利用计算机视觉绘画方法来增强深度学习模型

Mykola Baranov, Y. Shcherbyna, Oles Khodych
{"title":"利用计算机视觉绘画方法来增强深度学习模型","authors":"Mykola Baranov, Y. Shcherbyna, Oles Khodych","doi":"10.23939/sisn2022.12.001","DOIUrl":null,"url":null,"abstract":"In today’s world, the amount of available information grows exponentially every day. Most of this data is visual data. Correspondingly, the demand for the algorithm of image rent is growing. Traditionally, the first approaches to computer vision problems were classical algorithms without the use of machine learning. Such approaches are limited by many factors. First of all, the conditions imposed on the input images are applied – the shooting angle, lighting, position of objects on the scene, etc. Other classical algorithms cannot meet the needs of modern computer vision problems. Neural network approaches and deep learning models have largely replaced classical programming algorithms. The greatest advantage of deep neural networks in computer vision tasks is not only the possibility of automatically building data processing algorithms that cannot be built in any other way, but also the comprehensiveness of such an approach – actual deep neural networks provide all stages of image processing from start to finish. But. This approach is not always optimal. Training models require a large amount of annotated data to avoid the effect of overfitting such models. In many settings, the conditions have a significant degree of variability, but are limited. In such cases, the combination of both approaches of computer vision is fruitful – pre-processing of the image is performed by classical algorithms, and prediction (classification, object search, etc.) is performed by a neural network. This article noted an example of the use of damaged images in the classification of tasks (in the extreme cases, the percentage of damage reached 60 % of the image area). We have shown in practice that the use of classic approaches for restoration of damaged areas of the image (inpainting) made it possible to increase the final accuracy of the model by up to 10 % compared to the base model trained under identical conditions on the original data.","PeriodicalId":444399,"journal":{"name":"Vìsnik Nacìonalʹnogo unìversitetu \"Lʹvìvsʹka polìtehnìka\". Serìâ Ìnformacìjnì sistemi ta merežì","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Exploit computer vision inpainting approach to boost deep learning models\",\"authors\":\"Mykola Baranov, Y. Shcherbyna, Oles Khodych\",\"doi\":\"10.23939/sisn2022.12.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In today’s world, the amount of available information grows exponentially every day. Most of this data is visual data. Correspondingly, the demand for the algorithm of image rent is growing. Traditionally, the first approaches to computer vision problems were classical algorithms without the use of machine learning. Such approaches are limited by many factors. First of all, the conditions imposed on the input images are applied – the shooting angle, lighting, position of objects on the scene, etc. Other classical algorithms cannot meet the needs of modern computer vision problems. Neural network approaches and deep learning models have largely replaced classical programming algorithms. The greatest advantage of deep neural networks in computer vision tasks is not only the possibility of automatically building data processing algorithms that cannot be built in any other way, but also the comprehensiveness of such an approach – actual deep neural networks provide all stages of image processing from start to finish. But. This approach is not always optimal. Training models require a large amount of annotated data to avoid the effect of overfitting such models. In many settings, the conditions have a significant degree of variability, but are limited. In such cases, the combination of both approaches of computer vision is fruitful – pre-processing of the image is performed by classical algorithms, and prediction (classification, object search, etc.) is performed by a neural network. This article noted an example of the use of damaged images in the classification of tasks (in the extreme cases, the percentage of damage reached 60 % of the image area). We have shown in practice that the use of classic approaches for restoration of damaged areas of the image (inpainting) made it possible to increase the final accuracy of the model by up to 10 % compared to the base model trained under identical conditions on the original data.\",\"PeriodicalId\":444399,\"journal\":{\"name\":\"Vìsnik Nacìonalʹnogo unìversitetu \\\"Lʹvìvsʹka polìtehnìka\\\". Serìâ Ìnformacìjnì sistemi ta merežì\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Vìsnik Nacìonalʹnogo unìversitetu \\\"Lʹvìvsʹka polìtehnìka\\\". Serìâ Ìnformacìjnì sistemi ta merežì\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23939/sisn2022.12.001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vìsnik Nacìonalʹnogo unìversitetu \"Lʹvìvsʹka polìtehnìka\". Serìâ Ìnformacìjnì sistemi ta merežì","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23939/sisn2022.12.001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在当今世界,可用信息的数量每天都呈指数级增长。这些数据大多是可视数据。相应地,对图像租金算法的需求也在不断增长。传统上,计算机视觉问题的第一个方法是经典算法,没有使用机器学习。这种方法受到许多因素的限制。首先,对输入图像施加条件——拍摄角度、光线、场景中物体的位置等。其他经典算法已不能满足现代计算机视觉问题的需要。神经网络方法和深度学习模型已经在很大程度上取代了经典的编程算法。深度神经网络在计算机视觉任务中的最大优势不仅在于可以自动构建以任何其他方式无法构建的数据处理算法,而且还在于这种方法的全面性-实际的深度神经网络提供从头到尾的图像处理的所有阶段。但是。这种方法并不总是最佳的。训练模型需要大量带注释的数据,以避免模型过拟合的影响。在许多情况下,条件有很大程度的可变性,但是有限的。在这种情况下,计算机视觉的两种方法的结合是富有成效的——图像的预处理由经典算法执行,预测(分类,对象搜索等)由神经网络执行。本文指出了在任务分类中使用受损图像的一个示例(在极端情况下,损坏的百分比达到图像区域的60%)。我们已经在实践中证明,使用经典方法来恢复图像的受损区域(修复),与在原始数据上相同条件下训练的基础模型相比,可以将模型的最终精度提高10%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Exploit computer vision inpainting approach to boost deep learning models
In today’s world, the amount of available information grows exponentially every day. Most of this data is visual data. Correspondingly, the demand for the algorithm of image rent is growing. Traditionally, the first approaches to computer vision problems were classical algorithms without the use of machine learning. Such approaches are limited by many factors. First of all, the conditions imposed on the input images are applied – the shooting angle, lighting, position of objects on the scene, etc. Other classical algorithms cannot meet the needs of modern computer vision problems. Neural network approaches and deep learning models have largely replaced classical programming algorithms. The greatest advantage of deep neural networks in computer vision tasks is not only the possibility of automatically building data processing algorithms that cannot be built in any other way, but also the comprehensiveness of such an approach – actual deep neural networks provide all stages of image processing from start to finish. But. This approach is not always optimal. Training models require a large amount of annotated data to avoid the effect of overfitting such models. In many settings, the conditions have a significant degree of variability, but are limited. In such cases, the combination of both approaches of computer vision is fruitful – pre-processing of the image is performed by classical algorithms, and prediction (classification, object search, etc.) is performed by a neural network. This article noted an example of the use of damaged images in the classification of tasks (in the extreme cases, the percentage of damage reached 60 % of the image area). We have shown in practice that the use of classic approaches for restoration of damaged areas of the image (inpainting) made it possible to increase the final accuracy of the model by up to 10 % compared to the base model trained under identical conditions on the original data.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Project of the information system of sales on the charity auction platform Intelligent system for analyzing battery charge consumption processes Information system of feedback monitoring in social networks for the formation of recommendations for the purchase of goods Software for the implementation of an intelligent system to solve the problem of “cold start” Analysis of multiplication algorithms in Galuis fields for the cryptographic protection of information
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1