On-line Recognition System Research Articles

Electroencephalogram-Based Facial Gesture Recognition Using Self-Organizing Map.

Brain-computer interfaces (BCIs) allow information to be transmitted directly from the human brain to a computer, enhancing the ability of human brain activity to interact with the environment. In particular, BCI-based control systems are highly desirable because they can control equipment used by people with disabilities, such as wheelchairs and prosthetic legs. BCIs make use of electroencephalograms (EEGs) to decode the human brain's status. This paper presents an EEG-based facial gesture recognition method based on a self-organizing map (SOM). The proposed facial gesture recognition uses α, β, and θ power bands of the EEG signals as the features of the gesture. The SOM-Hebb classifier is utilized to classify the feature vectors. We utilized the proposed method to develop an online facial gesture recognition system. The facial gestures were defined by combining facial movements that are easy to detect in EEG signals. The recognition accuracy of the system was examined through experiments. The recognition accuracy of the system ranged from 76.90% to 97.57% depending on the number of gestures recognized. The lowest accuracy (76.90%) occurred when recognizing seven gestures, though this is still quite accurate when compared to other EEG-based recognition systems. The implemented online recognition system was developed using MATLAB, and the system took 5.7 s to complete the recognition flow.

Paddle-OCR-Based Real-Time Online Recognition System for Steel Plate Slab Spray Marking Characters

Paddle-OCR-Based Real-Time Online Recognition System for Steel Plate Slab Spray Marking Characters

Social IoT Approach to Cyber Defense of a Deep-Learning-Based Recognition System in Front of Media Clones Generated by Model Inversion Attack

Model inversion attack (MIA) is a cyber threat with an increasing alert even for deep-learning-based recognition systems (DLRSs). By targeting a DLRS under a scenario of attacker access to the model structure and parameters, MIA generates a data clone for a certain targeted class label. To avoid the possible threats of such MIA-generated data clones, this research work proposes a social IoT approach to a collaborative cyber-defense among the online recognition systems (RSs) sharing the targeted class label. Since, the generation of an MIA-clone is by targeting an RS model and using its structure, parameters, and class labels output scores in an iterative optimization process, the generated clone is partially inherent to the targeted model. Thus, it is expected for an MIA-clone to show a different performance on a secondary RS wherein the same targeted class label is included. It is because, in the MIA generation of the clone, not only the targeted class label but also other class labels, and model parameters and structure affect the process, while the second model has just the targeted class label in common with the target model. Deploying the Social Internet of Recognition Systems (SIoRS), the proposed technique utilizes a collaborative recognition by SIoRC which plays the role of a complementary recognition besides the targeted RS. The recognition output by the targeted RS is further verified by the SIoRS complementary recognition result. To avoid the MIA-targeted data clones, the verification of recognition is by the log-likelihood ratio test between the targeted RS and the SIoRS complementary recognition confidence scores. The proposed technique is evaluated by statistical analysis on deep face RSs in 10 000 Monte Carlo runs for each of the conventional, dc-generative adversarial network (GAN) and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha$</tex-math> </inline-formula> -GAN integrated MIA techniques in targeting two different user identities. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Z$</tex-math> </inline-formula> scores of the fitted normal distribution of the log-likelihood ratios indicate almost <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$100\%$</tex-math> </inline-formula> detection rate of clones generated by conventional MIA and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$95.23\%$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$86\%$</tex-math> </inline-formula> of clones, respectively, generated by DC-GAN and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha$</tex-math> </inline-formula> -GAN integrated deep MIA techniques.

Classification of whole slide images of breast histopathology based on spatial correlation characteristics

目的 病理学检查是明确乳腺癌诊断及肿瘤类型的金标准。深度神经网络广泛应用于乳腺病理全切片的诊断工作并取得了明显进展，但是现有大多数工作只是将全切片切割成小图像块，对每个图像块进行单独处理，没有考虑它们之间的空间信息。为此，提出了一种融合空间相关性特征的乳腺组织病理全切片分类方法。方法 首先基于卷积神经网络对病理图像块进行预测，并提取每个图像块有代表性的深层特征，然后利用特征融合将图像块及其周围图像的特征进行聚合，以形成具有空间相关性的块描述符，最后将全切片图像中最可疑的块描述符传递给循环神经网络，以预测最终的全切片级别的分类。结果 本文构建了一个经过详细标注的乳腺病理全切片数据集，并在此数据集上进行良性/恶性二分类实验。在自建的数据集中与3种全切片分类方法进行了比较。结果表明，本文方法的分类精度达到96.3%，比未考虑空间相关性的方法高出了1.9%，与基于热力图特征和基于空间性和随机森林的方法相比，分类精度分别高出8.8%和1.3%。结论 本文提出的乳腺组织病理全切片识别方法将空间相关性特征融合和RNN分类集成到一个统一模型，有助于提高图像识别准确率，为病理图像诊断工作提供了高效的辅助诊断工具。;Objective Pathological examination can be as the“gold standard”to interpret breast cancer diagnosis and its tumor types. To improve the treatment effect of breast cancer，accurate interpretation is beneficial to clarify the type of the disease early and effectively. However，it is time-consuming to check the pathological whole slide images（WSIs）manually，and the diagnosis result is easily affected by personal experience. Due to computer vision-based convolutional neural networks（CNNs）are applied to the classification task of histopathological images computer-aided diagnostic（CAD）techniques for digital images of histopathology has been developing intensively. However，it is still challenged to split largesized WSIs into small patches and each patch is processed individually without the spatial information between them. Also， the information-involved of the patches learned is not utilized in the small size patch feature aggregation process. To resolve these problems，we develop a spatial correlation-based classification method for breast histopathology images，which can re-identify the WSIs classification problem through deep learning feature fusion and recurrent neural network（RNN）based classification. Method Our demonstration consists of four aspects：1）pre-processing operation of WSIs，2）CNN-based breast patch prediction，3）image patch feature fusion，and 4）RNN-based WSIs classification. First，it is focused on a preprocessing operation on whole slide images of breast pathology，using a sliding window to cut the WSIs into patches of a suitable size in terms of a CNN. Second，CNN-based patch prediction is used to predict the possibility of cancer in each patch and each patch is encoded as a fixed-length feature. To reduce unpredictable class of cancerous patch being classified as non-cancerous patch，the ResNet34 is used as the patch classification model and penalty factors is added in Focal loss. Third，the feature fusion of image blocks can be recognized as a feature fusion niche that takes the entire grid of patches as input and the spatial correlation of patches and their surrounding patches are as feature fusion of all patches within the grid，thus block descriptors are formed. Feature fusion methods are involved in，including 1）Weight，2）Max， 3）Avg，4）Norm3，and 5）WeightNorm3. Finally，the RNN-based WSIs classification is used to pass the block feature descriptors with high probability of cancer in each WSIs to the RNN，and the RNN model is used to learn the sequence relationship between the image block feature sequences. It can expand the processing field of view of the classification model to multiple Blocks and optimize the classification accuracy of breast pathology WSIs. Additionally，we design and develop an online recognition system for assistance. Result A detailed annotated whole slide images dataset of breast pathology is constructed，and benign/malignant dichotomous classification experiments are carried out on this dataset. The results are compared to three WSIs classification methods in the self-constructed dataset，and it shows that the classification accuracy of the method can be reached to 96. 3%，which is 1. 9% higher than non-spatial correlation method. The classification accuracy of each is 8. 8% and 1. 3% higher compared to heat map features-based methods and spatial correlation and random forest-related methods. Conclusion The proposed breast pathology recognition method can improve image recognition accuracy and provide an efficient diagnostic aid for pathology image diagnosis work，which integrates feature fusion and RNN classification into a synthesized model.

Motor Imagery EEG Decoding Based on Multi-scale Hybrid Networks and Feature Enhancement.

Motor Imagery (MI) based on Electroencephalography (EEG), a typical Brain-Computer Interface (BCI) paradigm, can communicate with external devices according to the brain's intentions. Convolutional Neural Networks (CNN) are gradually used for EEG classification tasks and have achieved satisfactory performance. However, most CNN-based methods employ a single convolution mode and a convolution kernel size, which cannot extract multi-scale advanced temporal and spatial features efficiently. What's more, they hinder the further improvement of the classification accuracy of MI-EEG signals. This paper proposes a novel Multi-Scale Hybrid Convolutional Neural Network (MSHCNN) for MI-EEG signal decoding to improve classification performance. The two-dimensional convolution is used to extract temporal and spatial features of EEG signals and the one-dimensional convolution is used to extract advanced temporal features of EEG signals. In addition, a channel coding method is proposed to improve the expression capacity of the spatiotemporal characteristics of EEG signals. We evaluate the performance of the proposed method on the dataset collected in the laboratory and BCI competition IV 2b, 2a, and the average accuracy is at 96.87%, 85.25%, and 84.86%, respectively. Compared with other advanced methods, our proposed method achieves higher classification accuracy. Then we use the proposed method for an online experiment and design an intelligent artificial limb control system. The proposed method effectively extracts EEG signals' advanced temporal and spatial features. Additionally, we design an online recognition system, which contributes to the further development of the BCI system.

A Multifeatured Time–Frequency Neural Network System for Classifying sEMG

Human gesture-related electromyographic signal in intelligent recognition systems has attracted widespread attention. The EMG signal is the temporal and spatial superposition of motor unit neural potentials and it contains nonlinear and complex characteristics. Despite the previous efforts, recognizing more different actions and building an online recognition system remain challenging. To address these issues, we construct a multi-feature time-frequency neural network system and a dataset which contains twenty kinds of hand movements. In a multi-featured time-frequency neural network system, the multi-layer CNN structure is used to obtain faster recognition and better classification results. The experimental results demonstrate that equipment and algorithmic model can reach a 94.66% accuracy. Our approach focuses on processing multiple time and frequency domain features of sEMG using CNN. Importantly, we also perform real-time validation. The system can accurately recognize hand movements to control UAV motion in real-time, in which case system classification takes 0.05s. This demonstrates the practicality and effectiveness of the sEMG acquisition system based on the multifeatured time-frequency neural network.

Image Recognition Algorithm Based on Artificial Intelligence and Machine Learning

At present, most of the existing image recognition methods are not only cumbersome in process but also require manual design of functions, resulting in poor recognition results and time-consuming training. This study explores image recognition algorithms based on artificial intelligence and machine learning, which can simulate the hierarchical structure of the human brain and nervous system, realize automatic extraction of complex features, and have powerful data representation capabilities. In this study, the structure of artificial neuron is introduced first, and the training process of the neural network is introduced in detail. At the same time, this study improves the traditional training algorithm and proposes two new machine learning models for different application scenarios, which effectively improves the performance of the optimal model. In relevant tests, the effect is significant. On the basis of these improved algorithms, an online recognition system is designed and implemented. The recognition accuracy rate of the system for the hidden layer reaches more than 90%, which verifies the effectiveness of the technology. At the same time, after repeated experiments, the results show that the multiview algorithm effectively solves the problem that the recognition results of the traditional multiview algorithm are affected by the size of the target contour.

Deblurring Method of Face Recognition AI Technology Based on Deep Learning

As a common method of deep learning, a convolutional neural network (CNN) shows excellent performance in face recognition. The features extracted by traditional face recognition methods are greatly influenced by subjective factors and are time-consuming and laborious. In addition, these images are susceptible to illumination, expression, occlusion, posture, and other factors, which bring a lot of interference to the computer face recognition and increase recognition difficulty. Deep learning is the most important technical means in the field of computer vision. The participation of this technology reduces manual participation and can identify the identity of visitors from multiple aspects. This study, based on the introduction at all levels and on the fundamental principle of the colloidal neural network, combines the basic model and the common exploitation methods of aspects to make a model of a combination of multiple aspects. Then, an improved CNN-based multifeature fusion face recognition model is proposed, and the effectiveness of the model in face feature extraction is verified by experiments. With the experimental results, the identification rate for the ORL and Yale data sets is 98.2% and 98.8%, respectively. Accordingly, an online face detection system and recognition system based on the combination of element models are designed. The system can obtain dynamic facial recognition and meet the recognition rate of the design requirements. The system is training four detection models and online recognition, and the test results show that the noise component model has the highest recognition rate, and the recognition rate has improved by 13% compared with the baseline capacity, further verifying that a model of a combination of features can achieve more effectively.

Automatic Fungi Recognition: Deep Learning Meets Mycology.

The article presents an AI-based fungi species recognition system for a citizen-science community. The system’s real-time identification too — FungiVision — with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset — Danish Fungi 2020 (DF20) — with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities.

Multi-lingual character handwriting framework based on an integrated deep learning based sequence-to-sequence attention model

Online signals are rich in dynamic features such as trajectory chronology, velocity, pressure and pen up/down movements. Their offline counterparts consist of a set of pixels. Thus, online handwriting recognition accuracy is generally better than offline. In this paper, we propose an original framework for recovering temporal order and pen velocity from offline multi-lingual handwriting. Our framework is based on an integrated sequence-to-sequence attention model. The proposed system involves extracting a hidden representation from an image using a convolutional neural network (CNN) and a bidirectional gated recurrent unit (BGRU), and decoding the encoded vectors to generate dynamic information using a BGRU with temporal attention. We validate our framework using an online recognition system applied to a benchmark Latin, Arabic and Indian On/Off dual-handwriting character database. The performance of the proposed multi-lingual system is demonstrated through a low error rate of point coordinates and high accuracy system rate.

Stroke Extraction for Offline Handwritten Mathematical Expression Recognition

Offline handwritten mathematical expression recognition is often considered much harder than its online counterpart due to the absence of temporal information. In order to take advantage of the more mature methods for online recognition and save resources, an oversegmentation approach is proposed to recover strokes from textual bitmap images automatically. The proposed algorithm first breaks down the skeleton of a binarized image into junctions and segments, then segments are merged to form strokes, finally stroke order is normalized by using recursive projection and topological sort. Good offline accuracy was obtained in combination with ordinary online recognizers, which are not specially designed for extracted strokes. Given a ready-made state-of-the-art online handwritten mathematical expression recognizer, the proposed procedure correctly recognized 58.22%, 65.65%, and 65.22% of the offline formulas rendered from the datasets of the Competitions on Recognition of Online Handwritten Mathematical Expressions(CROHME) in 2014, 2016, and 2019 respectively. Furthermore, given a trainable online recognition system, retraining it with extracted strokes resulted in an offline recognizer with the same level of accuracy. On the other hand, the speed of the entire pipeline was fast enough to facilitate on-device recognition on mobile phones with limited resources. To conclude, stroke extraction provides an attractive way to build optical character recognition software.

Development of a Recognition System for Spraying Areas from Unmanned Aerial Vehicles Using a Machine Learning Approach.

Unmanned aerial vehicle (UAV)-based spraying systems have recently become important for the precision application of pesticides, using machine learning approaches. Therefore, the objective of this research was to develop a machine learning system that has the advantages of high computational speed and good accuracy for recognizing spray and non-spray areas for UAV-based sprayers. A machine learning system was developed by using the mutual subspace method (MSM) for images collected from a UAV. Two target lands: agricultural croplands and orchard areas, were considered in building two classifiers for distinguishing spray and non-spray areas. The field experiments were conducted in target areas to train and test the system by using a commercial UAV (DJI Phantom 3 Pro) with an onboard 4K camera. The images were collected from low (5 m) and high (15 m) altitudes for croplands and orchards, respectively. The recognition system was divided into offline and online systems. In the offline recognition system, 74.4% accuracy was obtained for the classifiers in recognizing spray and non-spray areas for croplands. In the case of orchards, the average classifier recognition accuracy of spray and non-spray areas was 77%. On the other hand, the online recognition system performance had an average accuracy of 65.1% for croplands, and 75.1% for orchards. The computational time for the online recognition system was minimal, with an average of 0.0031 s for classifier recognition. The developed machine learning system had an average recognition accuracy of 70%, which can be implemented in an autonomous UAV spray system for recognizing spray and non-spray areas for real-time applications.

Online Handwritten Gurmukhi Character Recognition using Hybrid Feature Set

Online handwriting character recognition is gaining attention from the researchers across the world because with the advent of touch based devices, a more natural way of communication is being explored. Stroke based online recognition system is proposed in this paper for a very complex Gurmukhi script. In this effort, recognition for 35 basic characters of Gurmukhi script has been implemented on the dataset of 2019 Gurmukhi samples. For this purpose, 32 stroke classes have been considered. Three types of features have been extracted. Hybrid of these features has been proposed in this paper to train the classification models. For stroke classification, three different classifiers namely, KNN, MLP and SVM are used and compared to evaluate the effectiveness of these models. A very promising “stroke recognition rate” of 94% by KNN, 95.04% by MLP and 95.04% by SVM has been obtained.

Online Recognition Approach of Arabic Numerals Using Matching Alignment Algorithm

Online text recognition systems have been continually given due importance these days globally because of the rapidly developing touch screen gadgets. However, it has been difficult to utilize keyboards and external mouse-like inputs in significantly tinier devices which consequently paved the way to current researched based scientists to look for some newer techniques which could design such type of online systems which could further deal with different kinds of texts for example, digits, symbols and alphabets. In the present paper, an online system for recognizing manually written Arabic numerals is being given. This paper will show digit acquisition, preprocessing, feature extraction and recognition phases in detail. The set of the data was gathered from 100 writers using a touch screen PC with 100 samples of every digit. The average accuracy rate of the outcome of the test of this proposed system was 98%, which is a significant accuracy rate.

Toward a Wearable RFID System for Real-Time Activity Recognition Using Radio Patterns

Elderly care is one of the many applications supported by real-time activity recognition systems. Traditional approaches use cameras, body sensor networks, or radio patterns from various sources for activity recognition. However, these approaches are limited due to ease-of-use, coverage, or privacy preserving issues. In this paper, we present a novel wearable Radio Frequency Identification (RFID) system aims at providing an easy-to-use solution with high detection coverage. Our system uses passive tags which are maintenance-free and can be embedded into the clothes to reduce the wearing and maintenance efforts. A small RFID reader is also worn on the user's body to extend the detection coverage as the user moves. We exploit RFID radio patterns and extract both spatial and temporal features to characterize various activities. We also address the issues of false negative of tag readings and tag/antenna calibration, and design a fast online recognition system. Antenna and tag selection is done automatically to explore the minimum number of devices required to achieve target accuracy. We develop a prototype system which consists of a wearable RFID system and a smartphone to demonstrate the working principles, and conduct experimental studies with four subjects over two weeks. The results show that our system achieves a high recognition accuracy of 93.6 percent with a latency of 5 seconds. Additionally, we show that the system only requires two antennas and four tagged body parts to achieve a high recognition accuracy of 85 percent.

On-line structure-based handwritten Chinese phonetic symbol recognition

This paper proposes a high-accuracy on-line structure-based handwritten Chinese phonetic symbol recognition system. Each reference symbol consists of visible and hidden line segments, where two line segments intersecting each other form an X-shape structure, and those forming a crucial T-shape structure mark a T-shape structure. The first-stage recognition performs the structure-based dynamic programming to match the input handwriting with reference symbols. The second-stage recognition performs the partialmerge dynamic programming to reevaluate the similarity between the input handwriting and the candidate symbols in a confusing set. The third-stage recognition performs the structure-constrained confirmation to determine the best candidate.

An Efficient and Effective Automatic Recognition System for Online Recognition of Foreign Fibers in Cotton

Preventing foreign fibers from being mixed with cotton is essential for producing high-quality cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This paper proposes an efficient recognition system to accurately recognize foreign fibers mixed in cotton. The core component of the proposed system is an efficient classifier based on the kernel extreme learning machine (KELM). A two-step grid search strategy, which integrates a coarse search with a fine search, is adopted to train an optimal KELM recognition model. The resultant model is compared with the support vector machine and extreme learning machine on a real data set using tenfold cross-validation analysis. The experimental results show that the proposed recognition system can achieve classification accuracy as high as 93.57%, which is superior to the other two state-of-the-art systems. The results clearly confirm the superiority of the developed model in terms of classification accuracy. Promisingly, the proposed system can serve as a new candidate of powerful foreign fiber recognition systems with excellent performance.

Film Defects of Lithium Battery Recognition Based on Brightness and One-against-All Support Vector Machine

Lithium battery film on-line defect recognition system is realized based on industrial charge-coupled device (CCD) to improve quality. Otsu algorithm is adopted for threshold instead of traditional method. Area of defect is sorted to get the largest defect and geometry and projective is extracted from image. Film defects of lithium battery recognition is realized based on Brightness Judgment and One-against-all support vector machine (OAA-SVM). Experiment results show that these methods are effective and feasible, the accuracy can reach 90%.

Recent developments in the study of rapid human movements with the kinematic theory: Applications to handwriting and signature synthesis

Human movement modeling can be of great interest for the design of pattern recognition systems relying on the understanding of the fine motor control (such as on-line handwriting recognition or signature verification) as well as for the development of intelligent systems involving in a way or another the processing of human movements. In this paper, we briefly list the different models that have been proposed in order to characterize the handwriting process and focus on a representation involving a vectorial summation of lognormal functions: the Sigma–lognormal model. Then, from a practical perspective, we describe a new stroke extraction algorithm suitable for the reverse engineering of handwriting signals. In the following section it is shown how the resulting representation can be used to study the writer and signer variability. We then report on two joint projects dealing with the automatic generation of synthetic specimens for the creation of large databases. The first application concerns the automatic generation of totally synthetic signature specimens for the training and evaluation of verification performances of automatic signature recognition systems. The second application deals with the synthesis of handwritten gestures for speeding up the learning process in customizable on-line recognition systems to be integrated in electronic pen pads.

On-line surface roughness recognition system by vibration monitoring in CNC turning using adaptive neuro-fuzzy inference system (ANFIS)

This study presents a new method for modeling an adaptive neuro-fuzzy inference system (ANFIS) based on vibration for predicting surface roughness in the CNC turning process. The input parameters of the model are insert nose radius, cutting speed, feed rate, depth of cut and vibration amplitude, which determine the output parameter of the surface roughness. A Gauss type membership function was used to train on ANFIS. The predicted values derived from ANFIS were compared with experimental data. The obtained prediction accuracy of 97.52% demonstrates that the developed system’s improved performance over other models available in the literature. The resulting ANFIS model based on vibration efficiently uses the fuzzy inference system for predicting surface roughness in turning of AISI 1040 steel. Key words: Adaptive neuro-fuzzy inference system (ANFIS), CNC turning, surface roughness, prediction model.