and SSD model to validate its feasibility and accuracy further and provide a new approach for the detection of coal and gangue.

An empirical study of AI techniques in mobile applications

The integration of artificial intelligence (AI) into mobile applications has significantly transformed various domains, enhancing user experiences and providing personalized services through advanced machine learning (ML) and deep learning (DL) technologies. AI-driven mobile apps typically refer to applications that leverage ML/DL technologies to perform key tasks such as image recognition and natural language processing. Despite existing research exploring how mobile apps exploit AI techniques, they have the following main limitations: (1) Most existing studies focus on DL-based apps, with limited research on ML-based apps. (2) Existing research typically focuses on investigating the apps and the technologies utilized in the apps, lacking user-level analysis. (3) The number of apps studied is limited, with only 1,000 to 2,000 ML/DL apps identified after filtering. To fill the gap, in this paper, we conducted the most extensive empirical study on AI applications, exploring on-device ML apps, on-device DL apps, and AI service-supported (cloud-based) apps. Our study encompasses 56,682 real-world AI applications, focusing on three crucial perspectives: (1) Application analysis, where we analyze the popularity of AI apps and investigate the update states of AI apps; (2) Framework and model analysis, where we analyze AI framework usage and AI model protection; (3) User analysis, where we examine user privacy protection and user review attitudes. Our study has strong implications for AI app developers, users, and AI R&D. On one hand, our findings highlight the growing trend of AI integration in mobile applications, demonstrating the widespread adoption of various AI frameworks and models. On the other hand, our findings emphasize the need for robust model protection to enhance app security. Additionally, our study highlights the importance of user privacy and presents user attitudes towards the AI technologies utilized in current AI apps. We provide our AI app dataset (currently the most extensive AI app dataset) as an open-source resource for future research on AI technologies utilized in mobile applications.