计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2014年
7期
139-143
,共5页
程少光%何毕%布树辉%刘贞报
程少光%何畢%佈樹輝%劉貞報
정소광%하필%포수휘%류정보
场景识别%超像素空间金字塔模型%空间PACT%bag of words特征%支持向量机
場景識彆%超像素空間金字塔模型%空間PACT%bag of words特徵%支持嚮量機
장경식별%초상소공간금자탑모형%공간PACT%bag of words특정%지지향량궤
scene recognition%S-SPM(Super-pixel Spatial Pyramid Model)%PACT(Principal component Analysis of Census Transform)%bag of words%SVM(Support Vector Machine)
针对以往场景识别研究中将图像分割成大小相等的矩形区域进行特征提取而导致识别率低的问题,提出了一种基于超像素空间金字塔模型的场景识别方法:先对图像做不同分辨率的超像素分割,在得到的每个图像子区域中提取PACT特征,然后利用K-means聚类构建出图像集的视觉词典。在进行场景识别时,将每幅图像所有分割子区域的PACT特征连接成一个特征向量,并加入bag of words特征进行分类,最终的场景分类结果在支持向量机LIBSVM上获得。实验结果表明该算法能够有效提高识别率。
針對以往場景識彆研究中將圖像分割成大小相等的矩形區域進行特徵提取而導緻識彆率低的問題,提齣瞭一種基于超像素空間金字塔模型的場景識彆方法:先對圖像做不同分辨率的超像素分割,在得到的每箇圖像子區域中提取PACT特徵,然後利用K-means聚類構建齣圖像集的視覺詞典。在進行場景識彆時,將每幅圖像所有分割子區域的PACT特徵連接成一箇特徵嚮量,併加入bag of words特徵進行分類,最終的場景分類結果在支持嚮量機LIBSVM上穫得。實驗結果錶明該算法能夠有效提高識彆率。
침대이왕장경식별연구중장도상분할성대소상등적구형구역진행특정제취이도치식별솔저적문제,제출료일충기우초상소공간금자탑모형적장경식별방법:선대도상주불동분변솔적초상소분할,재득도적매개도상자구역중제취PACT특정,연후이용K-means취류구건출도상집적시각사전。재진행장경식별시,장매폭도상소유분할자구역적PACT특정련접성일개특정향량,병가입bag of words특정진행분류,최종적장경분류결과재지지향량궤LIBSVM상획득。실험결과표명해산법능구유효제고식별솔。
In order to overcome drawbacks of SPM based scene recognition, a novel scene recognition method based on Super-pixel Spatial Pyramid Model(S-SPM)is proposed:images are hierarchically divided into sub-regions through super-pixel segmentation and then the visual vocabulary is constructed by clustering the Principal component Analysis of Census Transform(PACT)features which are extracted from every corresponding spatial sub-region. To recognize the category of a scene, PACT of all spatial sub-regions are concatenated to form a feature vector and then the bag of words feature are added. Finally the LIBSVM is used to classify the scene category. The experimental results indicate that this method has higher recognition rate.