To address the problems about the difficulty in accurate recognition of distribution features of gas flow center at blast furnace throat and determine the relationship between gas flow center distribution and gas util...To address the problems about the difficulty in accurate recognition of distribution features of gas flow center at blast furnace throat and determine the relationship between gas flow center distribution and gas utilization rate,a method for recognizing distribution features of blast furnace gas flow center was proposed based on infrared image processing,and distribution features of blast furnace gas flow center and corresponding gas utilization rates were categorized by using fuzzy C-means clustering and statistical methods.A concept of gas flow center offset was introduced.The results showed that,when the percentage of gas flow center without offset exceeded 85%,the average blast furnace gas utilization rate was as high as 41%;when the percentage of gas flow center without offset exceeded50%,the gas utilization rate was primarily the center gas utilization rate,and exhibited a positive correlation with no center offset degree;when the percentage of gas flow center without offset was below 50% but the sum of the percentage of gas flow center without offset and that of gas flow center with small offset exceeded 86%,the gas utilization rate depended on both the center and the edges,and was primarily the edge gas utilization rate.The method proposed was able to accurately and effectively recognize gas flow center distribution state and the relationship between it and gas utilization rate,providing evidence in favor of on-line blast furnace control.展开更多
Image segmentation is one of important steps on pattern recognition study in the course of wood across-compression. By comparing and studying processing methods in finding cell space and cell wall, this paper puts for...Image segmentation is one of important steps on pattern recognition study in the course of wood across-compression. By comparing and studying processing methods in finding cell space and cell wall, this paper puts forward some image segmentation methods that are suitable for study of cell images of wood crossgrained compression. The method of spline function fitting was used for linking edges of cell, which perfects the study of pattern recognition in the course of wood across-compression.展开更多
The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street ligh...The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street lighting system at night for the entire road, or inexpensive design that sacrifices the safety, relying on using vehicles lighting, to eliminate the problem of high cost energy consumption during the night operation of the road. By taking into account both of these factors, smart lighting automation system is proposed using Pattern Recognition Technique applied on vehicle number-plates. In this proposal, the road is sectionalized into zones, and based on smart Pattern Recognition Technique, the control system of the road lighting illuminates only the zone that the vehicles pass through. Economic analysis is provided in this paper to support the value of using this design of lighting control system.展开更多
A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective....A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective. A new three-layer detection method was proposed to detect and identify white-backed planthoppers （WBPHs, Sogatella furcifera （Horvath）） and their developmental stages using image processing. In the first two detection layers, we used an AdaBoost classifier that was trained on a histogram of oriented gradient （HOG） features and a support vector machine （SVM） classifier that was trained on Gabor and Local Binary Pattern （LBP） features to detect WBPHs and remove impurities. We achieved a detection rate of 85.6% and a false detection rate of 10.2%. In the third detection layer, a SVM classifier that was trained on the HOG features was used to identify the different developmental stages of the WBPHs, and we achieved an identification rate of 73.1%, a false identification rate of 23.3%, and a 5.6% false detection rate for the images without WBPHs. The proposed three-layer detection method is feasible and effective for the identification of different developmental stages of planthoppers on rice plants in paddy fields.展开更多
Aim To study the parking management in the condition of vehicles' increasing. Methods The methods of pattern recognition and image processing were used to analyze the eigenvalues of parking lot images. Results ...Aim To study the parking management in the condition of vehicles' increasing. Methods The methods of pattern recognition and image processing were used to analyze the eigenvalues of parking lot images. Results The automatic identification of every parking place in the parking plot was realized. The automatic measuring of parked vehicle count and parking lot utilization was completed. Conclusion It can complete the real time recognition, and has some practicabilities.展开更多
Using the Radon transform and morphological image processing, an algorithm for ship's wake detection in the SAR (synthetic aperture radar) image is developed. Being manipulated in the Radon space to invert the gra...Using the Radon transform and morphological image processing, an algorithm for ship's wake detection in the SAR (synthetic aperture radar) image is developed. Being manipulated in the Radon space to invert the gray-level and binary images, the linear texture of ship wake in oceanic clutter can be well detected. It has been applied to the automatic detection of a moving ship from the SEASAT SAR image. The results show that this algorithm is well robust in a strong noisy background and is not very sensitive to the threshold parameter and the working window size.展开更多
Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,...Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,a large amount of the books are described by Kuzushiji,a type of handwriting cursive script that is no longer in use today and only readable by a few experts.Therefore,researchers are trying to detect and recognise the characters from these books through modern techniques.Unfortunately,the characteristics of the Kuzushiji,such as Connect-Separate-characters and Manyvariation,hinder the modern technique assisted re-organisation.Connect-Separatecharacters refer to the case of some characters connecting each other or one character being separated into unconnected parts,which makes character detection hard.Manyvariation is one of the typical characteristics of Kuzushiji,defined as the case that the same character has several variations even if they are written by the same person in the same book at the same time,which increases the difficulty of character recognition.In this sense,this paper aims to construct an early Japanese book reorganisation system by combining image processing and deep learning techniques.The experimentation has been done by testing two early Japanese books.In terms of character detection,the final Recall,Precision and F-value reaches 79.8%,80.3%,and 80.0%,respectively.The deep learning based character recognition accuracy of Top3 reaches 69.52%,and the highest recognition rate reaches 82.57%,which verifies the effectiveness of our proposal.展开更多
The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant par...The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant parts,including flowers,leaves,and roots,have been acknowledged for their healing properties and employed in plant identification.Leaf images,however,stand out as the preferred and easily accessible source of information.Manual plant identification by plant taxonomists is intricate,time-consuming,and prone to errors,relying heavily on human perception.Artificial intelligence(AI)techniques offer a solution by automating plant recognition processes.This study thoroughly examines cutting-edge AI approaches for leaf image-based plant identification,drawing insights from literature across renowned repositories.This paper critically summarizes relevant literature based on AI algorithms,extracted features,and results achieved.Additionally,it analyzes extensively used datasets in automated plant classification research.It also offers deep insights into implemented techniques and methods employed for medicinal plant recognition.Moreover,this rigorous review study discusses opportunities and challenges in employing these AI-based approaches.Furthermore,in-depth statistical findings and lessons learned from this survey are highlighted with novel research areas with the aim of offering insights to the readers and motivating new research directions.This review is expected to serve as a foundational resource for future researchers in the field of AI-based identification of medicinal plants.展开更多
A dual-beam electronic speckle pattern interferometry (ESPI) system was adopted to get speckle patterns for the measurement of welding dynamic displacement fields. The mathematical model of this system was described, ...A dual-beam electronic speckle pattern interferometry (ESPI) system was adopted to get speckle patterns for the measurement of welding dynamic displacement fields. The mathematical model of this system was described, based on which methods of the ESPI pattern image processing were discussed. Gray transformation and histogram equalization were used to enhance the contrast of speckle patterns. A discrete cosine image processing method was carried out and an exponent low-pass filter was chosen to reduce multiplicative noise in speckle patterns. Speckle grain noise can be eliminated effectively after these processes.展开更多
From the perspective of geological zone selection for coalbed methane(CBM) development, the evaluation parameters(covering geological conditions and production conditions) of geological sweetspot for CBM development a...From the perspective of geological zone selection for coalbed methane(CBM) development, the evaluation parameters(covering geological conditions and production conditions) of geological sweetspot for CBM development are determined, and the evaluation index system of geological sweetspot for CBM development is established. On this basis, the fuzzy pattern recognition(FPR) model of geological sweetspot for CBM development is built. The model is applied to evaluate four units of No.3 Coal Seam in the Fanzhuang Block, southern Qinshui Basin, China. The evaluation results are consistent with the actual development effect and the existing research results, which verifies the rationality and reliability of the FPR model. The research shows that the proposed FPR model of geological sweetspot for CBM development does not involve parameter weighting which leads to uncertainties in the results of the conventional models such as analytic hierarchy process and multi-level fuzzy synthesis judgment, and features a simple computation without the construction of multi-level judgment matrix. The FPR model provides reliable results to support the efficient development of CBM.展开更多
In steel plants, estimation of the production system characteristic is highly critical to adjust the system parameters for best efficiency. Although the system parameters may be tuned very well, due to the machine and...In steel plants, estimation of the production system characteristic is highly critical to adjust the system parameters for best efficiency. Although the system parameters may be tuned very well, due to the machine and human factors involved in the production line some deficiencies may occur in product. It is important to detect such problems as early as possible. Surface defects and dimensional deviations are the most important quality problems. In this study, it is aimed to develop an approach to measure the dimensions of metal profiles by obtaining images of them. This will be of use in detecting the deviations in dimensions. A platform was introduced to simulate the real-time environment and images were taken from the metal profile using 4 laser light sources. The shape of the material is generated by combining the images taken from different cameras. Real dimensions were obtained by using image processing and mathematical conversion operations on the images. The results obtained with small deviations from the real values showed that this method can be applied in a real-time production line.展开更多
The objective of this work is to provide an automatic system to count white blood cells in a blood smear. To do so an experiment was assembled, composed by a standard microscope with two step motors coupled to its kno...The objective of this work is to provide an automatic system to count white blood cells in a blood smear. To do so an experiment was assembled, composed by a standard microscope with two step motors coupled to its knobs in order to move the microscope in x and y directions and a web cam which was mounted in the top of the microscope responsible for to acquire images from the smear. The step motors and the web cam are controlled by a microcomputer PC standard via software developed inDelphi. The motors use the parallel port to communicate with the PC and the camera use the USB port. The main idea is to set an initial point into the smear and the automated system will carry over the smear acquiring images (frames with 640 × 480 pixels) and counting the white blood cells encountered. The double histogram threshold technique is implemented to initially exclude the red cells from the image leaving only the white ones. Preliminaries results are obtained and show that the system is quite fast and has a good capacity of selection, even when different kinds of smear are used.展开更多
According to the fundamental theory of visual cognition mechanism and cognitive psychology,the visual pattern recognition model is introduced briefly.Three pattern recognition models,i.e.template_based matching model,...According to the fundamental theory of visual cognition mechanism and cognitive psychology,the visual pattern recognition model is introduced briefly.Three pattern recognition models,i.e.template_based matching model,prototype_based matching model and feature_based matching model are built and discussed separately.In addition,the influence of object background information and visual focus point to the result of pattern recognition is also discussed with the example of recognition for fuzzy letters and figures展开更多
A wide range of methods for geological reservoir modeling has been offered from which a few can reproduce complex geological settings, especially different facies and fracture networks. Multi Point Statistic (MPS) alg...A wide range of methods for geological reservoir modeling has been offered from which a few can reproduce complex geological settings, especially different facies and fracture networks. Multi Point Statistic (MPS) algorithms by applying image processing techniques and Artificial Intelligence (AI) concepts proved successful to model high-order relations from a visually and statistically explicit model, a training image. In this approach, the patterns of the final image (geological model) are obtained from a training image that defines a conceptual geological scenario for the reservoir by depicting relevant geological patterns expected to be found in the subsurface. The aim is then to reproduce these training patterns within the final image. This work presents a multiple grid filter based MPS algorithm to facies and fracture network images reconstruction. Processor is trained by training images (TIs) which are representative of a spatial phenomenon (fracture network, facies...). Results shown in this paper give visual appealing results for the reconstruction of complex structures. Computationally, it is fast and parsimonious in memory needs.展开更多
Fast and accurate plant disease detection is critical to increasing agricultural productivity in a sustainable way.Traditionally,human experts have been relied upon to diagnose anomalies in plants caused by diseases,p...Fast and accurate plant disease detection is critical to increasing agricultural productivity in a sustainable way.Traditionally,human experts have been relied upon to diagnose anomalies in plants caused by diseases,pests,nutritional deficiencies or extreme weather.However,this is expensive,time consuming and in some cases impractical.To counter these challenges,research into the use of image processing techniques for plant disease recognition has become a hot research topic.In this paper,we provide a comprehensive review of recent studies carried out in the area of crop pest and disease recognition using image processing and machine learning techniques.We hope that this work will be a valuable resource for researchers in this area of crop pest and disease recognition using image processing techniques.In particular,we concentrate on the use of RGB images owing to the low cost and high availability of digital RGB cameras.We report that recent efforts have focused on the use of deep learning instead of training shallow classifiers using handcrafted features.Researchers have reported high recognition accuracies on particular datasets but in many cases,the performance of those systems deteriorated significantly when tested on different datasets or in field conditions.Nevertheless,progress made so far has been encouraging.Experimental results showing the leaf disease recognition performance of ten CNN architectures in terms of recognition accuracy,recall,precision,specificity,F1-score,training duration and storage requirements are also presented.Subsequently,recommendations are made on the most suitable architectures to deploy in conventional as well as mobile/embedded computing environments.We also discuss some of the unresolved challenges that need to be addressed in order to develop practical automatic plant disease recognition systems for use in field conditions.展开更多
With rapid urbanization,fires pose significant challenges in urban governance.Traditional fire detection methods often struggle to detect smoke in complex urban scenes due to environmental interferences and variations...With rapid urbanization,fires pose significant challenges in urban governance.Traditional fire detection methods often struggle to detect smoke in complex urban scenes due to environmental interferences and variations in viewing angles.This study proposes a novel multimodal smoke detection method that fuses infrared and visible imagery using a transformer-based deep learning model.By capturing both thermal and visual cues,our approach significantly enhances the accuracy and robustness of smoke detection in business parks scenes.We first established a dual-view dataset comprising infrared and visible light videos,implemented an innovative image feature fusion strategy,and designed a deep learning model based on the transformer architecture and attention mechanism for smoke classification.Experimental results demonstrate that our method outperforms existing methods,under the condition of multi-view input,it achieves an accuracy rate of 90.88%,precision rate of 98.38%,recall rate of 92.41%and false positive and false negative rates both below 5%,underlining the effectiveness of the proposed multimodal and multi-view fusion approach.The attention mechanism plays a crucial role in improving detection performance,particularly in identifying subtle smoke features.展开更多
Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in ...Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.展开更多
Marine environments present significant challenges for image processing due to factors such as low light intensity,suspended particles,and varying degrees of water turbidity.These conditions severely degrade the clari...Marine environments present significant challenges for image processing due to factors such as low light intensity,suspended particles,and varying degrees of water turbidity.These conditions severely degrade the clarity and quality of captured marine images,making accurate image recognition difficult.The problem is further compounded by the limited availability of high-quality,labeled training samples,which restricts the effectiveness of conventional recognition algorithms.Existing techniques in both academic and industrial settings—such as Principal Component Analysis(PCA),Neural Networks,and Wavelet Transforms—typically involve converting color images to grayscale prior to feature extraction.While this simplifies processing,it also results in the loss of essential color information,which is often critical for distinguishing features in marine imagery.To address these issues,this paper proposes a novel approach that preserves and utilizes the full color information of marine images during processing and recognition.The method combines color image representation with Hu's invariant moments to extract stable and rotation-invariant features.These features are then input into a Back Propagation Neural Network(BPNN),which is trained to recognize and classify various marine targets.The integration of color-based feature extraction with BPNN significantly improves recognition performance,particularly under complex environmental conditions.Experimental results show that the proposed system achieves a recognition accuracy exceeding 98%,demonstrating its effectiveness and potential for practical applications in marine exploration,environmental monitoring,and underwater robotics.展开更多
Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in ...Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.展开更多
基金Item Sponsored by National Natural Science Foundation of China(61263015)
文摘To address the problems about the difficulty in accurate recognition of distribution features of gas flow center at blast furnace throat and determine the relationship between gas flow center distribution and gas utilization rate,a method for recognizing distribution features of blast furnace gas flow center was proposed based on infrared image processing,and distribution features of blast furnace gas flow center and corresponding gas utilization rates were categorized by using fuzzy C-means clustering and statistical methods.A concept of gas flow center offset was introduced.The results showed that,when the percentage of gas flow center without offset exceeded 85%,the average blast furnace gas utilization rate was as high as 41%;when the percentage of gas flow center without offset exceeded50%,the gas utilization rate was primarily the center gas utilization rate,and exhibited a positive correlation with no center offset degree;when the percentage of gas flow center without offset was below 50% but the sum of the percentage of gas flow center without offset and that of gas flow center with small offset exceeded 86%,the gas utilization rate depended on both the center and the edges,and was primarily the edge gas utilization rate.The method proposed was able to accurately and effectively recognize gas flow center distribution state and the relationship between it and gas utilization rate,providing evidence in favor of on-line blast furnace control.
文摘Image segmentation is one of important steps on pattern recognition study in the course of wood across-compression. By comparing and studying processing methods in finding cell space and cell wall, this paper puts forward some image segmentation methods that are suitable for study of cell images of wood crossgrained compression. The method of spline function fitting was used for linking edges of cell, which perfects the study of pattern recognition in the course of wood across-compression.
文摘The paper covers analysis and investigation of lighting automation system in low-traffic long-roads. The main objective is to provide optimal solution between expensive safe design that utilizes continuous street lighting system at night for the entire road, or inexpensive design that sacrifices the safety, relying on using vehicles lighting, to eliminate the problem of high cost energy consumption during the night operation of the road. By taking into account both of these factors, smart lighting automation system is proposed using Pattern Recognition Technique applied on vehicle number-plates. In this proposal, the road is sectionalized into zones, and based on smart Pattern Recognition Technique, the control system of the road lighting illuminates only the zone that the vehicles pass through. Economic analysis is provided in this paper to support the value of using this design of lighting control system.
基金financially supported by the National High Technology Research and Development Program of China (863 Program, 2013AA102402)the 521 Talent Project of Zhejiang Sci-Tech University, Chinathe Key Research and Development Program of Zhejiang Province, China (2015C03023)
文摘A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective. A new three-layer detection method was proposed to detect and identify white-backed planthoppers （WBPHs, Sogatella furcifera （Horvath）） and their developmental stages using image processing. In the first two detection layers, we used an AdaBoost classifier that was trained on a histogram of oriented gradient （HOG） features and a support vector machine （SVM） classifier that was trained on Gabor and Local Binary Pattern （LBP） features to detect WBPHs and remove impurities. We achieved a detection rate of 85.6% and a false detection rate of 10.2%. In the third detection layer, a SVM classifier that was trained on the HOG features was used to identify the different developmental stages of the WBPHs, and we achieved an identification rate of 73.1%, a false identification rate of 23.3%, and a 5.6% false detection rate for the images without WBPHs. The proposed three-layer detection method is feasible and effective for the identification of different developmental stages of planthoppers on rice plants in paddy fields.
文摘Aim To study the parking management in the condition of vehicles' increasing. Methods The methods of pattern recognition and image processing were used to analyze the eigenvalues of parking lot images. Results The automatic identification of every parking place in the parking plot was realized. The automatic measuring of parked vehicle count and parking lot utilization was completed. Conclusion It can complete the real time recognition, and has some practicabilities.
基金This project was supported by the National Natural Science Foundation of China (No. 49831060).
文摘Using the Radon transform and morphological image processing, an algorithm for ship's wake detection in the SAR (synthetic aperture radar) image is developed. Being manipulated in the Radon space to invert the gray-level and binary images, the linear texture of ship wake in oceanic clutter can be well detected. It has been applied to the automatic detection of a moving ship from the SEASAT SAR image. The results show that this algorithm is well robust in a strong noisy background and is not very sensitive to the threshold parameter and the working window size.
文摘Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,a large amount of the books are described by Kuzushiji,a type of handwriting cursive script that is no longer in use today and only readable by a few experts.Therefore,researchers are trying to detect and recognise the characters from these books through modern techniques.Unfortunately,the characteristics of the Kuzushiji,such as Connect-Separate-characters and Manyvariation,hinder the modern technique assisted re-organisation.Connect-Separatecharacters refer to the case of some characters connecting each other or one character being separated into unconnected parts,which makes character detection hard.Manyvariation is one of the typical characteristics of Kuzushiji,defined as the case that the same character has several variations even if they are written by the same person in the same book at the same time,which increases the difficulty of character recognition.In this sense,this paper aims to construct an early Japanese book reorganisation system by combining image processing and deep learning techniques.The experimentation has been done by testing two early Japanese books.In terms of character detection,the final Recall,Precision and F-value reaches 79.8%,80.3%,and 80.0%,respectively.The deep learning based character recognition accuracy of Top3 reaches 69.52%,and the highest recognition rate reaches 82.57%,which verifies the effectiveness of our proposal.
文摘The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern drugs.Throughout the extensive history of medicinal plant usage,various plant parts,including flowers,leaves,and roots,have been acknowledged for their healing properties and employed in plant identification.Leaf images,however,stand out as the preferred and easily accessible source of information.Manual plant identification by plant taxonomists is intricate,time-consuming,and prone to errors,relying heavily on human perception.Artificial intelligence(AI)techniques offer a solution by automating plant recognition processes.This study thoroughly examines cutting-edge AI approaches for leaf image-based plant identification,drawing insights from literature across renowned repositories.This paper critically summarizes relevant literature based on AI algorithms,extracted features,and results achieved.Additionally,it analyzes extensively used datasets in automated plant classification research.It also offers deep insights into implemented techniques and methods employed for medicinal plant recognition.Moreover,this rigorous review study discusses opportunities and challenges in employing these AI-based approaches.Furthermore,in-depth statistical findings and lessons learned from this survey are highlighted with novel research areas with the aim of offering insights to the readers and motivating new research directions.This review is expected to serve as a foundational resource for future researchers in the field of AI-based identification of medicinal plants.
文摘A dual-beam electronic speckle pattern interferometry (ESPI) system was adopted to get speckle patterns for the measurement of welding dynamic displacement fields. The mathematical model of this system was described, based on which methods of the ESPI pattern image processing were discussed. Gray transformation and histogram equalization were used to enhance the contrast of speckle patterns. A discrete cosine image processing method was carried out and an exponent low-pass filter was chosen to reduce multiplicative noise in speckle patterns. Speckle grain noise can be eliminated effectively after these processes.
基金Key Project of China National Natural Science Foundation (42230814,52234002)Research Program Foundation of Key Laboratory of Tectonics and Petroleum Resources (China University of Geosciences),Ministry of Education (TPR-2022-17)。
文摘From the perspective of geological zone selection for coalbed methane(CBM) development, the evaluation parameters(covering geological conditions and production conditions) of geological sweetspot for CBM development are determined, and the evaluation index system of geological sweetspot for CBM development is established. On this basis, the fuzzy pattern recognition(FPR) model of geological sweetspot for CBM development is built. The model is applied to evaluate four units of No.3 Coal Seam in the Fanzhuang Block, southern Qinshui Basin, China. The evaluation results are consistent with the actual development effect and the existing research results, which verifies the rationality and reliability of the FPR model. The research shows that the proposed FPR model of geological sweetspot for CBM development does not involve parameter weighting which leads to uncertainties in the results of the conventional models such as analytic hierarchy process and multi-level fuzzy synthesis judgment, and features a simple computation without the construction of multi-level judgment matrix. The FPR model provides reliable results to support the efficient development of CBM.
文摘In steel plants, estimation of the production system characteristic is highly critical to adjust the system parameters for best efficiency. Although the system parameters may be tuned very well, due to the machine and human factors involved in the production line some deficiencies may occur in product. It is important to detect such problems as early as possible. Surface defects and dimensional deviations are the most important quality problems. In this study, it is aimed to develop an approach to measure the dimensions of metal profiles by obtaining images of them. This will be of use in detecting the deviations in dimensions. A platform was introduced to simulate the real-time environment and images were taken from the metal profile using 4 laser light sources. The shape of the material is generated by combining the images taken from different cameras. Real dimensions were obtained by using image processing and mathematical conversion operations on the images. The results obtained with small deviations from the real values showed that this method can be applied in a real-time production line.
文摘The objective of this work is to provide an automatic system to count white blood cells in a blood smear. To do so an experiment was assembled, composed by a standard microscope with two step motors coupled to its knobs in order to move the microscope in x and y directions and a web cam which was mounted in the top of the microscope responsible for to acquire images from the smear. The step motors and the web cam are controlled by a microcomputer PC standard via software developed inDelphi. The motors use the parallel port to communicate with the PC and the camera use the USB port. The main idea is to set an initial point into the smear and the automated system will carry over the smear acquiring images (frames with 640 × 480 pixels) and counting the white blood cells encountered. The double histogram threshold technique is implemented to initially exclude the red cells from the image leaving only the white ones. Preliminaries results are obtained and show that the system is quite fast and has a good capacity of selection, even when different kinds of smear are used.
文摘According to the fundamental theory of visual cognition mechanism and cognitive psychology,the visual pattern recognition model is introduced briefly.Three pattern recognition models,i.e.template_based matching model,prototype_based matching model and feature_based matching model are built and discussed separately.In addition,the influence of object background information and visual focus point to the result of pattern recognition is also discussed with the example of recognition for fuzzy letters and figures
文摘A wide range of methods for geological reservoir modeling has been offered from which a few can reproduce complex geological settings, especially different facies and fracture networks. Multi Point Statistic (MPS) algorithms by applying image processing techniques and Artificial Intelligence (AI) concepts proved successful to model high-order relations from a visually and statistically explicit model, a training image. In this approach, the patterns of the final image (geological model) are obtained from a training image that defines a conceptual geological scenario for the reservoir by depicting relevant geological patterns expected to be found in the subsurface. The aim is then to reproduce these training patterns within the final image. This work presents a multiple grid filter based MPS algorithm to facies and fracture network images reconstruction. Processor is trained by training images (TIs) which are representative of a spatial phenomenon (fracture network, facies...). Results shown in this paper give visual appealing results for the reconstruction of complex structures. Computationally, it is fast and parsimonious in memory needs.
文摘Fast and accurate plant disease detection is critical to increasing agricultural productivity in a sustainable way.Traditionally,human experts have been relied upon to diagnose anomalies in plants caused by diseases,pests,nutritional deficiencies or extreme weather.However,this is expensive,time consuming and in some cases impractical.To counter these challenges,research into the use of image processing techniques for plant disease recognition has become a hot research topic.In this paper,we provide a comprehensive review of recent studies carried out in the area of crop pest and disease recognition using image processing and machine learning techniques.We hope that this work will be a valuable resource for researchers in this area of crop pest and disease recognition using image processing techniques.In particular,we concentrate on the use of RGB images owing to the low cost and high availability of digital RGB cameras.We report that recent efforts have focused on the use of deep learning instead of training shallow classifiers using handcrafted features.Researchers have reported high recognition accuracies on particular datasets but in many cases,the performance of those systems deteriorated significantly when tested on different datasets or in field conditions.Nevertheless,progress made so far has been encouraging.Experimental results showing the leaf disease recognition performance of ten CNN architectures in terms of recognition accuracy,recall,precision,specificity,F1-score,training duration and storage requirements are also presented.Subsequently,recommendations are made on the most suitable architectures to deploy in conventional as well as mobile/embedded computing environments.We also discuss some of the unresolved challenges that need to be addressed in order to develop practical automatic plant disease recognition systems for use in field conditions.
基金supported by the National Natural Science Foundation of China(32171797)Chunhui Project Foundation of the Education Department of China(HZKY20220026).
文摘With rapid urbanization,fires pose significant challenges in urban governance.Traditional fire detection methods often struggle to detect smoke in complex urban scenes due to environmental interferences and variations in viewing angles.This study proposes a novel multimodal smoke detection method that fuses infrared and visible imagery using a transformer-based deep learning model.By capturing both thermal and visual cues,our approach significantly enhances the accuracy and robustness of smoke detection in business parks scenes.We first established a dual-view dataset comprising infrared and visible light videos,implemented an innovative image feature fusion strategy,and designed a deep learning model based on the transformer architecture and attention mechanism for smoke classification.Experimental results demonstrate that our method outperforms existing methods,under the condition of multi-view input,it achieves an accuracy rate of 90.88%,precision rate of 98.38%,recall rate of 92.41%and false positive and false negative rates both below 5%,underlining the effectiveness of the proposed multimodal and multi-view fusion approach.The attention mechanism plays a crucial role in improving detection performance,particularly in identifying subtle smoke features.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R765),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.
文摘Marine environments present significant challenges for image processing due to factors such as low light intensity,suspended particles,and varying degrees of water turbidity.These conditions severely degrade the clarity and quality of captured marine images,making accurate image recognition difficult.The problem is further compounded by the limited availability of high-quality,labeled training samples,which restricts the effectiveness of conventional recognition algorithms.Existing techniques in both academic and industrial settings—such as Principal Component Analysis(PCA),Neural Networks,and Wavelet Transforms—typically involve converting color images to grayscale prior to feature extraction.While this simplifies processing,it also results in the loss of essential color information,which is often critical for distinguishing features in marine imagery.To address these issues,this paper proposes a novel approach that preserves and utilizes the full color information of marine images during processing and recognition.The method combines color image representation with Hu's invariant moments to extract stable and rotation-invariant features.These features are then input into a Back Propagation Neural Network(BPNN),which is trained to recognize and classify various marine targets.The integration of color-based feature extraction with BPNN significantly improves recognition performance,particularly under complex environmental conditions.Experimental results show that the proposed system achieves a recognition accuracy exceeding 98%,demonstrating its effectiveness and potential for practical applications in marine exploration,environmental monitoring,and underwater robotics.
基金supported by the National Natural Science Foundation of China(Grant Nos.11934011,12074339,62075194,U21A6006,62202418,and U21B2004)the National Key Research and Development Program of China(Grant Nos.2019YFA0308100,2023YFB2806000,and 2022YFA1204700)+4 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB28000000)the Leading Innovation and Entrepreneurship Team in Zhejiang Province(Grant No.2020R01001)the Open Program of the State Key Laboratory of Advanced Optical Communication Systems and Networks at Shanghai Jiao Tong University(Grant No.2023GZKF024)the Fundamental Research Funds for the Central Universities,the Information Technology Center and State Key Lab of CAD&CG at the Zhejiang University,the Zhejiang Provincial Key Laboratory of Information Processing,Communication and Networking(IPCAN)the National Institutes of Health(NIH)(Grant Nos.R01GM127696,R01GM152633,R21GM142107,and R21CA269099)。
文摘Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.
