2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)最新文献_第3页

Quantifying the Uncertainty in 3D CT Lung Cancer Images Classification 三维CT肺癌图像分类的不确定性量化

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179053

Rahimi Zahari, J. Cox, B. Obara

{"title":"Quantifying the Uncertainty in 3D CT Lung Cancer Images Classification","authors":"Rahimi Zahari, J. Cox, B. Obara","doi":"10.1109/ICPRS58416.2023.10179053","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179053","url":null,"abstract":"Lung cancer has caused the deaths of millions of people. Early diagnosis is proven vital to increase survival rate. This can be done using computed tomography screening, and when such a system is in place with a computer-aided diagnostic system and deep learning algorithms, it has been proven to be an effective approach. However, most existing systems do not quantify the uncertainty in the prediction. Radiologists should have complete confidence in the predictions during the screening. Therefore, to address this issue, we have developed an uncertainty-aware model framework not only to classify lung cancer nodules from 3D computed tomography images, but also to estimate the associated uncertainty in the prediction of the model. We have used the ResNet50 architecture as our base model and, through investigation with different loss functions and the inclusion of class weights, we concluded that the use of the focal loss function shows its superiority over the results of the benchmark model. Two approaches have been adopted to estimate the uncertainty during test time; Monte Carlo dropout and Test Time Augmentation, and from the multiple predictions obtained, three uncertainty metrics have been calculated; entropy, standard deviation, and Bhattacharyya coefficient. Our model achieves the best performance with the F1 score, 83.0 % using the dropout rate, p, 0.5 and Monte Carlo iterations, M, 10. We have also shown that using a threshold value can greatly improve the classification performance even more, but the amount of data to be referred needs to be taken into account.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115828844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning-based Human Height Estimation from a Stereo Vision System 基于立体视觉系统的深度学习人体高度估计

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179079

Henry O. Velesaca, Jorge Vulgarin, B. Vintimilla

引用次数: 0

Balanced Pedestrian Attribute Recognition for Improved Attribute-based Person Retrieval 基于改进属性的人检索的平衡行人属性识别

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10178990

Andreas Specker, Jürgen Beyerer

{"title":"Balanced Pedestrian Attribute Recognition for Improved Attribute-based Person Retrieval","authors":"Andreas Specker, Jürgen Beyerer","doi":"10.1109/ICPRS58416.2023.10178990","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10178990","url":null,"abstract":"Attribute-based person retrieval is a crucial task in surveillance systems since it enables the search for an individual if no image of the suspect is available. Searches can be based on soft biometric characteristics, understood as semantic attributes people typically use to describe each other. Examples are gender, age, or a description of the person's clothing and accessories. One possible solution is Pedestrian Attribute Recognition (PAR). Resulting attribute predictions are compared to the query attributes with the model's predictions. However, related literature indicates approaches tend to either perform well regarding the recognition of single attributes or achieve superior retrieval results at the expense of an increased number of false positives. This work aims to improve single-attribute recognition and attribute-based retrieval simultaneously by applying spatial projection and normalization modules. Spatial projection extracts features for different receptive fields to account for global as well as local attributes. Our PARNorm module normalizes attribute logits attribute-and instance-wise to enhance label-based PAR metrics without hurting instance-based performance. Furthermore, we propose a novel evaluation metric for attribute-based person retrieval that considers the degree of match between attribute queries and gallery images instead of using binary relevance labels. This allows for more realistic estimates of retrieval accuracy, which correlate strongly with the visual impression of the rankings. Our model outperforms the current state-of-the-art in generalization on the UPAR dataset and its challenge version.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121334967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Construction of Spatial Pedigree of Chinese Typical Village Settlements 中国典型村落聚落空间谱系的构建

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179054

Die Lu, Yi-shao Shi, Junyan Yang, Qiao Wang

引用次数: 0

Mathematical Palm Vein Modeling for Large-Scale Biometric Recognition 面向大规模生物识别的手掌静脉数学建模

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179063

E. Salazar-Jurado, R. Hernández-García, Karina Vilches Ponce, R. J. Barrientos

{"title":"Mathematical Palm Vein Modeling for Large-Scale Biometric Recognition","authors":"E. Salazar-Jurado, R. Hernández-García, Karina Vilches Ponce, R. J. Barrientos","doi":"10.1109/ICPRS58416.2023.10179063","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179063","url":null,"abstract":"Individual recognition through palm vein authentication has gained the attention of the scientific community due to its high level of security. However, the algorithms for recognition are validated with a limited number of images due to the small number of subjects in public databases, making it challenging to implement deep learning-based methods and evaluate scalability for mass identification. Creating a large-scale database of real palm vein images is laborious in terms of time, security, and cost. In other biometrics, such as fingerprint recognition, synthetic images greatly enhance the accuracy of developed techniques. Although the reasons behind palm vein patterns are not fully understood, there is evidence that geometric characterization and anatomical study allow for the proposal of reasonable assumptions to create realistic vein pattern images through models. Therefore, this study aims to generate synthetic palm vein images by modeling the vascular structure. Thus, our proposal will favor future research that requires the generation of large-scale databases to provide reliable and scalable solutions to biometric recognition tasks of individuals with palm veins.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"76 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127394440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring multi-food detection using deep learning-based algorithms 探索使用基于深度学习的算法进行多种食物检测

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179037

Roberto Morales, Juan Quispe, Eduardo Aguilar

{"title":"Exploring multi-food detection using deep learning-based algorithms","authors":"Roberto Morales, Juan Quispe, Eduardo Aguilar","doi":"10.1109/ICPRS58416.2023.10179037","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179037","url":null,"abstract":"People are becoming increasingly concerned about their diet, whether for disease prevention, medical treatment or other purposes. In meals served in restaurants, schools or public canteens, it is not easy to identify the ingredients and/or the nutritional information they contain. Currently, technological solutions based on deep learning models have facilitated the recording and tracking of food consumed based on the recognition of the main dish present in an image. Considering that sometimes there may be multiple foods served on the same plate, food analysis should be treated as a multi-class object detection problem. EfficientDet and YOLOv5 are object detection algorithms that have demonstrated high mAP and real-time performance on general domain data. However, these models have not been evaluated and compared on public food datasets. Unlike general domain objects, foods have more challenging features inherent in their nature that increase the complexity of detection. In this work, we performed a performance evaluation of Efficient-Det and YOLOv5 on three public food datasets: UNIMIB2016, UECFood256 and ChileanFood64. From the results obtained, it can be seen that YOLOv5 provides a significant difference in terms of both mAP and response time compared to EfficientDet in all datasets. Furthermore, YOLOv5 outperforms the state-of-the-art on UECFood256, achieving an improvement of more than 4% in terms of mAP@.50 over the best reported.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131274938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised Flight Fault Propagation Analysis Using a Variational Autoencoder 基于变分自编码器的无监督飞行故障传播分析

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179004

Emanuil Mladenov, Miguel Martínez-García, Yu Zhang, Shaheryar Khan, Faizan Patankar

引用次数: 0

Study of machine learning techniques for pedestrian dynamics simulation models 行人动力学仿真模型的机器学习技术研究

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179045

Pedro Reyes Norambuena, Juan Bekios-Calfa, Javier Martínez Torres

引用次数: 0

A New Methodology for Analysing Interactions between an Autonomous Vehicle and other Users 一种分析自动驾驶车辆与其他用户交互的新方法

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10179070

Josué Manuel Rivera Velázquez, Pascal Housam Salmane, G. Saint-Pierre, L. Khoudour, Olivier Huynh, J. Garrigos

{"title":"A New Methodology for Analysing Interactions between an Autonomous Vehicle and other Users","authors":"Josué Manuel Rivera Velázquez, Pascal Housam Salmane, G. Saint-Pierre, L. Khoudour, Olivier Huynh, J. Garrigos","doi":"10.1109/ICPRS58416.2023.10179070","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10179070","url":null,"abstract":"The increasingly present automation of vehicles generates great concern both in the industrial and public sectors. Evidently, the autonomy of vehicles is accompanied by a large number of scientific questions: what are the real benefits of automating transport services? what are the new expected situations due to the presence of an autonomous vehicle? etc. In terms of road safety, great interest has been aroused in the interactions between autonomous vehicles and the rest of the road users (pedestrians, cyclists, motorists, etc.). Especially, there is interest in the way current road users act/react to the inclusion of this new element (the autonomous vehicle) in the road ecosystem. The definition and classification of these interactions undoubtedly influence the Operational Design Domain (ODD) as well as the defined behaviour that the autonomous vehicle must perform in any situation. In this article, the description of the methodology carried out for the identification, registration and subsequent analysis of these situations of interest is presented, which is composed of five parts: 1) Installation of fixed cameras and GPS system used for monitoring interactions, 2) detection of the autonomous vehicle (AV) and other road users, 3) estimation of AV and other users trajectories, 4) estimation of the distances between the AV and other users, and 5) interpretation of the data collected and its use to improve road safety.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122559936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Red-Unet: An Enhanced U-Net Architecture to Segment Tuberculosis Lesions on X-Ray Images Red-Unet:一种增强的U-Net架构在x射线图像上分割结核病灶

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) Pub Date : 2023-07-04 DOI: 10.1109/ICPRS58416.2023.10178991

Luis Mosquera-Berrazueta, Noel Pérez, D. Benítez, Felipe Grijalva, Oscar Camacho, M. Herrera, Yovani Marrero-Ponce

{"title":"Red-Unet: An Enhanced U-Net Architecture to Segment Tuberculosis Lesions on X-Ray Images","authors":"Luis Mosquera-Berrazueta, Noel Pérez, D. Benítez, Felipe Grijalva, Oscar Camacho, M. Herrera, Yovani Marrero-Ponce","doi":"10.1109/ICPRS58416.2023.10178991","DOIUrl":"https://doi.org/10.1109/ICPRS58416.2023.10178991","url":null,"abstract":"The lung is the organ most commonly affected by tuberculosis infection, with estimates of lung involvement in subjects with active tuberculosis ranging from 79% to 87%. This type of disease is an airborne infectious disease caused by Mycobacterium tuberculosis and is a significant cause of morbidity and mortality, particularly in developing countries. Although recent medical advances have saved many patients, doctors are still subject to human errors when detecting and segmenting these lung lesions. Deep learning models have been developed to aid in lowering errors in the medical industry. In order to successfully detect and segment tuberculosis lesions in a data set of chest X-ray images, we propose a new deep learning technique called Red-Unet based on the conventional U-net architecture. Both the Red-Unet and the U-net were trained using a ten-fold stratified cross-validation schema three times under the same experimental conditions. The results showed that Red-Unet performs as well as the baseline model in less time and with fewer computational requirements, which is significant. The mean and standard deviation of the DICE coefficient and IoU scores for the Red-Unet were 0.92 (0.10) and 0.86 (0.14), while the U-net obtained 0.91 (0.18) and 0.85 (0.19), respectively. Furthermore, the Red-Unet model chosen in the top list with 100 training epochs was validated in a randomly selected test set, scoring as highly as the training values. The quality and generalization ability of the model was confirmed by this performance evaluation on the test data set, which demonstrated that it successfully identified and segmented lung anomalies brought on by tuberculosis regardless of size.","PeriodicalId":253231,"journal":{"name":"2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121818024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0