Recognition Technology Research Articles

Development of Dust Emission Prediction Model for Open-Pit Mines Based on SHPB Experiment and Image Recognition Method

Open-pit coal mining offers high resource recovery, excellent safety conditions, and large-scale production. However, the process generates significant dust, leading to occupational diseases such as pneumoconiosis among miners and adversely affecting nearby vegetation through dust deposition, which hinders photosynthesis and causes ecological damage. This limits the transition of open-pit mining to a green, low-carbon model. Among these processes, blasting generates the most dust and has the widest impact range, but the specific amount of dust generated has not yet been thoroughly studied. This study integrates indoor experiments, theoretical analyses, and field tests, employing the Split Hopkinson Pressure Bar (SHPB) system to conduct impact loading tests on coal–rock samples under pressures ranging from 0.13 MPa to 2.0 MPa. The results indicate that as the impact load increases, the proportion of large-sized blocks decreases while smaller fragments and powdered samples increase, signifying intensified sample fragmentation. Using stress wave attenuation theory, this study translates indoor impact loadings to field blast shock waves, revealing the relationship between blasting dust mass fraction and impact pressure. Field tests at the Haerwusu open-pit coal mine validated the formula. Using image recognition technology to analyze post-blast muck-pile fragmentation, the estimated dust production closely matched the calculated values, with an error margin of less than 10%. This formula provides valuable insights for estimating dust production and improving dust control measures during open-pit mine blasting operations.

BFFN: A novel balanced feature fusion network for fair facial expression recognition

Facial expression recognition (FER) technology has become increasingly mature and applicable in recent years. However, it still suffers from the bias of expression class, which can lead to unfair decisions for certain expression classes in applications. This study aims to mitigate expression class bias through both pre-processing and in-processing approaches. First, we analyze the output of existing models and demonstrate the existence of obvious class bias, particularly for underrepresented expressions. Second, we develop a class-balanced dataset constructed through data generation, mitigating unfairness at the data level. Then, we propose the Balanced Feature Fusion Network (BFFN), a class fairness-enhancing network. The BFFN mitigates the class bias by adding facial action units (AU) to enrich expression-related features and allocating weights in the AU feature fusion process to improve the extraction ability of underrepresented expression features. Finally, extensive experiments on datasets (RAF-DB and AffectNet) provide evidence that our BFFN outperforms existing FER models, improving the fairness by at least 16%.

Augmented dialectal speech recognition for AI-based neuropsychological scale assessment in Alzheimer’s disease

Alzheimer’s disease (AD) is a prevalent and widespread neurodegenerative disorder among the older adult population worldwide. Among the numerous cognitive screening methods, neuropsychological scale assessments (NSA) are the widely utilized screening tools in clinical practice. The NSA places significant emphasis on speech-related questions, and thus the role of Automatic Speech Recognition (ASR) technology in AI-based NSA evaluations becomes particularly critical. However, the majority of ASR research pays limited attention to the study of speech recognition for various dialects. One of the primary reasons and main challenges for the scarcity of research in dialectal speech recognition is the limited availability of annotated dialectal data. Furthermore, the older adults’ unclear pronunciation leads to erroneous recognition of similar phonetic words by ASR. To overcome the challenges of limited annotated dialect data in various regions and the issues related to confusable pronunciation of older adults, we propose a dialectal collaborative encoder mechanism and a machine reading comprehension augmented model (MRCAM) that automatically corrects the texts in the NSA. The dialectal collaborative encoder mechanism utilizes layer frozenness to transfer recognition ability to the dialectal model. Meanwhile, the MRCAM model fills the gap by combining speech recognition algorithms with natural language processing (NLP) technology to recognize the dialects spoken by older adults. The experimental evaluation results indicate that the proposed augmented model achieves over 90% consistency with the physician’s judgment, providing the premise of the proposed methods for the task of automated screening for AD based on ASR.

Application of Convolutional Neural Network in Image Recognition

Image recognition is of great significance for both human social development and daily life. This paper mainly discusses the application research of convolutional neural network (CNN) in the field of image recognition. Firstly, the basic structure and working principle of CNN, including the core components of convolution layer, pooling layer and full connection layer, are introduced, and then the structure and characteristics of the middle layer are explained. Then, this paper compares the advantages and disadvantages of different CNN models such as LeNet-5, AlexNet, GoogLeNet, ResNet, etc., and analyzes their application in face recognition, medical image recognition, traffic recognition, character recognition and other fields. Finally, this paper summarizes the application of CNN in image recognition, and points out the problems faced in its practical application, such as model complexity, computational resource requirements, etc., aiming to provide reference for further research of image recognition technology.

An automatic classification method of testicular histopathology based on SC-YOLO framework.

The pathological diagnosis and treatment of azoospermia depend on precise identification of spermatogenic cells. Traditional methods are time-consuming and highly subjective due to complexity of Johnsen score, posing challenges for accurately diagnosing azoospermia. Here, we introduce a novel SC-YOLO framework for automating the classification of spermatogenic cells that integrates S3Ghost module, CoordAtt module and DCNv2 module, effectively capturing texture and shape features of spermatogenic cells while reducing model parameters. Furthermore, we propose a simplified Johnsen score criteria to expedite the diagnostic process. Our SC-YOLO framework presents the higher efficiency and accuracy of deep learning technology in spermatogenic cell recognition. Future research endeavors will focus on optimizing the model's performance and exploring its potential for clinical applications.

Evolutionary computation-based self-supervised learning for image processing: a big data-driven approach to feature extraction and fusion for multispectral object detection

The image object recognition and detection technology are widely used in many scenarios. In recent years, big data has become increasingly abundant, and big data-driven artificial intelligence models have attracted more and more attention. Evolutionary computation has also provided a powerful driving force for the optimization and improvement of deep learning models. In this paper, we propose an image object detection method based on self-supervised and data-driven learning. Differ from other methods, our approach stands out due to its innovative use of multispectral data fusion and evolutionary computation for model optimization. Specifically, our method uniquely combines visible light images and infrared images to detect and identify image targets. Firstly, we utilize a self-supervised learning method and the AutoEncoder model to perform high-dimensional feature extraction on the two types of images. Secondly, we fuse the extracted features from the visible light and infrared images to detect and identify objects. Thirdly, we introduce a model parameter optimization method using evolutionary learning algorithms to enhance model performance. Validation on public datasets shows that our method achieves comparable or superior performance to existing methods.

High-precision dynamic gesture recognition based on microfiber sensor and EMT-Net

Dynamic gesture recognition, which utilizes flexible wearable sensors and deep learning, is invaluable for human–computer interaction. Nevertheless, the primary challenges persist are the rapid detection of intricate gestures and the accurate recognition of dynamic signals. In this study, we suggest utilizing a microfiber sensor to identify the variations in wrist skin and detect dynamic gesture. In order to tackle the issue of insufficient feature extraction in the detected signals, resulting in reduced accuracy in recognition, we introduce a network dubbed EMT-Net (improve multi-head attention transformer network). This network utilizes a transformer encoder to capture and represent the characteristics of dynamic gesture signal and uses a CNN to classify the encoded features. To ensure that the model comprehensively captures the temporal and statistical characteristics of the signals, we enhance the multi-head attention mechanism by restricting certain attention heads to concentrate solely on the statistical features of the signals while allowing others to focus on the temporal features and global dependencies. Furthermore, because of the varying discriminatory abilities of different characteristics, we have developed an attention module to redistribution the attention weights on statistical features. The experimental results demonstrate that the microfiber sensor effectively recognizes ten distinct forms of dynamic gesture signals. Simultaneously, EMT-Net attains proficient identification with an accuracy of 98.80%, precision of 98.81%, recall of 98.80%, and an F1 score of 98.80%. The application value of this dynamic gesture recognition technology, which utilizes microfiber sensors and EMT-Net, is significant. The forthcoming alterations in human–computer interaction, virtual reality, and various other domains are anticipated.

Decoding environmental impact with image-based CO2 emission analytics

As per the regulations of Intergovernmental Panel on Climate Change (IPCC), the country’s carbon emission data hold primacy. Nevertheless, establishing and utilizing a database pose a daunting challenge. This study presents the “Carbon Seer System,” a novel software prototype designed to inform and educate users about the carbon footprint during their production and in daily life. The development process involved a three-stage user interview process, ensuring system’s alignment with user needs and preferences. The system employs machine learning and visual recognition technology, including convolutional neural networks (CNNs), feature pyramid networks, and self-attention mechanisms, enabling users to analyze captured images for carbon emission factors. It automatically identifies the carbon emission factors of industrial products, energy producers, household producers, waste treatment, and transportation. A unique “group detection” method allows for the simultaneous analysis of multiple objects in a single image, enhancing user convenience. Additionally, the software features a carbon footprint tracker and a carbon sink dashboard, providing users with insights into their carbon emissions and the efforts needed for offsetting. The study concludes that the “Carbon Seer System” represents a significant step towards individual enablement at understanding and actively participating in a low-carbon lifestyle.

Efficient face anti-spoofing via head-aware transformer based knowledge distillation with 5 MB model parameters

Although face recognition technology has been applied in many scenarios, it still suffers from many types of presentation attacks, so face anti-spoofing (FAS) becomes a hot topic in computer vision. Recently, vision transformer is recognized as the mainstream architecture for FAS, which always relies on auxiliary information, sophisticated tricks and huge model parameters. Considering that face based identity authentication usually takes place on mobile-like devices, therefore how to design an effective and lightweight model is of great significance. Inspired by the powerful global modeling ability of self-attention and the model compression ability of knowledge distillation, a simple yet effective knowledge distillation approach is proposed for FAS under transformer framework. Our primary idea is to leverage the rich knowledge of a teacher network pre-trained on large-scale face data to guide the learning of a lightweight student network. The main contributions of our method are threefold: (1) Feature- and logits-level distillation are combined to transfer the rich knowledge of teacher to student. (2) A head-aware strategy is proposed to deal with the dimension mismatching issue of middle encoder layers between teacher and student networks, in which a novel attention head correlation matrix is introduced. (3) Our method can bridge the performance gap between teacher and student, and the resulting student network is extremely lightweight with only 5 MB parameters. Extensive experiments are conducted on three public face-spoofing datasets, CASIA-FASD, Replay-Attack and OULU-NPU, the results demonstrate that our method can obtain performance on par with or superior to most FAS methods and outperform many knowledge distillation methods. Meanwhile, the distilled student network achieves excellent performance with 17× fewer parameters and 9× faster inference time compared to the teacher network. The code will be publicly available at https://github.com/Maricle-zhangjun/HaTFAS.

Human Muscle sEMG Signal and Gesture Recognition Technology Based on Multi-Stream Feature Fusion Network

Surface electromyography signals have significant value in gesture recognition due to their ability to reflect muscle activity in real time. However, existing gesture recognition technologies have not fully utilized surface electromyography signals, resulting in unsatisfactory recognition results. To this end, firstly, a Butterworth filter was adopted to remove high-frequency noise from the signal. A combined method of moving translation threshold was introduced to extract effective signals. Then, a gesture recognition model based on multi-stream feature fusion network was constructed. Feature extraction and fusion were carried out through multiple parallel feature extraction paths, combined with convolutional neural networks and residual attention mechanisms. Compared to popular methods of the same type, this new recognition method had the highest recognition accuracy of 92.1% and the lowest recognition error of 5%. Its recognition time for a single-gesture image was as short as 4s, with a maximum Kappa coefficient of 0.92. Therefore, this method combining multi-stream feature fusion networks can effectively improve the recognition accuracy and robustness of gestures and has high practical value.

An experimental study of acoustic bird repellents for reducing bird encroachment in pear orchards.

Bird invasion will reduce the yield of high-value crops, which threatens the healthy development of agricultural economy. Sonic bird repellent has the advantages of large range, no time and geographical restrictions, and low cost, which has attracted people's attention in the field of agriculture. At present, there are few studies on the application of sonic bird repellents in pear orchards to minimize economic losses and prolong the adaptive capacity of birds. In this paper, a sound wave bird repellent system based on computer vision is designed, which combines deep learning target recognition technology to accurately identify birds and drive them away. The neural network model that can recognize birds is first trained and deployed to the server. Live video is captured by an installed webcam, and the sonic bird repellent is powered by an ESP-8266 relay switch. In a pear orchard, two experimental areas were divided into two experimental areas to test the designed sonic bird repellent device, and the number of bad fruits pecked by birds was used as an indicator to evaluate the bird repelling effect. The results showed that the pear pecked fruit rate was 6.03% in the pear orchard area that used the acoustic bird repeller based on computer recognition, 7.29% in the pear orchard area of the control group that used the acoustic bird repeller with continuous operation, and 13.07% in the pear orchard area that did not use any bird repellent device. While acoustic bird repellers based on computer vision can be more effective at repelling birds, they can be used in combination with methods such as fruit bags to reduce the economic damage caused by birds.

Realization of Facial Recognition Technology for Attendance Monitoring Through Biometric Modalities Employing MTCNN Integration

Realization of Facial Recognition Technology for Attendance Monitoring Through Biometric Modalities Employing MTCNN Integration

Failure to Enroll: The Blurring Rhetorical Power of Anonymizing Tools and Photographs in Making In/Visible Black Lives

As Black Lives Matter (BLM) protests surged in response to the continued murders of black men and women, state surveillance practices, too, have increasingly monitored, tracked, and prosecuted protesters. Among the growing surveillance arsenal are facial recognition technologies (FRT), which authorities use to identify protesters, often leading to the mis/recognition of black and brown people, false arrests, and blacklisting from public spaces. In response to the prevalence of FRT, protesters and photographers are urging and employing anonymizing blurring technologies to evade state and citizen surveillance. I argue that these technologies materially and rhetorically disrupt the racialized surveillant gaze. I employ Simone Browne’s (2015) term “dark sousveillance” as a framework for understanding how blurring technologies enable evasion from state violence and promote ethical photography practices. Such practices challenge the relationship between whiteness and the law enforcement surveillance regime.

Sustainable Competitive Advantage in the Legal Industry: A Review of Business Strategies and Market Entry Approaches for Gowling WLG in Japan and Nigeria

The modern business landscape has been notably disrupted by events like the COVID-19 pandemic, which reduced global trade by 13% to 23% in 2020, affecting the triple bottom line—profit, people, and planet—of the legal industry. This research develops a sustainable competitive advantage framework for Gowling WLG in emerging markets, focusing on Japan and Nigeria. The study compares Gowling WLG's business strategies and market entry approaches through a strategic management model and case study design, comparing the firm's operations in these diverse markets. Data was collected via document analysis, interviews, field observations, and megatrend articles to evaluate the competitive landscape. A context analysis of existing literature helped formulate relevant themes. Findings reveal the dynamic nature of the legal sector, influenced by political stability, economic conditions, technological advancements, and environmental concerns. Despite challenges like Brexit, global growth opportunities and threats coexist. Gowling's strengths include global recognition and advanced technology, but it also faces challenges in innovation and leadership. Opportunities lie in expanding the high-legal industry and offering sustainability-focused services, though cybersecurity risks and economic instability are significant threats. Strategic alliances with local firms for risk management and expertise are advised. Entering Japan requires thorough research, local collaboration, and cultural sensitivity. This research contributes to the empirical and theoretical literature, noting data reliability limitations, especially in Nigeria.

Quantitative classification evaluation model for tight sandstone reservoirs based on machine learning

Tight sandstone reservoirs are a primary focus of research on the geological exploration of petroleum. However, many reservoir classification criteria are of limited applicability due to the inherent strong heterogeneity and complex micropore structure of tight sandstone reservoirs. This investigation focused on the Chang 8 tight reservoir situated in the Jiyuan region of the Ordos Basin. High-pressure mercury intrusion experiments, casting thin sections, and scanning electron microscopy experiments were conducted. Image recognition technology was used to extract the pore shape parameters of each sample. Based on the above, through grey relational analysis (GRA), analytic hierarchy process (AHP), entropy weight method (EWM) and comprehensive weight method, the relationship index Q1 between initial productivity and high pressure mercury injection parameters and the relationship index Q2 between initial productivity and pore shape parameters are obtained by fitting. Then a dual-coupled comprehensive quantitative classification prediction model for tight sandstone reservoirs was developed based on pore structure and shape parameters. A quantitative classification study was conducted on the target reservoir, analyzing the correlation between reservoir quality and pore structure and shape parameters, leading to the proposal of favourable exploration areas. The research results showed that when Q1 ≥ 0.5 and Q2 ≥ 0.5, the reservoir was classified as type I. When Q1 > 0.7 and Q2 > 0.57, it was classified as type I1, indicating a high-yield reservoir. When 0.32 < Q1 < 0.47 and 0.44 < Q2 < 0.56, was classified as type II. When 0.1 < Q1 < 0.32 and 0.3 < Q2 < 0.44, it was classified as type III. Type I reservoirs exhibit a zigzag pattern in the northwest part of the study area. Thus, the northwest should be prioritized in actual exploration and development. Additionally, the initial productivity of tight sandstone reservoirs showed a positive correlation with the porosity, permeability, sorting coefficient, coefficient of variation, and median radius. Conversely, it demonstrated a negative correlation with the median pressure and displacement pressure. The perimeters of pores, their circularity, and the length of the major axis showed a positive correlation with the porosity, permeability, sorting coefficient, coefficient of variation, and median radius. On the other hand, they exhibited a negative correlation with the median pressure and displacement pressure. This study quantitatively constructed a new classification and evaluation system for tight sandstone reservoirs from the perspective of microscopic pore structure, achieving an overall model accuracy of 93.3%. This model effectively predicts and evaluates tight sandstone reservoirs. It provides new guidance for identifying favorable areas in the study region and other tight sandstone reservoirs.

Esmeraldino Salles (1916 - 1979) documentado pela imprensa: uma incursão no Acervo da Hemeroteca Digital da Biblioteca Nacional

This article describes the process, methodology and results of a search in the National Library’s Digital Library for the São Paulo musician Esmeraldino Salles, who lived between 1916 and 1979. The Hemeroteca Digital has an important digitalized collection of newspapers, magazines and periodicals, photocopied and scanned, and the optical character recognition technology allows keyword searches, opening up enormous possibilities for researching the careers of musicians unknown to the general public. The aim of this paper is to document the results obtained from this source, describing and mapping Esmeraldino’s main professional activities as a musician: 1) performing on Rádio Tupi and television; 2) accompanying singers in São Paulo’s nightlife, in bars, nightclubs and concert halls; 3) photographic records; and 4) recording phonograms and albums. Through this description and mapping of data obtained from the Hemeroteca Digital, we can get an idea of the repercussions of Esmeraldino Salles’ work in his heyday, as well as the public’s perception of him.

Emotion recognition using machine learning: Opportunities and challenges for supporting those with autism or depression

Facial recognition technology, driven by advancements in machine learning, has become integral to various applications, from mobile security to access control. Recent developments in deep learning, particularly through convolutional and recurrent neural networks, have paved the way for enhanced emotion recognition capabilities. This paper explores the potential of facial emotion recognition (FER) and voice emotion recognition technologies, assessing their current state and future prospects. While FER techniques have evolved from traditional methods to deep learning approaches, and voice emotion recognition has shown promising results, challenges remain due to the inherent variability in human facial expressions and vocal characteristics. The paper further examines the impact of emotion recognition technologies on mental health, highlighting their potential to provide significant support to individuals with mental health disorders. By addressing the accuracy and application of these technologies, the research underscores the importance of continued innovation and careful implementation to maximize their benefits and mitigate potential risks. Ultimately, emotion recognition provides promising avenues for supporting those with mental illnesses. Aimed at fostering more personalized and effective interventions, these technologies hold the potential to revolutionize mental health care and improve the overall well-being of individuals.

Attention-Based Spatiotemporal-Aware Network for Fine-Grained Visual Recognition

On public benchmarks, current macro facial expression recognition technologies have achieved significant success. However, in real-life scenarios, individuals may attempt to conceal their true emotions. Conventional expression recognition often overlooks subtle facial changes, necessitating more fine-grained micro-expression recognition techniques. Different with prevalent facial expressions, weak intensity and short duration are the two main obstacles for perceiving and interpreting a micro-expression correctly. Meanwhile, correlations between pixels of visual data in spatial and channel dimensions are ignored in most existing methods. In this paper, we propose a novel network structure, the Attention-based Spatiotemporal-aware network (ASTNet), for micro-expression recognition. In ASTNet, we combine ResNet and ConvLSTM as a holistic framework (ResNet-ConvLSTM) to extract the spatial and temporal features simultaneously. Moreover, we innovatively integrate two level attention mechanisms, channel-level attention and spatial-level attention, into the ResNet-ConvLSTM. Channel-level attention is used to discriminate the importance of different channels because the contributions for the overall presentation of micro-expression vary between channels. Spatial-level attention is leveraged to dynamically estimate weights for different regions due to the diversity of regions’ reflections to micro-expression. Extensive experiments conducted on two benchmark datasets demonstrate that ASTNet achieves performance improvements of 4.25–16.02% and 0.79–12.93% over several state-of-the-art methods.

Comparative Study for Virtual Personal Assistants (VPA) and State-of-the-Art Speech Recognition Technology

Numerous types of virtual assistants have emerged as a result of the widespread use of smartphones, the expansion of their services, the tremendous advancements in automatic speech recognition and AI, and the growing reliance on virtual personal assistants (VPAs) for basic daily tasks like playing music, sending texts, making restaurant reservations, and getting weather updates. The popularity of virtual personal assistants is largely attributable to their convenient blend of user-friendliness and natural language interaction. This study comprehensively examines various virtual personal assistants powered by AI. It briefly overviews each, such as Microsoft Cortana, Samsung Bixby, Apple SIRI, Google Assistant, and Amazon Alexa. This study also includes a comprehensive overview of the state-of-the-art speech recognition used in virtual personal assistants. The findings show that each Virtual Personal Assistant has advantages, and a user may select any of them depending on his preferences and needs.

A Study of New Indexing Techniques for Multimodal Identification Using Iris, Fingerprint, and Face Biometrics

This paper explores innovative indexing techniques for multimodal biometric identification systems, focusing on iris, fingerprint, and facial recognition technologies. With the proliferation of digital identity verification needs, traditional single-modal biometric systems often fall short in terms of accuracy, speed, and security. Multimodal biometric systems, which integrate multiple biological characteristics, are becoming crucial for enhancing identification performance. This study aims to present a comprehensive analysis of new indexing methods that can significantly improve the efficiency, accuracy, and security of multimodal biometric identification systems.