-
1.发明申请METHOD FOR RETRIEVING SIMILAR IMAGE BASED ON VISUAL SALIENCIES AND VISUAL PHRASES 审中-公开基于视觉色彩和视觉图像检索类似图像的方法公开(公告)号：US20150269191A1
公开(公告)日：2015-09-24
申请号：US14603376
申请日：2015-01-23
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Wei Ma , Zeming Zhao , Xuan Zhang , Jun Miao
IPC: G06F17/30
CPC classification number: G06F16/5838
Abstract: The present invention discloses a method for retrieving a similar image based on visual saliencies and visual phrases, comprising: inputting an inquired image; calculating a saliency map of the inquired image; performing viewpoint shift on the saliency map by utilizing a viewpoint shift model, defining a saliency region as a circular region which taking a viewpoint as a center and R as a radius, and shifting the viewpoint for k times to obtain k saliency regions of the inquired image; extracting a visual word in each of the saliency regions of the inquired image, to constitute a visual phrase, and jointing k visual phrases to generate an image descriptor of the inquired image; obtaining an image descriptor for each image of an inquired image library; and calculating a similarity value between the inquired image and each image in the inquired image library depending on the image descriptors by utilizing a cosine similarity, to obtain an image similar to the inquired image from the inquired image library. Through the present invention, noise in expression of an image is reduced, so that the expression of the image in a computer may be more consistent with human understanding of the semantics of the image, presenting a better retrieving effect and a higher retrieving speed.
Abstract translation: 本发明公开了一种基于视觉效果和视觉短语检索相似图像的方法，包括：输入查询图像; 计算查询图像的显着图; 通过利用视点移动模型对显着性图进行视点移动，将显着区域定义为以视点为中心并以R为半径的圆形区域，并且将视点移动k次以获得查询的k个显着区域 图片; 提取查询图像的每个显着区域中的视觉词，构成视觉短语，并且连接k个视觉短语以生成所查询的图像的图像描述符; 获取查询的图像库的每个图像的图像描述符; 并且通过利用余弦相似度，根据图像描述符计算查询图像与查询图像库中的每个图像之间的相似度值，以从查询的图像库中获得类似于查询图像的图像。 通过本发明，图像的表达噪声减小，使得计算机中的图像的表达可以更好地符合人们对图像语义的理解，呈现更好的检索效果和更高的检索速度。
-
Patent Agency Ranking
公开(公告)号：US20160180188A1
公开(公告)日：2016-06-23
申请号：US14603282
申请日：2015-01-22
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Shuo Qiu , Wei Ma , Jun Miao , Jia Li
CPC classification number: G06K9/4671 , G06K9/3233 , G06K9/4623 , G06T5/10 , G06T7/13 , G06T7/174 , G06T7/269 , G06T2207/10012 , G06T2207/10021 , G06T2207/20021
Abstract: The present invention discloses a method for detecting a salient region of a stereoscopic image, comprising: step 1) calculating flow information of each pixel separately with respect to a left-eye view and a right-eye view of the stereoscopic image; step 2) matching the flow information, to obtain a parallax map; step 3) selecting one of the left-eye view and the right-eye view, dividing it into T non-overlapping square image blocks; step 4) calculating a parallax effect value for each of the image blocks of the parallax map; step 5) for each of the image blocks of the selected one of the left-eye view and the right-eye view, calculating a central bias feature value and a spatial dissimilarity value, and multiplying the three values, to obtain a saliency value of the image block; and step 6) obtaining a saliency gray scale map of the stereoscopic image from saliency values of the image blocks. The present invention provides a method for extracting stereoscopic saliency based on parallax effects and spatial dissimilarity, acquiring depth information by utilizing parallax, and combining visual central bias feature and spatial dissimilarity to realize more accurate detection of a stereoscopic salient region.
-
公开(公告)号：US10008004B1
公开(公告)日：2018-06-26
申请号：US15406504
申请日：2017-01-13
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Fangfang Liang , Yuanhua Qiao , Wei Ma , Jun Miao
Abstract: A method of establishing a 3D saliency model based on 3D contrast and depth weight, includes dividing left view of 3D image pair into multiple regions by super-pixel segmentation method, synthesizing a set of features with color and disparity information to describe each region, and using color compactness as weight of disparity in region feature component, calculating feature contrast of a region to surrounding regions; obtaining background prior on depth of disparity map, and improving depth saliency through combining the background prior and the color compactness; taking Gaussian distance between the depth saliency and regions as weight of feature contrast, obtaining initial 3D saliency by adding the weight of the feature contrast; enhancing the initial 3D saliency by 2D saliency and central bias weight.
-
公开(公告)号：US09501715B2
公开(公告)日：2016-11-22
申请号：US14603282
申请日：2015-01-22
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Shuo Qiu , Wei Ma , Jun Miao , Jia Li
CPC classification number: G06K9/4671 , G06K9/3233 , G06K9/4623 , G06T5/10 , G06T7/13 , G06T7/174 , G06T7/269 , G06T2207/10012 , G06T2207/10021 , G06T2207/20021
Abstract: The present invention discloses a method for detecting a salient region of a stereoscopic image, comprising: step 1) calculating flow information of each pixel separately with respect to a left-eye view and a right-eye view of the stereoscopic image; step 2) matching the flow information, to obtain a parallax map; step 3) selecting one of the left-eye view and the right-eye view, dividing it into T non-overlapping square image blocks; step 4) calculating a parallax effect value for each of the image blocks of the parallax map; step 5) for each of the image blocks of the selected one of the left-eye view and the right-eye view, calculating a central bias feature value and a spatial dissimilarity value, and multiplying the three values, to obtain a saliency value of the image block; and step 6) obtaining a saliency gray scale map of the stereoscopic image from saliency values of the image blocks. The present invention provides a method for extracting stereoscopic saliency based on parallax effects and spatial dissimilarity, acquiring depth information by utilizing parallax, and combining visual central bias feature and spatial dissimilarity to realize more accurate detection of a stereoscopic salient region.
Abstract translation: 本发明公开了一种用于检测立体图像的显着区域的方法，包括：步骤1）分别计算相对于立体图像的左眼视图和右眼视图的每个像素的流动信息; 步骤2）匹配流信息，获得视差图; 步骤3）选择左眼视图和右眼视图之一，将其划分为T个非重叠的平方图像块; 步骤4）计算视差图的每个图像块的视差效应值; 步骤5）对于所选择的左眼视图和右眼视图中的每一个图像块，计算中心偏置特征值和空间相似度值，并且将三个值相乘以获得显着值 图像块; 和步骤6）从图像块的显着值获得立体图像的显着灰度图。 本发明提供一种基于视差效应和空间相异性提取立体显着性的方法，通过利用视差获取深度信息，并组合视觉中心偏置特征和空间相异性，以实现对立体显着区域的更准确的检测。
-
公开(公告)号：US10810490B2
公开(公告)日：2020-10-20
申请号：US15018656
申请日：2016-02-08
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Bin Yuan , Song Cui , Jun Miao , Junfa Liu
IPC: G06N3/08
Abstract: The present invention relates to a clustering method based on iterations of neural networks, which comprises the following steps: step 1, initializing parameters of an extreme learning machine; step 2, randomly choosing samples of which number is equal to the number of clusters, each sample representing one cluster, forming an initial exemplar set and training the extreme learning machine; step 3, using current extreme learning machine to cluster samples, which generates a clustering result; step 4, choosing multiple samples from each cluster as exemplars for the cluster according to a rule; step 5, retraining the extreme learning machine by using the exemplars for each cluster obtained from step 4; and step 6, going back to step 3 to do iteration, otherwise obtaining and outputting clustering result until clustering result is steady or a maximal limit of the number of iterations is reached. The present invention resolves problems that how to realize clustering of high dimensional and nonlinear data space and that the prior art consumes a larger memory or need longer running time.
-
公开(公告)号：US20180182118A1
公开(公告)日：2018-06-28
申请号：US15406504
申请日：2017-01-13
Applicant: Beijing University of Technology
Inventor： Lijuan Duan , Fangfang Liang , Yuanhua Qiao , Wei Ma , Jun Miao
CPC classification number: G06T7/593 , G06K9/00201 , G06K9/4652 , G06K9/4676 , G06T7/194 , G06T15/20 , G06T17/00 , G06T2200/04
Abstract: A method of establishing a 3D saliency model based on 3D contrast and depth weight, includes dividing left view of 3D image pair into multiple regions by super-pixel segmentation method, synthesizing a set of features with color and disparity information to describe each region, and using color compactness as weight of disparity in region feature component, calculating feature contrast of a region to surrounding regions; obtaining background prior on depth of disparity map, and improving depth saliency through combining the background prior and the color compactness; taking Gaussian distance between the depth saliency and regions as weight of feature contrast, obtaining initial 3D saliency by adding the weight of the feature contrast; enhancing the initial 3D saliency by 2D saliency and central bias weight.
-
-
-
-
-
Search Results
6
records
(took 0.014 seconds)
