Segmentation of color documents by line oriented clustering using spatial information

A decomposition method for color document images is proposed in this paper. A two dimensional feature surface is constructed from the input color image, and then a novel and unsupervised method based on contour lines is proposed to segment the surface. In detail, colors of the image pixels are firstly projected to a spherical surface whose center is the background color. The projection is used to transform the observed colors to the corresponding 'ideal' foreground colors. Then the spherical surface is segmented into several non-overlapped regions, and each region corresponds to an individual layer of the input color document image. Finally, the image pixels are projected to the spherical surface and classified to the corresponding layers.

show abstract

“…[5]. Ideally, points belonging to the same content in one document are normally designed to the same 'ideal' color.…”

Section: ¾º½º ×øö ùø óò ò ø ê ×ômentioning

confidence: 99%

“…3) Classify the colors by clustering the samples according to the line shape distribution in the RGB space Worring and Todoran proposed a line oriented clustering method named LOCUSi [5] to make use of the specific distribution of color documents in the RGB space to segment them. It can deal with multiple background regions.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Decomposition of Color Document Images by Projecting Colors to a Spherical Surface

Sun

Naoi

et al. 2008

2008 the Eighth IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

show abstract

“…Many techniques [29,30,31,32,33,34,35,36,37,38] have been proposed that attempt to address the colour issue for text extraction from colour documents. Some of these work directly in the RGB colour model [30,31,33,35], while others convert the images to a HVS (Human Visual System) colour model [29,32,34]. The disadvantages of using a HVS model for such applications are the accuracy and efficiency loss during the conversion [39].…”

Section: A Colour Based Extraction Systemmentioning

confidence: 99%

Use of colour for hand-filled form analysis and recognition

Sherkat

Allen

Wong

2005

Pattern Anal Applic

View full text Add to dashboard Cite

Colour information in form analysis is currently under utilised. As technology has advanced and computing costs have reduced, the processing of forms in colour has now become practicable. This paper describes a novel colour-based approach to the extraction of filled data from colour form images.Images are first quantised to reduce the colour complexity and data is extracted by examining the colour characteristics of the images. The improved performance of the proposed method has been verified by comparing the processing time, recognition rate, extraction precision and recall rate to that of an equivalent black and white system.

show abstract

“…In the case of a scanner image, another type of color-mixing-Gaussian-type blurring-occurs at the boundary of the figure because of the low-pass property of the optical system and the sampling process involved. Therefore, the color of a preprint is distributed along a line between the centers of the fore-and background colors [5]. This property is valid when the ink is opaque or its thickness is uniform.…”

Section: Introductionmentioning

confidence: 96%

Color-Mixing Correction of Overlapped Colors in Scanner Images

Suwa

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Color mixing occurs between the colors of ink and paper when the former is non-opaque. For non-white paper, even the hue of a figure in such an ink may change. In such cases, color conversion is required to extract only the pattern of a specified ink-color from a document image. In this paper, we consider an effective model of the Yule-Nielsen type with the Beer-Lambert law for scanner images of handwritten forms with ballpoint pens, and propose a new method of correcting color mixing. These parameters are calculated using only the information obtained from a pair of scanner images with different-colored paper and the same ink color. The experimental results confirm the feasibility of this approach.

show abstract

Segmentation of color documents by line oriented clustering using spatial information

Cited by 8 publications

References 6 publications

Unsupervised Decomposition of Color Document Images by Projecting Colors to a Spherical Surface

Unsupervised Decomposition of Color Document Images by Projecting Colors to a Spherical Surface

Use of colour for hand-filled form analysis and recognition

Color-Mixing Correction of Overlapped Colors in Scanner Images

Contact Info

Product

Resources

About