Combining pixel projection, OCR, and scale calculation to perform graph feature extraction

Pratomo, Wahyu; Nugroho, Hary

doi:10.1109/icoict.2013.6574559

Cited by 2 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the chart image used here, the important features included title of the chart, title of the axis, legend, value of the chart, and the scale of the chart [10]. Feature extraction on the title of the chart, title of the axis, and also legend was done by using optical character recognition (OCR) so that the lexical seed word of the title, legend, etc will clearly obtained.…”

Section: B Image Feature Extractionmentioning

confidence: 99%

“…Feature extraction on the value and scale of the chart will leads to the recognition of the patterns occurred on the chart. In [10], the detail of the image feature extraction process was discussed.…”

Section: B Image Feature Extractionmentioning

confidence: 99%

“…Feature Extraction is performed by extracting any important feature on the chart image [10]. In the chart image used here, the important features included title of the chart, title of the axis, legend, value of the chart, and the scale of the chart [10].…”

Section: B Image Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Performing chart interpretation using lexical selection in Indonesian language

Pratomo

Barmawi

2013

2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

Self Cite

View full text Add to dashboard Cite

Recently, Indonesian Health Ministry has problems with interpreting health surveillance chart, because they need experts for interpreting the chart. Since it is difficult to provide experts especially in rural area, intelligent system for interpreting the health surveillance chart is necessary. This paper proposed a method to generate sentences in Indonesian language which is extracted from the chart image (e.g. health surveillance chart). The sentences is used to interpret the chart in Indonesian Language. In order to generate sentences, lexicalization based on image features data is proposed to provide some "seed words". These words are used by the NLG system to generate sentences. After obtaining the seed words, the lexical selection is conducted and the main topic of the paragraph is determined. Finally, the main topic was determined and furthermore the sentence in Indonesian Language is ready to be generated. There were some methods for interpreting data such as [1][2][3], but this method could not be used in Indonesian Health Ministry case because most of the chart which should be interpreted are in the form of chart image. Therefore, the proposed method uses NLG based on image extraction and pattern abstraction, such that it can be used for interpreting the chart image.

show abstract

Section: B Image Feature Extractionmentioning

confidence: 99%

Section: B Image Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Performing chart interpretation using lexical selection in Indonesian language

Pratomo

Barmawi

2013

2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…chart title, axis titles, legends, and data values), where those features are extracted from the related chart as explained in [5]. The sentences presented in the summary are the sentences in Indonesian language.…”

Section: Introductionmentioning

confidence: 99%

An automatic health surveillance chart interpretation system based on Indonesian language

Aulia

Barmawi

2015

2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

View full text Add to dashboard Cite

The Indonesian communities have the difficulties for interpreting the chart image, especially the health surveillance chart image. This condition is impacted on late awareness of disease threat. In Indonesia, the chart interpreter system based on Indonesian language is available, but it still has the limitation in generating the textual representation (i.e the health surveillance summaries) in the case of the user involvement. This paper proposed the automatic chart interpreter system as the Natural Language Generation (NLG) system adopting Datato-Text architecture for overcoming the intended problem. In other words, it emphasizes on the automation system, where the automation system refers to the ability of system for determining the related events and the inference of the related events as well as to generating the related summaries without requiring the manual input from the users. Based on the experiment result, the proposed system (HS-CISys) can perform the automation with involving Data Interpretation and Micro Planning. Therefore, Data Interpretation and Micro Planning ensure that the proposed system can generate the health surveillance summaries fully automatic without relying on the manual input from the users.

show abstract

Combining pixel projection, OCR, and scale calculation to perform graph feature extraction

Cited by 2 publications

References 4 publications

Performing chart interpretation using lexical selection in Indonesian language

Performing chart interpretation using lexical selection in Indonesian language

An automatic health surveillance chart interpretation system based on Indonesian language

Contact Info

Product

Resources

About