Title :
Combining pixel projection, OCR, and scale calculation to perform graph feature extraction
Author :
Pratomo, Wahyu ; Nugroho, Heru
Author_Institution :
ITTElkom Grad. Sch., Telkom Inst. of Technol., Bandung, Indonesia
Abstract :
Graph Feature Extraction is the task to collect any important feature on the graph image so the extracted data can be further processed. In this paper, it is assumed that the graph consists only one single curve. The extracted features here are graph title, axis title, axis values, legend, scales, and curve values.
Keywords :
feature extraction; graph theory; optical character recognition; OCR; axis title; axis values; combining pixel projection; curve values; data extraction; graph feature extraction; graph image; legend values; optical character recognition; scale calculation; scaled values; Character recognition; Communications technology; Data mining; Feature extraction; Image reconstruction; Optical character recognition software; Optical imaging; OCR; Pixel projection; feature extraction; graph image; graph value; image form; numeric form; scale calculation;
Conference_Titel :
Information and Communication Technology (ICoICT), 2013 International Conference of
Conference_Location :
Bandung
Print_ISBN :
978-1-4673-4990-1
DOI :
10.1109/ICoICT.2013.6574559
