Scientific Chart image property identification by connected component labeling in PDF files

Karthikeyani, V.; Nagarajan, Srikantan S.

doi:10.1109/icectech.2011.5941888

Cited by 5 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A two-step method is used for this purpose where the first step uses an enhanced variant of connected component labeling to separate text and graphical objects and the second step uses a statistical feature based algorithm to locate and identify the chart objects in the PDF file. (Karthikeyani & Nagarajan, 2011) The second step in the proposed algorithm uses a simple procedure to classify the identified charts as 2-dimensional and 3-dimensional charts. The charts considered are bar, pie, doughnut and line.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…On the other hand, the graphic components include axes, data markers, data series, tick marks and gridlines. The enhanced connected component algorithm (Karthikeyani & Nagarajan, 2011) is used again for this purpose. Both the components exhibit different characteristics and these characteristics are exploited for identifying 2D and 3D charts.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Ensemble Classification System for Scientific Chart Recognition from PDF Files

Nagarajan¹,

Karthikeyani

2012

International Journal of Computer Vision and Image Processing

Self Cite

View full text Add to dashboard Cite

Portable Document Format (PDF) is the most frequently used universal document format on the Internet and E-Publishing. Wide usage of PDF files has increased the need of conversion tools that convert PDF file content to text or HTML formats. A PDF converter can be categorized into two domains, namely, text recognition and graphics recognition. This paper focus on graphic recognition, especially chart type identification, which is concerned with developing algorithms that has the ability to determine the type of a given chart image from a PDF file. In the proposed system, initially an enhanced connected component and statistical feature based method is used to separate the chart region from other regions. The chart region is then analyzed and grouped as either 2-dimensional or 3-dimensional chart. After separating the graphic component from the text components, feature extraction is performed. The features can be grouped as object features, texture features and shape features. The combined feature vector is then classified using ensemble classification system. Experimental results show that the chart separation, feature extraction and ensemble classification models significantly improve the quality of chart identification.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Proposed Methodologymentioning

confidence: 99%

Ensemble Classification System for Scientific Chart Recognition from PDF Files

Nagarajan¹,

Karthikeyani

2012

International Journal of Computer Vision and Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first step is to locate the chart object, the second step is to extract the graph object and the third step is to identify the type of chart. The first two steps are dealt in [11]. This paper focus on the third step that is to identify the type of graph located from the PDF file using machine learning classification algorithms.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Classification Algorithms to Recognize Chart Types in Portable Document Format (PDF) Files

Karthikeyani¹,

Nagarajan²

2012

IJCA

Self Cite

View full text Add to dashboard Cite

Chart recognition system from PDF files is a relatively young research field where techniques and algorithms are proposed to identify type of charts and interpret them. This paper focus on recognition of chart type that is a part of PDF document using texture features and classification algorithm. Eleven types of texture features and three classifiers, namely, Multilayer perceptron, support vector machine and K nearest neighbour, are used. Performance analysis of the proposed chart type recognition systems show that texture features for chart type recognition has promising future and produces best result while using KNN and SVM algorithm.

show abstract

Review of chart image detection and classification

Bajić

Job

2023

IJDAR

View full text Add to dashboard Cite

Scientific Chart image property identification by connected component labeling in PDF files

Cited by 5 publications

References 13 publications

Ensemble Classification System for Scientific Chart Recognition from PDF Files

Ensemble Classification System for Scientific Chart Recognition from PDF Files

Machine Learning Classification Algorithms to Recognize Chart Types in Portable Document Format (PDF) Files

Review of chart image detection and classification

Contact Info

Product

Resources

About