A Method of Image Representation Based on Attribute Graph

Abstract

The present invention provides a kind of image representation method based on the attribute graph, uses indirect complete graph (V, E) to represent the image, is called the attribute graph; V={V l , V g} is the vertex of the graph; V l Represents a local node, describing all objects contained in the image; V g Represents the global node, which describes the background information of the image or the overall scene information; E represents the edge of the graph, which is divided into two types: local edge and global edge; the edge in the attribute graph represents the spatial relationship between objects in the image and the objects in the image. Spatial position in the whole image. The method provided by the invention uses attribute graphs to represent images, and can accurately classify images that contain the same object but represent different image semantics. The attribute graph not only considers the local features of the image, but also considers the global features of the image. At the same time, it uses edge information to describe the spatial relationship between objects and objects, as well as the spatial position of objects in the entire image, which has a positive effect on image classification and recognition. meaning.

Description

Technical field [0001] The invention relates to an image representation method, in particular to an image representation method based on attribute maps, and belongs to the technical field of image recognition. Background technique [0002] Image recognition methods based on learning have made great progress in the past few years. For specific object classes, especially human faces and cars, there are more reliable and efficient recognition based on underlying features (such as SIFT features or HOG features). However, the underlying features of these images cannot reflect image category information well. [0003] Recently, new research materials have proposed methods for classification using inherent attributes of images. Attributes refer to the characteristics that can be specified by a person and can be observed in the image. It can indicate whether the object in the image exists, it can describe the color, shape, material, component, category and function of the object in the i...

AI Technical Summary

Problems solved by technology

Fahadi et al (A.Farhadi, I.Endres, D.Hoiem, and D.Forsyth.Describing objects by their attributes.In CVPR, 2009.2, 5, 6) directly represent images with attributes and apply it to object classification; Patterson etc. (G.Patterson andJ.Hays.Sun attribute database: Discovering, annotating, and recognizing sceneattributes.In CVPR, 2012.2) use attributes to describe scene images and apply it to the classification of scene images; While Lan et al. (T.Lan , W.Yang, Y.W.0003, and G.Mori.Image retrieval with structured object queries using latent ranking svm.In ECCV, 2012, 2) It is believed that the spatial relationship of all objects in the image can be established and used to represent the image, but it is not considered The geometric distribution of all objects throughout the image, as well as the characteristics of individual objects; Kulkarni (G.Kulkarni, V.Premraj, V.Ordonez, S.Dhar, S.Li, Y.Choi, A.C.Berg, and T.L.Berg. Babytalk : Understanding and generating simple image descriptions) established a model of the relationship between objects and objects, but did not take into account the overall background information of the image; Zheng et al. (L.Zheng, S.Wang, Z.Liu, and Q.Tian.Packing and padding: Coupledmulti-index for accurate image retrieval.In CVPR, 2014.2) Add the underlying feature SIFT and color information of the image to the multidimensional index, and use this method to represent the image. Douze et al. (M.Douze, A.Ramisa , and C.Schmid. Combining attributes and fisher vectors for efficient image retrieval.In CVPR, 2011.2, 6, 7) Add attributes to Fisher vectors to represent images. These techniques only consider the overall information of the image, but do not pay attention to the image objects and the local features of these objects; Cao etc. (X.Cao, X.wei, X.Guo, Y.Han, and J.Tang. Augmented image retrieval using multi-orderobject layout with attributes.In ACM MM, 2014.2, 6, 7) built an attribute-based The triangle object structure is used to represent the image, but the global scene information of the image is not considered;

[0004] To sum up, some existing technologies describe images directly with attributes, but ignore the spatial information of objects in the image; some use the relationship between objects to represent images, but do not take into account the overall background of the image information; some consider the overall characteristics of the image, but ignore the objects in the image and the local characteristics of these objects

Images