图像分类的空间划分方法分析

12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL) Pub Date : 2014-11-01 DOI:10.1109/NEUREL.2014.7011509

A. Avramović, V. Risojevic

{"title":"图像分类的空间划分方法分析","authors":"A. Avramović, V. Risojevic","doi":"10.1109/NEUREL.2014.7011509","DOIUrl":null,"url":null,"abstract":"Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research we investigate the influence of upright and rotated partitions on image classification regardless of the image filtering step. We show that simple combination of rotated spatial partitions improves classification accuracy up to 10% compared to single spatial partition commonly used in spatial pyramid matching.","PeriodicalId":402208,"journal":{"name":"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis of spatial partitioning approaches for image classification\",\"authors\":\"A. Avramović, V. Risojevic\",\"doi\":\"10.1109/NEUREL.2014.7011509\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research we investigate the influence of upright and rotated partitions on image classification regardless of the image filtering step. We show that simple combination of rotated spatial partitions improves classification accuracy up to 10% compared to single spatial partition commonly used in spatial pyramid matching.\",\"PeriodicalId\":402208,\"journal\":{\"name\":\"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)\",\"volume\":\"7 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NEUREL.2014.7011509\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEUREL.2014.7011509","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

空间分割被证明是有利于图像分类、场景分类和目标识别的任务。空间金字塔匹配是最常用的捕捉场景粗糙空间结构的方法。然而，空间金字塔匹配导致对旋转敏感的图像表示。在本研究中，我们研究了垂直和旋转分割对图像分类的影响，而不考虑图像滤波步骤。我们表明，与空间金字塔匹配中常用的单个空间分区相比，旋转空间分区的简单组合可将分类精度提高10%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Analysis of spatial partitioning approaches for image classification

Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research we investigate the influence of upright and rotated partitions on image classification regardless of the image filtering step. We show that simple combination of rotated spatial partitions improves classification accuracy up to 10% compared to single spatial partition commonly used in spatial pyramid matching.

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

12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)

自引率

0.00%

发文量