Pub Date : 2023-05-04DOI: 10.1080/13682199.2023.2206763
Ravishankar Mehta, K. K. Singh
In the pandemic of COVID-19, identifying a person from their face became difficult due to wearing of mask. In regard to the given circumstances, the authors have remarkably put effort on identifying a person using 2D ear images based on deep convolutional neural network (CNNs). They investigated the challenges of limited data and varying environmental conditions in this regards. To deal with such challenges, the authors developed an augmentation-based light-weight CNN model using CPU enabled machine so that it can be ported into embedded devices. While applying data augmentation technique to enhance the quality and size of training dataset, the authors analysed and discussed the different augmentation parameters (rotation, flipping, zooming, and fill mode) that are effective for generating the large number of sample images of different variability. The model works well on constrained and unconstrained ear datasets and achieves good recognition accuracy. It also reduces the problem of overfitting. [ FROM AUTHOR] Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
在2019冠状病毒病大流行期间，由于戴口罩，从面部识别一个人变得困难。考虑到给定的情况，作者在使用基于深度卷积神经网络(cnn)的二维耳朵图像识别人的问题上付出了显著的努力。他们调查了这方面有限的数据和变化的环境条件所带来的挑战。为了应对这些挑战，作者开发了一种基于增强的轻量级CNN模型，使用启用CPU的机器，以便将其移植到嵌入式设备中。在应用数据增强技术提高训练数据集的质量和规模的同时，作者分析和讨论了不同的增强参数(旋转、翻转、缩放和填充模式)对生成大量不同可变性的样本图像的效果。该模型对有约束和无约束的耳朵数据集都能很好地识别，并取得了较好的识别精度。它还减少了过拟合的问题。image Science Journal版权归Taylor & Francis Ltd所有，未经版权所有者明确书面许可，不得将其内容复制或通过电子邮件发送到多个网站或发布到listserv。但是，用户可以打印、下载或通过电子邮件发送文章供个人使用。这可以删节。对副本的准确性不作任何保证。用户应参阅原始出版版本的材料的完整。(版权适用于所有人。)
{"title":"Deep convolutional neural network-based effective model for 2D ear recognition using data augmentation","authors":"Ravishankar Mehta, K. K. Singh","doi":"10.1080/13682199.2023.2206763","DOIUrl":"https://doi.org/10.1080/13682199.2023.2206763","url":null,"abstract":"In the pandemic of COVID-19, identifying a person from their face became difficult due to wearing of mask. In regard to the given circumstances, the authors have remarkably put effort on identifying a person using 2D ear images based on deep convolutional neural network (CNNs). They investigated the challenges of limited data and varying environmental conditions in this regards. To deal with such challenges, the authors developed an augmentation-based light-weight CNN model using CPU enabled machine so that it can be ported into embedded devices. While applying data augmentation technique to enhance the quality and size of training dataset, the authors analysed and discussed the different augmentation parameters (rotation, flipping, zooming, and fill mode) that are effective for generating the large number of sample images of different variability. The model works well on constrained and unconstrained ear datasets and achieves good recognition accuracy. It also reduces the problem of overfitting. [ FROM AUTHOR] Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88332064","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}
Pub Date : 2023-04-29DOI: 10.1080/13682199.2023.2202576
Hany A. AbdElghfar, Abdelmoty M. Ahmed, A. A. Alani, Hammam M. Abdelaal, B. Bouallegue, M. Khattab, Hassan A. Youness
{"title":"QSLRS-CNN: Qur'anic sign language recognition system based on convolutional neural networks","authors":"Hany A. AbdElghfar, Abdelmoty M. Ahmed, A. A. Alani, Hammam M. Abdelaal, B. Bouallegue, M. Khattab, Hassan A. Youness","doi":"10.1080/13682199.2023.2202576","DOIUrl":"https://doi.org/10.1080/13682199.2023.2202576","url":null,"abstract":"","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88870990","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}
Pub Date : 2023-04-26DOI: 10.1080/13682199.2023.2200060
M. Dharani, R. Thamilselvan
{"title":"Hybrid optimization enabled deep learning model for Parkinson's disease classification","authors":"M. Dharani, R. Thamilselvan","doi":"10.1080/13682199.2023.2200060","DOIUrl":"https://doi.org/10.1080/13682199.2023.2200060","url":null,"abstract":"","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86441838","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}
Pub Date : 2023-04-26DOI: 10.1080/13682199.2023.2195097
A. Vivekraj, S. Sumathi
ABSTRACT This paper proposes a Resnet-UNet-Fractional Snake Optimization Algorithm (Res-UNet-FSOA) for cranial nerve segmentation. Firstly, MRI images are considered as input, and thereafter preprocessing is conducted utilizing median filtering. In the module of pre-processing, the image enhancement is carried out based upon improved multiscale vesselness that is in identifying local tubular portions of an image. After that, cranial nerve segmentation is done employing Res-UNet, which is an amalgamation of Resnet and UNet. The network is then trained by a devised optimization approach namely, FSOA. The FSOA is proposed by incorporating Fractional Calculus (FC) and Snake Optimizer (SO). Then, start point and end point extraction is executed utilizing deep seeded region growing (DSRG). At last, medial axis extraction is performed using tensor voting and non-maximum suppression (TV-NMS) method. Furthermore, the proposed approach obtained segmentation accuracy of 0.930, Jaccard coefficient of 0.947, and dice coefficient of 0.950.
{"title":"Resnet-Unet-FSOA based cranial nerve segmentation and medial axis extraction using MRI images","authors":"A. Vivekraj, S. Sumathi","doi":"10.1080/13682199.2023.2195097","DOIUrl":"https://doi.org/10.1080/13682199.2023.2195097","url":null,"abstract":"ABSTRACT This paper proposes a Resnet-UNet-Fractional Snake Optimization Algorithm (Res-UNet-FSOA) for cranial nerve segmentation. Firstly, MRI images are considered as input, and thereafter preprocessing is conducted utilizing median filtering. In the module of pre-processing, the image enhancement is carried out based upon improved multiscale vesselness that is in identifying local tubular portions of an image. After that, cranial nerve segmentation is done employing Res-UNet, which is an amalgamation of Resnet and UNet. The network is then trained by a devised optimization approach namely, FSOA. The FSOA is proposed by incorporating Fractional Calculus (FC) and Snake Optimizer (SO). Then, start point and end point extraction is executed utilizing deep seeded region growing (DSRG). At last, medial axis extraction is performed using tensor voting and non-maximum suppression (TV-NMS) method. Furthermore, the proposed approach obtained segmentation accuracy of 0.930, Jaccard coefficient of 0.947, and dice coefficient of 0.950.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73264837","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}
Pub Date : 2023-04-24DOI: 10.1080/13682199.2023.2202577
Harshad S. Modi, D. Parikh
{"title":"An intelligent unsupervised anomaly detection in videos using inception capsule auto encoder","authors":"Harshad S. Modi, D. Parikh","doi":"10.1080/13682199.2023.2202577","DOIUrl":"https://doi.org/10.1080/13682199.2023.2202577","url":null,"abstract":"","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91030407","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}
Pub Date : 2023-04-23DOI: 10.1080/13682199.2023.2202096
Mohamed Hallek, Randa Khemiri, Ali Algarwi, Abdellatif Mtibaa, Mohamed Atri
Real-time stereo matching with high accuracy is a dynamic research topic; it is attractive in diverse computer vision applications. This paper presents a stereo-matching algorithm that produces high-quality disparity map while maintaining real-time performance. The proposed stereo-matching method is based on three per-pixel difference measurements with adjustment elements. The absolute differences and the gradient matching are combined with a colour-weighted extension of complete rank transform to reduce the effect of radiometric distortion. The disparity calculation is realized using improved dynamic programming that optimizes along and across all scanlines. It solves the inter-scanline inconsistency problem and increases the matching accuracy. The proposed algorithm is implemented on parallel high-performance graphic hardware using the Compute Unified Device Architecture to reach over 240 million disparity evaluations per second. The processing speed of our algorithm reaches 98 frames per second on 240 × 320-pixel images and 32 disparity levels. Our method ranks fourth in terms of accuracy and runtime for quarter-resolution images in the Middlebury stereo benchmark.
{"title":"Colour-weighted rank transform and improved dynamic programming for fast and accurate stereo matching","authors":"Mohamed Hallek, Randa Khemiri, Ali Algarwi, Abdellatif Mtibaa, Mohamed Atri","doi":"10.1080/13682199.2023.2202096","DOIUrl":"https://doi.org/10.1080/13682199.2023.2202096","url":null,"abstract":"Real-time stereo matching with high accuracy is a dynamic research topic; it is attractive in diverse computer vision applications. This paper presents a stereo-matching algorithm that produces high-quality disparity map while maintaining real-time performance. The proposed stereo-matching method is based on three per-pixel difference measurements with adjustment elements. The absolute differences and the gradient matching are combined with a colour-weighted extension of complete rank transform to reduce the effect of radiometric distortion. The disparity calculation is realized using improved dynamic programming that optimizes along and across all scanlines. It solves the inter-scanline inconsistency problem and increases the matching accuracy. The proposed algorithm is implemented on parallel high-performance graphic hardware using the Compute Unified Device Architecture to reach over 240 million disparity evaluations per second. The processing speed of our algorithm reaches 98 frames per second on 240 × 320-pixel images and 32 disparity levels. Our method ranks fourth in terms of accuracy and runtime for quarter-resolution images in the Middlebury stereo benchmark.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134955934","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}
Pub Date : 2023-04-22DOI: 10.1080/13682199.2023.2195701
Alan Hodgson
{"title":"Dry gelatin ‘Photo-mechanical’ plates – their significance in the evolution of scientific & technical photography","authors":"Alan Hodgson","doi":"10.1080/13682199.2023.2195701","DOIUrl":"https://doi.org/10.1080/13682199.2023.2195701","url":null,"abstract":"","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85503762","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：