Learning For Image Recognition Research Articles

Deep learning image recognition of cow behavior and an open data set acquired near an automatic milking robot

Production animals enjoying good health and well-being are more productive and have a higher output quality. Several technical solutions have been used to monitor the animals’ welfare: those based on computer vision provide cost-efficient and scalable options. In this work, we performed a continuous two-month image acquisition of cows in front of an automatic milking station and divided the data into ten different classes related to the most important activities appearing in the images. The data consisted of almost 19 hours of video, equivalent to more than 1.7 million still images. Based on these imaged, we then implemented a convolutional neural network classifier to recognize the cows' behavior. The network was tested using cross-validation methodology and achieved an 86% precision rate and 85% recall rate in the classification. The data and the Python program code used in this study are made available. An image data set that directly resembles the harsh conditions inside a barn and can be used for deep learning purposes has not been previously made available.

Summary of Research on Application of Deep Learning in Image Recognition

With the rapid development of technology, artificial intelligence is gradually applied in the field of image processing. Traditional image processing and recognition takes human extraction of features as a means to describe and characterize low-level edge information in images, but a large number of features extraction causes certain troubles to image recognition, and it is difficult to extract deep-level information. In recent years, deep learning, as an important emerging technology in the field of image recognition, has broad application prospects, and the research on image recognition technology has important theoretical value and practical significance to promote the development of computer vision and artificial intelligence. It opens up a whole new direction in image processing research, thus meeting the demand for efficient image processing. This paper reviews the applications of deep learning in image recognition, analyzes the classical convolutional neural network model, and summarizes the applications of deep learning in the fields of license plate recognition, face recognition, and medical image recognition.

Evaluation of the Correlation between Gaze Avoidance and Schizophrenia Psychopathology with Deep Learning-based Emotional Recognition

IntroductionDirect gaze is the most important mediator of social interaction and communication. Existing studies have evaluated eye movements of patients with schizophrenia by presenting stimuli using photographs or pre-recorded videos, but few directly investigated gaze avoidance in real-world situations.ObjectivesTo investigate the correlation between gaze avoidance and psychopathology in patients with schizophrenia through eye movement measurements in real-life interpersonal situations.MethodsWe enrolled 52 clinically stable patients with schizophrenia. Psychopathology was evaluated using the Positive and Negative Syndrome Scale (PANSS), Hamilton Depression Rating Scale, and Hamilton Anxiety Rating Scale. After presenting a visual stimulus, eye movements were measured with Tobii Pro Wearable Glasses 2, and deep learning-based emotional recognition using the residual masking network was used for neutral stimulus verification. Statistical analyses were performed using Pearson’s correlation and regression analyses.ResultsData of 45 participants with verified stimulus neutrality by deep learning image recognition were used for analysis. The first dwelling time was negatively correlated with the PANSS positive syndrome subscale (p=0.028), general psychopathology subscale (p=0.008), total score (p=0.008), 5-factor positive symptoms (p=0.035), and 5-factor depression/anxiety symptoms (p=0.008). The baseline-area of interest (AOI) pupil diameter change was positively correlated with PANSS 5-factor positive symptom scores (p=0.039). After adjusting for additional variables, the same items had a significant effect on the first dwelling time and baseline-AOI pupil diameter change.ConclusionsPsychopathology, particularly positive symptoms, was associated with gaze avoidance and pupil diameter in patients with schizophrenia. Evaluating the characteristics of eye movements in patients with schizophrenia will enable better understanding of their symptoms.DisclosureNo significant relationships.

Research on License Plate Location Algorithm Based on YOLOv5

License plate location is a key part of license plate recognition, and its positioning accuracy seriously determines the final result of license plate recognition. Firstly, the traditional license plate location methods are compared and analyzed. Secondly, in order to solve the localization problem in low resolution and multi-vehicle environment, a license plate method based on YOLOv5s was proposed by using deep learning image recognition technology, and data enhancement was introduced to improve YOLOv5s. Finally, the YOLOv5 algorithm is applied to real vehicle images under complex environmental conditions for experimental verification, and the results show that the accuracy is 99.12%. The experimental results show that the license plate location model based on YOLOv5S can effectively solve the influence of illumination, image quality and other factors on license plate location, improve the efficiency and accuracy compared with the traditional license plate location method, the algorithm has good robustness and fast calculation speed.

Applying deep learning image recognition technology to promote environmentally sustainable behavior

Since the dawn of the 21st century, the carbon footprint has become an important indicator for measuring environmental impact. While it's been recognized that changing one's dietary habits can help to reduce food-related carbon emissions, many consumers do not yet understand much about carbon emissions generated by food production and dissemination and do not actively search for related information. Thus, developing a way for consumers to identify a food's carbon footprint easily and quickly and perhaps to then adjust their eating habits is one way to help achieve environmentally sustainable eating behavior. This study establishes a carbon footprint tracking system using convolutional neural network image recognition technology to explore and improve the advantages of environmentally sustainable eating behavior. Results show the accuracy of the proposed model is 94.79%, indicating it can effectively recognize food types. During a two-week experiment testing the tracking system, the measured total carbon footprint for the study participants was reduced by 22.25%. Additionally, the number of participants whose daily carbon footprint was less than the targeted goal of 3 kg increased by 81.82%, indicating that the system can effectively help people reduce their food carbon footprints while providing them with calorie and nutrient information required to help achieve a balance between health and environment.

Design of Basketball Player Training Action Error Correction System Based on Convolutional Neural Network Algorithm

With the development of industry and the progress of science and technology, more and more new technology is gradually applied to the movement of error correction. This not only relieves workers of unneeded burdens by making their task more straightforward and error-free, but it also improves production efficiency. Deep neural networks are one of these new technologies that have exploded in popularity in recent years, with applications in a variety of industries. Of course, the application in image recognition must not be less, image recognition technology based on deep neural network has become more mature, and the error rate of recognition is now much lower than human vision recognition. So at present, some industrial detection is gradually from human vision detection to computer vision detection. This study discloses a basketball action error correction method based on deep learning image recognition, which includes the following steps: receiving each frame of basketball image captured from the fitness video, recording the corresponding time of each frame of fitness image, and preprocessing each frame of fitness image; the preprocessed basketball image was fed into the human joint recognition model, and the human joint recognition model calculated each human joint in the fitness image and output its position coordinates. According to the coordinate position of each joint orderly line, the human skeleton diagram is obtained; the human skeleton diagram is compared and assessed in accordance with standard fitness action, and the nonstandard basketball image is generated to realize basketball action repair. A basketball action error correction system based on deep learning picture identification is also disclosed in the invention. The system and method are capable of efficiently addressing the difficult challenge of comparing fitness movements with and without music rhythm.

Detection of Diseases Using Machine Learning Image Recognition Technology in Artificial Intelligence.

With the continuous development and improvement of artificial intelligence technology, machine learning technology has also been extensively developed, which has promoted the development of computer vision, image processing, natural language processing, and other fields. Purpose. This article aims to apply the image processing technology based on machine learning in the detection of childhood diseases and propose the application of image processing technology to the detection of childhood diseases. This article introduces machine learning, image recognition technology, and related algorithms in detail and experiments on image recognition technology based on machine learning. The experimental results show that image recognition technology based on machine learning can well identify white blood cells that are difficult to distinguish with the naked eye, with a recognition rate of up to 90%. Applying image recognition technology based on machine learning in disease diagnosis has greatly improved the level of medical diagnosis.

Reliable Algorithms for Machine Learning Models: Implementation Research in Data Science

Machine Learning generates programs that make predictions and informed decisions about complex problems in an efficient and reliable way. These ML programs autonomously test solutions against the dataset to find the best fit for the problem. The paper aims to review the ML algorithms that develop prediction models by utilizing training dataset and known output. The paper also focuses on ML principles, algorithms, approaches, and applications for Supervised, Unsupervised, and Reinforcement learning that can perform tasks without being explicitly programmed for it. Completely opposite to rule-based programming, the machine learning paradigm uses examples of real data sets and pre-process it before providing the desired outputs based on these examples. In the case of more involved and complex tasks, it can be challenging for humans to explicitly program the models. On the other hand, it can be more effective to help the machines develop the algorithms for advanced tasks. This paper will also present the trending real-world applications of Machine Learning in Image Recognition and Biomedicine. Additionally, it will provide a background analysis of machine learning and related fields of data science.

Preface

Due to recent pandemic, 2021 3rd International Conference on Robotics, Intelligent Control and Artificial Intelligence (ICRICA 2021) was held virtually online on December 03 - 05, 2021. The decision to hold the virtual conference was made in compliance with many restrictions and regulations that were imposed by countries around the globe. Such restrictions were made to minimize the risk of people contracting or spreading the COVID-19 through physical contact. There were 150 individuals who attended this on-line conference, represented many countries.ICRICA 2021 brings together industry professionals and academics from research institute, governmental agencies, and universities around the world to exchange information on advances in Robotics, Intelligent Control and Artificial Intelligence. The objective of the ICRICA 2021 is to facilitate the exchange between researchers and practitioners in the area of Robotics, Intelligent Control and Artificial Intelligence and related technologies, and provides attendees with a unique opportunity to share, discuss, and witness research results, thereby creating a common platform for exchanging ideas and fostering future developments in the field.During the conference, the conference model was divided into three sessions, including oral presentations, keynote speeches, and online Q&A discussion. In the first part, some scholars, whose submissions were selected as the excellent papers, were given about 5-10 minutes to perform their oral presentations one by one. Then in the second part, keynote speakers were each allocated 30-45 minutes to hold their speeches. In the second part, we invited three professors as our keynote speakers. Prof. Rüdiger Dillmann, Karlsruhe Institute of Technology, German (IEEE Fellow, IROS Fellow). His research interest is in the areas of humanoid robotics and neurorobotics with special emphasis on intelligent, autonomous, and interactive robot behavior generated with the help of machine learning methods and programming by demonstration (PbD). The second keynote speakers, Prof. Xiaofang Yuan, Hunan University, China. His research area includes intelligent control theory and application, electric vehicle control, robot drive control. Lastly, we were glad to invite Prof. Hui Zhang, Hunan University, China as our finale keynote speakers. He is mainly engaged in the research of intelligent robot vision detection, deep learning image recognition and other fields. Their insightful speeches had triggered heated discussion in the third session of the conference. Every participant praised this conference for disseminating useful and insightful knowledge.The proceedings are a compilation of the accepted papers and represent an interesting outcome of the conference. Topics include but are not limited to the following areas: Robot structure design and control, Sensor/actuator networks, Robot kinematics and dynamics, Robot operating system and other related topics. All the papers have been through rigorous review and process to meet the requirements of international publication standard.List of Committee member are available in this pdf.

Using Image Recognition to Process Unbalanced Data in Genetic Diseases From Biobanks.

With precision medicine as the goal, the human biobank of each country should be analyzed to determine the complete research results related to genetic diseases. In addition, with the increase in medical imaging data, automatic image processing with image recognition has been widely studied and applied in biomedicine. However, case–control data imbalance often occurs in human biobanks, which is usually solved by the statistical method SAIGE. Due to the huge amount of genetic data in human biobanks, the direct use of the SAIGE method often faces the problem of insufficient computer memory to support calculations and excessive calculation time. The other method is to use sampling to adjust the data to balance the case–control ratio, which is called Synthetic Minority Oversampling Technique (SMOTE). Our study employed the Manhattan plot and genetic disease information from the Taiwan Biobank to adjust the imbalance in the case–control ratio by SMOTE, called “TW-SMOTE.” We further used a deep learning image recognition system to identify the TW-SMOTE. We found that TW-SMOTE can achieve the same results as that of SAIGE and the UK Biobank (UKB). The processing of the technical data can be equivalent to the use of data plots with a relatively large UKB sample size and achieve the same effect as that of SAIGE in addressing data imbalance.

Evaluation of the correlation between gaze avoidance and schizophrenia psychopathology with deep learning-based emotional recognition.

To investigate the correlation between gaze avoidance and psychopathology in patients with schizophrenia through eye movement measurements in real-life interpersonal situations. We enrolled 52 clinically stable patients with schizophrenia. Psychopathology was evaluated using the Positive and Negative Syndrome Scale (PANSS), Hamilton Depression Rating Scale, and Hamilton Anxiety Rating Scale. After presenting a visual stimulus, eye movements were measured with Tobii Pro Wearable Glasses 2, and deep learning-based emotional recognition using the residual masking network was used for neutral stimulus verification. Statistical analyses were performed using Pearson's correlation and regression analyses. Data of 45 participants with verified stimulus neutrality by deep learning image recognition were used for analysis. The first dwelling time was negatively correlated with the PANSS positive syndrome subscale (p=0.028), general psychopathology subscale (p=0.008), total score (p=0.008), 5-factor positive symptoms (p=0.035), and 5-factor depression/anxiety symptoms (p=0.043). The baseline-area of interest (AOI) pupil diameter change was positively correlated with PANSS 5-factor positive symptom scores (p=0.039). After adjusting for additional variables, the same items had a significant effect on the first dwelling time and baseline-AOI pupil diameter change. Psychopathology, particularly positive symptoms, was associated with gaze avoidance and pupil diameter in patients with schizophrenia. Evaluating the characteristics of eye movements in patients with schizophrenia will enable better understanding of their symptoms.

Proposal and Evaluation of a Teaching Process for Learning Image Recognition Technology Using Artificial Intelligence through Programming

Proposal and Evaluation of a Teaching Process for Learning Image Recognition Technology Using Artificial Intelligence through Programming

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer.

Simple SummaryMalignant melanomas (MMs) with aypical clinical presentation constitute a diagnostic pitfall, and false negatives carry the risk of a diagnostic delay and improper disease management. Among the most common, challenging presentation forms of MMs are those that clinically resemble seborrheic keratosis (SK). On the other hand, SK may mimic melanoma, producing ‘false positive overdiagnosis’ and leading to needless excisions. The evolving efficiency of deep learning algorithms in image recognition and the availability of large image databases have accelerated the development of advanced computer-aided systems for melanoma detection. In the present study, we used image data from the International Skin Image Collaboration archive to explore the capacity of deep knowledge transfer in the challenging diagnostic task of the atypical skin tumors of MM and SK.Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

A Web-based Andhra University Spatial Information System (AUSIS) and a Building Information Extraction Model using WebGIS & Image Recognition Technique

A university campus is an intricate infrastructure. Especially new students, who are thereon for the first time, have a tough time orienting themselves and finding places. The campus of Andhra University occupies more than 422 acres (170.7 hectares). The campus has many different buildings. Every year, thousands of new students join the university. These students either take a campus commuter or walk around to get familiar with the campus compound. Visitors to Andhra University might have a hard time searching for a particular location on the campus. Every day, uncountable numbers of students, staff, and visitors move around the campus compound to perform tasks by walking, cycling, driving, or riding campus commuters. Even if there are maps at various points on the campus premises, users do not have continuous help to reach their destination. On these static maps, they can try to figure out a way to get to their target, but as soon as they start walking in the target direction, they have no help anymore. The main objective of this study is to develop a Spatial Information System for Andhra University (a Progressive Web App). Which provides several features like a voice-enabled optimal navigation solution, shows nearby places within campus premises, and a geo-tagged university (Geo-tagging of all entities within campus premises). To make the web application more operative, the application is appended with more features. For instance, a map shows statistical data with pie charts visualization (statistical data like monthly attendance), machine learning's image recognition model for extracting the building information from the digital or captured images.

Sentiment analysis of pets using deep learning technologies in artificial intelligence of things system

This research paper proposes sentiment analysis of pets using deep learning technologies in the artificial intelligence of things system. Mask R-CNN is used to detect image objects and generate contour mask maps, pose analysis algorithms are used to obtain object posture information, and at the same time object sound signals are converted into spectrograms as features, using deep learning image recognition technology to obtain object emotion information. By using the fusion of object posture and emotional characteristics as the basis for pet emotion identification and analysis, the detected specific pet behaviour states will be actively notified to the owner for processing. Compared with traditional speech recognition, which uses mel-frequency cepstral coefficients for feature extraction, coupled with a Gaussian mixture model-hidden Markov model for voice recognition, the experimental method of this research paper effectively improves the accuracy by 70%. Prior work on the implementation of smart pet surveillance systems has used the pet's tail and mouth as features, and has combined these with sound features to analyse the pet's emotions. This research paper proposes a new method of sentiment analysis in pets, and our method is compared with previous related work. Experimental results show that our approach increases the accuracy rate by 70%.

A Novel Approach for Network Intrusion Detection Using Multistage Deep Learning Image Recognition

The current rise in hacking and computer network attacks throughout the world has heightened the demand for improved intrusion detection and prevention solutions. The intrusion detection system (IDS) is critical in identifying abnormalities and assaults on the network, which have grown in size and pervasiveness. The paper proposes a novel approach for network intrusion detection using multistage deep learning image recognition. The network features are transformed into four-channel (Red, Green, Blue, and Alpha) images. The images then are used for classification to train and test the pre-trained deep learning model ResNet50. The proposed approach is evaluated using two publicly available benchmark datasets, UNSW-NB15 and BOUN Ddos. On the UNSW-NB15 dataset, the proposed approach achieves 99.8% accuracy in the detection of the generic attack. On the BOUN DDos dataset, the suggested approach achieves 99.7% accuracy in the detection of the DDos attack and 99.7% accuracy in the detection of the normal traffic.

Detection of 3D face masks with thermal infrared imaging and deep learning techniques

Biometric systems are becoming more and more efficient due to increasing performance of algorithms. These systems are also vulnerable to various attacks. Presentation of falsified identity to a biometric sensor is one the most urgent challenges for the recent biometric recognition systems. Exploration of specific properties of thermal infrared seems to be a comprehensive solution for detecting face presentation attacks. This letter presents outcome of our study on detecting 3D face masks using thermal infrared imaging and deep learning techniques. We demonstrate results of a two-step neural network-featured method for detecting presentation attacks. Full Text: PDF ReferencesS.R. Arashloo, J. Kittler, W. Christmas, "Face Spoofing Detection Based on Multiple Descriptor Fusion Using Multiscale Dynamic Binarized Statistical Image Features", IEEE Trans. Inf. Forensics Secur. 10, 11 (2015). CrossRef A. Anjos, M.M. Chakka, S. Marcel, "Motion-based counter-measures to photo attacks inface recognition", IET Biometrics 3, 3 (2014). CrossRef M. Killioǧlu, M. Taşkiran, N. Kahraman, "Anti-spoofing in face recognition with liveness detection using pupil tracking", Proc. SAMI IEEE, (2017). CrossRef A. Asaduzzaman, A. Mummidi, M.F. Mridha, F.N. Sibai, "Improving facial recognition accuracy by applying liveness monitoring technique", Proc. ICAEE IEEE, (2015). CrossRef M. Kowalski, "A Study on Presentation Attack Detection in Thermal Infrared", Sensors 20, 14 (2020). CrossRef C. Galdi, et al, "PROTECT: Pervasive and useR fOcused biomeTrics bordEr projeCT - a case study", IET Biometrics 9, 6 (2020). CrossRef D.A. Socolinsky, A. Selinger, J. Neuheisel, "Face recognition with visible and thermal infrared imagery", Comput. Vis Image Underst. 91, 1-2 (2003) CrossRef L. Sun, W. Huang, M. Wu, "TIR/VIS Correlation for Liveness Detection in Face Recognition", Proc. CAIP, (2011). CrossRef J. Seo, I. Chung, "Face Liveness Detection Using Thermal Face-CNN with External Knowledge", Symmetry 2019, 11, 3 (2019). CrossRef A. George, Z. Mostaani, D Geissenbuhler, et al., "Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network", IEEE Trans. Inf. Forensics Secur. 15, (2020). CrossRef S. Ren, K. He, R. Girshick, J. Sun, "Proceedings of IEEE Conference on Computer Vision and Pattern Recognition", Proc. CVPR IEEE 39, (2016). CrossRef K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition", Proc. CVPR, (2016). CrossRef K. Mierzejewski, M. Mazurek, "A New Framework for Assessing Similarity Measure Impact on Classification Confidence Based on Probabilistic Record Linkage Model", Procedia Manufacturing 44, 245-252 (2020). CrossRef

Application of deep learning in image recognition and diagnosis of gastric cancer

Application of deep learning in image recognition and diagnosis of gastric cancer

Novel Algorithm for Image Classification Using Cross Deep Learning Technique

The basic concepts of training and the model structure of deep belief networks (DBNs) in deep analysis are studied to apply image recognition in the area of deep learning. Random propound is provided with the parameter in the fine-tuning stage and the randomly hidden layer eliminated to maintain unchanged weights. The results show that the layered DBN training system reduces training problems and training times significantly. In the small sample, the deep faith network has improved significantly after introducing the down sample and random dropdown and effectively alleviates the over-fitting phenomenon. Design a new Deep Learning Image Recognition and Classification Algorithm. Novel Algorithm for Image Classification Using Cross Deep Learning Technique.

Application of deep learning in image recognition

Deep learning is a new field in machine learning, which is based on the neural network model to extract features by simulating human brain cognition. Image recognition is an essential subject in the field of deep learning and has made significant progress in recent years. In the training process, only the computer needs to cooperate, and no personnel need to participate in the process to get a good image recognition effect. This paper makes an in-depth analysis on the application of deep learning in image recognition, discusses the necessary steps of image trial and the basic principle of the neural network, and puts forward some problems and popular deep learning models used in image recognition.