Pub Date : 2024-06-01DOI: 10.1117/1.jei.33.3.033036
Mengqi Chen, Yifan Wang, Qian Sun, Weiming Wang, Fu Lee Wang
Content-based commodity retrieval (CCR) faces two major challenges: (1) commodities in real-world scenarios are often captured randomly by users, resulting in significant variations in image backgrounds, poses, shooting angles, and brightness; and (2) many commodities in the CCR dataset have similar appearances but belong to different brands or distinct products within the same brand. We introduce a CCR neural network called CCR-Net, which incorporates both length loss and salient loss. These two losses can operate independently or collaboratively to enhance retrieval quality. CCR-Net offers several advantages, including the ability to (1) minimize data variations in real-world captured images; and (2) differentiate between images containing highly similar but fundamentally distinct commodities, resulting in improved commodity retrieval capabilities. Comprehensive experiments demonstrate that our CCR-Net achieves state-of-the-art performance on the CUB200-2011, Perfect500k, and Stanford Online Products datasets for commodity retrieval tasks.
{"title":"Length and salient losses co-supported content-based commodity retrieval neural network","authors":"Mengqi Chen, Yifan Wang, Qian Sun, Weiming Wang, Fu Lee Wang","doi":"10.1117/1.jei.33.3.033036","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.033036","url":null,"abstract":"Content-based commodity retrieval (CCR) faces two major challenges: (1) commodities in real-world scenarios are often captured randomly by users, resulting in significant variations in image backgrounds, poses, shooting angles, and brightness; and (2) many commodities in the CCR dataset have similar appearances but belong to different brands or distinct products within the same brand. We introduce a CCR neural network called CCR-Net, which incorporates both length loss and salient loss. These two losses can operate independently or collaboratively to enhance retrieval quality. CCR-Net offers several advantages, including the ability to (1) minimize data variations in real-world captured images; and (2) differentiate between images containing highly similar but fundamentally distinct commodities, resulting in improved commodity retrieval capabilities. Comprehensive experiments demonstrate that our CCR-Net achieves state-of-the-art performance on the CUB200-2011, Perfect500k, and Stanford Online Products datasets for commodity retrieval tasks.","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141532508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1117/1.jei.33.3.031210
Ichraq Lemghari, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Jennifer Vandoni
The advent of deep learning methods has led to impressive advances in computer vision tasks over the past decades, largely due to their ability to extract non-linear features that are well adapted to the task at hand. For supervised approaches, data labeling is essential to achieve a high level of performance; however, this task can be so fastidious or even troublesome in difficult contexts (e.g., specific defect detection, unconventional data annotations, etc.) that experts can sometimes erroneously provide the wrong ground truth label. Considering classification problems, this paper addresses the issue of handling noisy labels in datasets. Specifically, we first detect the noisy samples of a dataset using set-valued labels and then improve their classification using Venn–Abers predictors. The obtained results reach more than 0.99 and 0.90 accuracy for noisified versions of two widely used image classification datasets, digit MNIST and CIFAR-10 respectively with a 40% two-class pair-flip noise ratio and 0.87 accuracy for CIFAR-10 with 10-class uniform 40% noise ratio.
{"title":"Robust classification with noisy labels using Venn–Abers predictors","authors":"Ichraq Lemghari, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Jennifer Vandoni","doi":"10.1117/1.jei.33.3.031210","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.031210","url":null,"abstract":"The advent of deep learning methods has led to impressive advances in computer vision tasks over the past decades, largely due to their ability to extract non-linear features that are well adapted to the task at hand. For supervised approaches, data labeling is essential to achieve a high level of performance; however, this task can be so fastidious or even troublesome in difficult contexts (e.g., specific defect detection, unconventional data annotations, etc.) that experts can sometimes erroneously provide the wrong ground truth label. Considering classification problems, this paper addresses the issue of handling noisy labels in datasets. Specifically, we first detect the noisy samples of a dataset using set-valued labels and then improve their classification using Venn–Abers predictors. The obtained results reach more than 0.99 and 0.90 accuracy for noisified versions of two widely used image classification datasets, digit MNIST and CIFAR-10 respectively with a 40% two-class pair-flip noise ratio and 0.87 accuracy for CIFAR-10 with 10-class uniform 40% noise ratio.","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141518295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1117/1.jei.33.3.031211
Saïd Rahmani, Roger de Souza Lima, Eric Serris, Ana Cameirão, Johan Debayle
To enhance control and monitoring of industrial crystallization processes, we propose an innovative nondestructive imaging method utilizing in situ 2D vision sensors. This approach enables the acquisition of 2D videos depicting crystal aggregates throughout the batch crystallization process. Our approach is built upon experimental observations, specifically regarding the process dynamics and sensor fouling. It involves dynamic segmentation of observed aggregates, from which quantitative analyses are derived. Notably, our method allows for tracking the evolution of the particle size distribution of crystal aggregates over time and the determination of the growth kinetics of crystals that agglomerate at the sensor air gap. This enables the detection of key stages in the crystallization process and the geometric characterization of crystal aggregate production.
{"title":"Monitoring of industrial crystallization processes through image sequence segmentation and characterization","authors":"Saïd Rahmani, Roger de Souza Lima, Eric Serris, Ana Cameirão, Johan Debayle","doi":"10.1117/1.jei.33.3.031211","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.031211","url":null,"abstract":"To enhance control and monitoring of industrial crystallization processes, we propose an innovative nondestructive imaging method utilizing in situ 2D vision sensors. This approach enables the acquisition of 2D videos depicting crystal aggregates throughout the batch crystallization process. Our approach is built upon experimental observations, specifically regarding the process dynamics and sensor fouling. It involves dynamic segmentation of observed aggregates, from which quantitative analyses are derived. Notably, our method allows for tracking the evolution of the particle size distribution of crystal aggregates over time and the determination of the growth kinetics of crystals that agglomerate at the sensor air gap. This enables the detection of key stages in the crystallization process and the geometric characterization of crystal aggregate production.","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141518514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1117/1.jei.33.3.033022
Yuhang Zhao, Ping Zhao
{"title":"Image denoising model using adaptive regularization parameter based on structure tensor","authors":"Yuhang Zhao, Ping Zhao","doi":"10.1117/1.jei.33.3.033022","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.033022","url":null,"abstract":"","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1117/1.jei.33.3.033021
Jiahao Li, Xiaohong Han
{"title":"Monocular 3D object detection for distant objects","authors":"Jiahao Li, Xiaohong Han","doi":"10.1117/1.jei.33.3.033021","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.033021","url":null,"abstract":"","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1117/1.jei.33.3.033023
Xiaoju Yin, Li Zhou, Bo Li
{"title":"Pointer meter recognition algorithm based on two-dimensional convolution and calculus accumulation","authors":"Xiaoju Yin, Li Zhou, Bo Li","doi":"10.1117/1.jei.33.3.033023","DOIUrl":"https://doi.org/10.1117/1.jei.33.3.033023","url":null,"abstract":"","PeriodicalId":54843,"journal":{"name":"Journal of Electronic Imaging","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}