Classifying Computer Generated Charts

TitleClassifying Computer Generated Charts
Publication TypeConference Papers
Year of Publication2007
AuthorsPrasad VSN, Siddiquie B, Golbeck J, Davis LS
Conference NameContent-Based Multimedia Indexing, 2007. CBMI '07. International Workshop on
Date Published2007/06//
Keywordsalgorithm;scale, analysis;visual, classification;image, database;image, databases;, feature, Internet;bar-chart;curve-plot;image, invariant, match, matching;image, relationship;surface-plot;Internet;image, representation;image, segmentation;pie-chart;pyramid, segmentation;statistical, transform;scatter-plot;spatial

We present an approach for classifying images of charts based on the shape and spatial relationships of their primitives. Five categories are considered: bar-charts, curve-plots, pie-charts, scatter-plots and surface-plots. We introduce two novel features to represent the structural information based on (a) region segmentation and (b) curve saliency. The local shape is characterized using the Histograms of Oriented Gradients (HOG) and the Scale Invariant Feature Transform (SIFT) descriptors. Each image is represented by sets of feature vectors of each modality. The similarity between two images is measured by the overlap in the distribution of the features -measured using the Pyramid Match algorithm. A test image is classified based on its similarity with training images from the categories. The approach is tested with a database of images collected from the Internet.