Design Of Recognition System Research Articles

Design and Implementation of Chess and Card Recognition System Based on Deep Learning

In order to improve the speed and accuracy of mahjong factory packaging detection, the neural network-based chess and card recognition system designed in this paper mainly includes image preprocessing and image recognition. The image preprocessing uses the OpenCV computer vision library to segment the complete chess and cards into individual chess and cards. It is mainly to grayscale the image, use Gaussian blur to denoise the image, calculate the gradient of the image, transform the gradient image into a threshold image, perform morphological operations on the image, and perform contour detection to find the surrounding matrix of the contour. The target and the background can be divided by the vertex coordinates, and a 9x4 grid is superimposed on the divided target image and can be divided into a single mahjong chess card for neural network recognition. Image recognition uses the Vision Transformer neural network. In this paper, we first use the convolution layer to obtain the feature map, and use the feature map as the input of the Vision Transformer. The data set is mainly derived from the shooting of the mobile phone and the image expansion. Here, the image is mainly expanded according to the image brightness, blur and rotation at a certain angle. Finally, the accuracy rate of the model on the test set can reach 98%. Finally, the trained model is deployed on the android mobile terminal using TensorFlow-Lite.

Feature Selection for Continuous within- and Cross-User EEG-Based Emotion Recognition

The monitoring of emotional state is important in the prevention and management of mental health problems and is increasingly being used to support affective computing. As such, researchers are exploring various modalities from which emotion can be inferred, such as through facial images or via electroencephalography (EEG) signals. Current research commonly investigates the performance of machine-learning-based emotion recognition systems by exposing users to stimuli that are assumed to elicit a single unchanging emotional response. Moreover, in order to demonstrate better results, many models are tested in evaluation frameworks that do not reflect realistic real-world implementations. Consequently, in this paper, we explore the design of EEG-based emotion recognition systems using longer, variable stimuli using the publicly available AMIGOS dataset. Feature engineering and selection results are evaluated across four different cross-validation frameworks, including versions of leave-one-movie-out (testing with a known user, but a previously unseen movie), leave-one-person-out (testing with a known movie, but a previously unseen person), and leave-one-person-and-movie-out (testing on both a new user and new movie). Results of feature selection lead to a 13% absolute improvement over comparable previously reported studies, and demonstrate the importance of evaluation framework on the design and performance of EEG-based emotion recognition systems.

Unique three‐component co‐assembly among AIEgen, L‐GSH, and Ag+ for the formation of helical nanowires

AbstractNature has selected, produced, and evolved numerous molecular architectural motifs over billions of years for particular bio‐functions. During this process, molecular self‐assembly plays a critically important role. Inspired by these delicate assemblies, scientists devote themselves to developing various sophisticated complexes assembled by diverse and numerous structural motifs. By far, most of the examples focus on single‐molecule self‐assembly or co‐assembly between two molecules, seldom works report the co‐assembly among three building blocks due to the substantially increased complexity and decreased controllability. Here we report a novel three‐component co‐assembly among L‐glutathione (L‐GSH), AgNO3, and an aggregation‐induced emission luminogen (AIEgen), namely triphenylamine–pyridinium (abbreviated to TPA‐Py). TPA‐Py, L‐GSH, and Ag+ co‐assemble into numerous long and ordered nanowires with left‐handed helices, which show remarkable AIE properties that can be observed by naked eyes. This effect is only detected in this system, the replacement of TPA‐Py with other AIEgens, L‐GSH with other cysteine derivatives or anions, Ag+ with other metal ions, could not lead to the unique AIE effect, which endows this system with high specificity and controllability. This work provides new insight into the design of biomolecule recognition systems and discloses that ternary co‐assembly could become a facile route to build sophisticated nanobiomaterials.

Bald eagle search optimization with deep transfer learning enabled age-invariant face recognition model

Facial aging variation is a challenging process in the design of face recognition system because of high intra-personal differences instigated by age progression. Age-invariant face recognition (AIFR) models find applicability in several real time applications such as criminal identification, missing person detection, and so on. The main issue is the high intra-personal disparities because of complicated and non-linear age progression process. An essential component of face recognition model is the extraction of important features from the facial images for reducing intrapersonal differences produced by illumination, expression, pose, age, etc. The recent advances of machine learning (ML) and deep learning (DL) models pave a way for effective design of AIFR models. In this view, this study presents a new Bald Eagle Search Optimization with Deep Transfer Learning Enabled AFIR (BESDTL-AIFR) model. The presented BESDTL-AIFR model primarily pre-processes the facial images to enhance the quality. Besides, the BESDTL-AIFR model utilizes Inception v3 model for learning high level deep features. Next, these features are passed into the optimal deep belief network (DBN) model for face recognition. Finally, the hyperparameters of the DBN model are optimally chosen by the use of BES algorithm. Experimentation analysis on challenging benchmark datasets pointed out the promising outcomes of the BESDTL-AIFR model compared to recent approaches. • Develop a deep learning based Age-Invariant Face Recognition model. • Employ Inception v3 feature extractor with DBN classification model. • Present bald eagle search optimization based hyperparameter tuning process. • Validate the performance of BESDTL-AIFR model on UTKFace and CACD dataset.

Design of a Sugarcane Diseases Recognition System Based on GoogLeNet for a Web Application

—Sugarcane diseases in Peru occur due to the agricultural community's lack of understanding of these, which means a slow response to the application of methods of control and eradication of these diseases; thus, causing economic losses and underproduction. Due to the aforementioned, a web application for sugarcane diseases recognition is proposed. The five types of sugarcane diseases that will be recognized using this system are: Pineapple Sett Rot, Ring Spot, Mosaic, Brown Rust and Leaf Scorch. This system was developed using GoogLeNet, which is a 22 layers convolutional neural network (CNN), and also the Matlab software and its App Designer extensions (for the web application creation); additionally, Matlab Web App Server was used to host the application on the web. The pre-trained neural network developed in Matlab based on the GoogLeNet architecture allowed the creation and configuration of the training parameters (supervised learning) that were evaluated, and it was considered convenient to split the data between training, validation and testing (70%, 20% and 10%, respectively). A total of 250 images composed of 50 images for each disease were used. The web application was designed in App Designer which provided us with a set of tools and a programming interface for the insertion of the trained CNN, with a validation percentage of 94.67% obtained by varying the number of epochs, reaching a maximum of 6000 iterations. Finally, the web application supported by the Matlab Web App Server was generated and tests were performed on a local network, resulting in a web application capable of identifying images within the established guidelines, with an accuracy rate of 96%

SEMG-Based Gesture Recognition Using Deep Learning From Noisy Labels.

Gesture recognition for myoelectric prosthesis control utilizing sparse multichannel surface Electromyography (sEMG) is a challenging task, and from a Muscle-Computer Interface (MCI) standpoint, the performance is still far from optimal. However, the design of a well-performed sEMG recognition system depends on the flexibility of the input-output function and the dataset's quality. To improve the performance of MCI, we proposed a novel gesture recognition framework that (i) Enrich the spectral information of the sparse sEMG signals by constructing a fused map image (denoted as sEMG-Map) that integrates a multiresolution decomposition (by means of orthogonal wavelets) through the raw signals then rely upon the Convolutional Neural Network (CNN) capacity to exploit the composite hierarchies in the constructed sEMG-Map input. (ii) Deals with the label noise by proposing a data-centric method (denoted as ALR-CNN) that synchronously refines the falsely labeled samples and optimizes the CNN model based on two basic assumptions. First, the deep model accuracy improves as the training progress. Second, a set of successive learnable max-activated outputs of a well-performed deep model is a reliable estimator for motion detection in the muscle activation pattern. Our proposed framework is evaluated on three large-scale public databases. The average classification accuracy is 95.50%, 95.85%, and 85.58% for NinaPro DB2, NinaPro DB7, and NinaPro DB3, respectively. The experimental results verify the effectuality of the proposed method and show high accuracy.

Design of the Vocal Music Feature Recognition System Based on the Internet of Things Technology

In order to meet the needs of vocal feature recognition, the author proposes a system design based on the Internet of things technology. The principle of the method is that the body sensory layer of the body puts the sound sensors in different positions, records the primary sound signal, and monitors and makes the sound signal using the TMS320VC5402 light red processor. The network transport layer audio signal processes and sends the voice signal database in the process layer. The sound characteristic analysis module in the application layer uses a real-time dynamic change algorithm to obtain the best similarity between the experimental model and the design, identify the characteristics of the sound set red, and identify the content of the voice feature, the music, and the emotional results of the song. Experiments have shown that the system is capable of recognizing speech in a noisy environment, with an accuracy of approximately 95%, resulting in better sound control and the ability to switch switches and remote control. The system, developed with the Internet of things technology, has been proven to improve voice recognition.

Design of Abnormal Heart Sound Recognition System Based on HSMM and Deep Neural Network.

IntroductionHeart sound signal is an important physiological signal of human body, and the identification and research of heart sound signal is of great significance.MethodsFor abnormal heart sound signal recognition, an abnormal heart sound recognition system, combining hidden semi-Markov models (HSMM) with deep neural networks, is proposed. Firstly, HSMM is used to build a heart sound segmentation model to accurately segment the heart sound signal, and then the segmented heart sound signal is subjected to feature extraction. Finally, the trained deep neural network model is used for recognition.ResultsCompared with other methods, this method has a relatively small amount of input feature data and high accuracy, fast recognition speed.DiscussionHSMM combined with deep neural network is expected to be deployed on smart mobile devices for telemedicine detection.

Design and Implementation of a Face Recognition System Using ZEDboard

Design and Implementation of a Face Recognition System Using ZEDboard

Hadoop Small Image Processing Technology Based on Big Data Processing and Its Application Effect in Face Feature Extraction and Face Recognition System Design

From standard software to crucial applications, face recognition (FR) is always at the core of many unique advances over the past 20 years. Big data is a rapidly growing collection of data. It is important in many applications such as medical, academic, and industries, and it refers to vast data sources that are hard to analyze, store, and interpret for subsequent procedures. Hadoop is an open-source large data processing platform that stores and analyses data in scalable computer clusters. FR technology is built on Hadoop processing to boost the effectiveness of recognition using MapReduce computing. This paper presents a novel adaptive fine-tuned AdaBoost (AFTA) algorithm to enhance the FR in the Hadoop processing. Collected face data sets are employed in preprocessing stage to normalize and enhance the superiority through the median filter (MF) and contour-based image enhancement (CIE), correspondingly. To handle vast quantities of the data, boosted k-means clustering (BKC) approach is used over the Hadoop servers for the MapReduce process. The binary partition tree (BPT) approach is employed in the segmentation stage to split the data into many subgroups. To lessen the dimension of the data, we use the Gabor filter. To select the consistent features, threshold-based binary particle swarm optimization (T-BPSO) is applied. Then, our proposed technique is utilized in the FR process. Finally, the performance metrics of the proposed technique are examined and compared with existing techniques to accomplish our research with the greatest effectiveness. For accuracy, precision, recall, and F-score, we attained the proposed (AFTA) values of 99.67, 97.13, 95.21, and 94.11, respectively. The outcomes are depicted in graphical representation by employing the MATLAB tool.

Research and design of a rapid nuclide recognition system

Due to possible nuclear accidents as a radioactive source loss as happened in Nanjing, China, there is demand for rapid identification of nuclides. This paper proposes a new recognition algorithm based on sequential Bayes that reduces the time required for that identification. A nuclide identification system was built by appropriate detector selection, electronic design, and software programming. Experiments show that the radioactive sources 137Cs (with an activity of 46500 Bq) and 60Co (with an activity of 39000 Bq) at a distance of 40 cm from the detection system can be distinguished rapidly within 3.0 and 4.1 s respectively with a detection rate reaching 100%.

Design and Implementation of W-shaped Steel Band Hole Image Recognition System Based on OpenCV-Python

The mine Roofbolter is widely used in drilling and supporting of underground roof and side wall, which greatly alleviates the imbalance of driving anchor. However, with the progress of sensor technology, electrical and electronic technology, electro-hydraulic proportional control technology and the continuous improvement of users’ requirements for the safety and efficiency of bolt support, domestic and foreign mining equipment manufacturers have carried out the development of automatic bolt and anchor cable support equipment, especially to improve the performance requirements of control system and develop intelligent visualization technology. At present, the hole location in the process of drilling still needs to be identified and located by human eyes, which is inefficient and the working environment is a great threat to the physical and mental health of personnel, so it is urgent to introduce computer technology and artificial intelligence technology. In this paper, with the help of image recognition technology, machine vision recognition replaces human eye recognition of hole location, and puts forward an image recognition technology of W-shaped steel belt hole recognition system based on OpenCV to assist the scheme, so as to ensure the safety and efficiency of roadway support. This system uses pychar, opencv and python language to realize the recognition and positioning of W-shaped steel strip hole. The scheme has the advantages of small amount of calculation, high accuracy and fast recognition speed. This research conclusion provides a reference for the further spatial positioning analysis of W-shaped steel belt hole, and improves the efficiency of underground support operation and personnel safety.

Design and Test of Cleaning Loss Kernel Recognition System for Corn Combine Harvester

Cleaning loss is an important parameter to judge the performance of a corn combine harvester. At present, there exists the phenomenon that corn cleaning loss rate detection devices have a long signal processing time and low recognition accuracy. To solve this problem, based on the principle of the impacting piezoelectric effect, the impacting signals of corn kernels and impurities are analyzed by means of the frequency spectrum method to obtain the characteristic frequency for effectively distinguishing corn kernels and impurities, which is determined as 8.7 kHz. Based on this characteristic frequency, a corn cleaning loss kernel recognition system is designed, which can realize the function of corn kernel recognition and cleaning loss rate recording. In this system, signal processing circuits which mainly include two-order high-pass filtration, envelope wave detection and voltage comparison are designed. On the basis of the signal processing circuit, adding the judgment program for the holding time of the output square wave signal improves the system’s recognition accuracy for kernels impacting the sensitive plate simultaneously. The system was tested in indoor conditions. The results show that 20–30 corn kernels could be accurately recognized per minute on a single sensitive plate, and the recognition accuracy rate of this system could reach 85% when three corn kernels impacted simultaneously. The results serve as a theoretical basis and represent a new method for the design of a cleaning loss kernel recognition system.

Design of Tone Recognition System for Pipa Strings Based on Wireless Sensors

Pipa has been widely used as a wooden musical instrument as early as the Han period. It mainly relies on human fingers to pluck the strings to make sounds. The timbre of the pipa also has a very strong national characteristic. Understanding the meaning of words, phrases, and sentences requires tone recognition. For tone identification, the fundamental frequency conveys the most unique information. This paper summarizes the influence of the pipa’s characteristics, technology and skills of the player, and the player’s factors on the timbre of the pipa performance. In addition, given the problems of low accuracy and high data packet loss rate in the existing pipa playing tone recognition methods, this paper proposes a pipa string playing tone recognition algorithm based on wireless sensors. According to the sensor stage and weight-corresponding characteristics, on the premise of minimizing the total mean square error, the optimal weight corresponding to the sensor measurement value is found according to the adaptive mode. The unbiased estimated value of the measured value of each node is obtained through iterative calculation. The Euclidean distance between the measured value and the estimated value of each sensor obtained by the normalization process is used as the adaptive weighted recognition weight. It completes the conversion of the adaptive weighted recognition algorithm structure and the binary recognition result. The experimental results show that the proposed method has good tonal recognition accuracy in the pipa playing environment.

Recognition and Detection of Wide Field Bionic Compound Eye Target Based on Cloud Service Network.

In this paper, a multidisciplinary cross-fusion of bionics, robotics, computer vision, and cloud service networks was used as a research platform to study wide-field bionic compound eye target recognition and detection from multiple perspectives. The current research status of wide-field bionic compound-eye target recognition and detection was analyzed, and improvement directions were proposed. The surface microlens array arrangement was designed, and the spaced surface bionic compound eye design principle cloud service network model was established for the adopted spaced-type circumferential hierarchical microlens array arrangement. In order to realize the target localization of the compound eye system, the content of each step of the localization scheme was discussed in detail. The distribution of virtual spherical targets was designed by using the subdivision of the positive icosahedron to ensure the uniformity of the targets. The spot image was pre-processed to achieve spot segmentation. The energy symmetry-based spot center localization algorithm was explored and its localization effect was verified. A suitable spatial interpolation method was selected to establish the mapping relationship between target angle and spot coordinates. An experimental platform of wide-field bionic compound eye target recognition and detection system was acquired. A super-resolution reconstruction algorithm combining pixel rearrangement and an improved iterative inverse projection method was used for image processing. The model was trained and evaluated in terms of detection accuracy, leakage rate, time overhead, and other evaluation indexes, and the test results showed that the cloud service network-based wide-field bionic compound eye target recognition and detection performs well in terms of detection accuracy and leakage rate. Compared with the traditional algorithm, the correct rate of the algorithm was increased by 21.72%. Through the research of this paper, the wide-field bionic compound eye target recognition and detection and cloud service network were organically provide more technical support for the design of wide-field bionic compound eye target recognition and detection system.

Design of a compact palmprint recognition system based on edge computing

随着生物特征身份认证技术的发展, 非接触式掌纹识别的高识别率、低侵犯性和非接触性等优点, 使其得到了越来越广泛的关注. 为了满足边缘环境下多设备的实时高效的处理需求, 本文设计了一套基于边缘计算的紧致化掌纹识别框架, 分别在终端设备层、边缘服务器层、云端搭建掌纹识别子系统. 在终端设备层采用基于Tiny YOLO-v3的目标识别算法和基于MobilenetV2的关键点定位算法对采集图像进行预处理, 提取掌纹ROI, 并提出识别请求. 在边缘服务器层, 对接受到的掌纹ROI利用基于对抗度量学习的GoogLeNet模型进行特征提取和特征匹配, 在返回识别结果后进行数据同步. 在数据中心, 将对会所有的识别任务记录日志并归入数据库, 同时定时训练更新终端设备和边缘设备的网络模型, 以提高系统的跨领域识别能力. 该框架是一套完整可行的生物特征识别框架, 具有广阔的市场前景和应用价值.

Computer Analysis and Automatic Recognition Technology of Music Emotion

With the rapid development of the related computer industry, the use of computer-related technologies has become more and more frequent. The music industry is no exception. The research and analysis of music emotions has been a problem since ancient times. Due to the diversification of music emotions, people with different music in the same piece of music will have different feelings. The research topic of this article is to make a comprehensive analysis of the computer’s automatic identification technology, combined with the powerful subcapacity of the computer, so that the research on music emotion can be developed rapidly. The article analyzes the technical research of the automatic recognition and analysis of music emotion in the computer, and conducts a comprehensive analysis of the music emotion through the research of the computer-related automatic recognition technology. This paper focuses on the computer automatic recognition model of music emotion, and successfully realizes the design and simulation of the automatic recognition system based on the MATLAB platform. An automatic identification model using BP neural network algorithm is proposed. By comparing it with the statistical classification algorithm, the experimental results verify the effectiveness of the designed BP network in music emotion recognition.

Robust Multi-Scenario Speech-Based Emotion Recognition System.

Every human being experiences emotions daily, e.g., joy, sadness, fear, anger. These might be revealed through speech—words are often accompanied by our emotional states when we talk. Different acoustic emotional databases are freely available for solving the Emotional Speech Recognition (ESR) task. Unfortunately, many of them were generated under non-real-world conditions, i.e., actors played emotions, and recorded emotions were under fictitious circumstances where noise is non-existent. Another weakness in the design of emotion recognition systems is the scarcity of enough patterns in the available databases, causing generalization problems and leading to overfitting. This paper examines how different recording environmental elements impact system performance using a simple logistic regression algorithm. Specifically, we conducted experiments simulating different scenarios, using different levels of Gaussian white noise, real-world noise, and reverberation. The results from this research show a performance deterioration in all scenarios, increasing the error probability from 25.57% to 79.13% in the worst case. Additionally, a virtual enlargement method and a robust multi-scenario speech-based emotion recognition system are proposed. Our system’s average error probability of 34.57% is comparable to the best-case scenario with 31.55%. The findings support the prediction that simulated emotional speech databases do not offer sufficient closeness to real scenarios.

Statement of Retraction: Real-time image recognition algorithm and system design of Android mobile devices

This article refers to:Retracted Article: Real-time image recognition algorithm and system design of Android mobile devices

Design and Realization of Computer Image Intelligent Recognition System

The application of intelligent image recognition technology in life is more and more extensive, especially in the field of computer and multimedia, the research of machine vision system is becoming more and more mature, and the demand of human society for information processing is constantly increasing. This article first analyzes the basic knowledge of digital images based on computer technology, including basic knowledge of digital images, basic knowledge of image filtering and image recognition algorithms. Secondly, this paper studies the design and implementation of computer image intelligent recognition system.