Document segmentation and coding techniques

Nadler, Morton

doi:10.1016/0734-189x(84)90153-1

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this page, the union of regions {O, 2, 3} in the SGTF matches with the union {25, 1} in the segmentation. Likewise, the GTR 7 is both split in regions 4, 5, 6,7,8,9,10 in S, and partially merged with GTR 8,9. In other words, segmentation can both split a GTR and merge it partially or totally with other GTR. This cannot be directly seen by scanning the two lists M(Rg) and M(Rsq) separately.…”

Section: Examplesmentioning

confidence: 96%

<title>Automatic benchmarking scheme for page segmentation</title>

1994

View full text Add to dashboard Cite

An automatic bitmap-level, set-based benchmarking scheme for page segmentation, comparing results with predefined "ground truth files" containing all the possible correct solutions, is presented here. A successful page segmentation is a necessary precondition for a document recognition process to be successful. There exists currently no robust method to benchmark segmentation techniques. Moreover, there exist no standard to represent all correct segmentations of a page. The problems addressed here are: design methods to describe all possible correct segmentations for a given page and design methods to compare two segmentations. The proposed segmentation ground truth representation scheme defines ground truth text regions as non-inergeable maximal sets of text lines, merged in a language-dependent direction. It includes the other possible correct seginentations in that authorized cuts in the region are explicitely specified. At this low-level stage, quality criteria for a page segmentation are mainly defined as providing correct input for region ordering and classification. The qualitative and quantitative evaluation method tests the overlap between the two sets of regions. In fact, the regions are defined as being the black pixels contained in the derived polygons. The algorithm is simple and fast, and provides an explicit multi-level output for each segmentation.

show abstract

Section: Examplesmentioning

confidence: 96%

<title>Automatic benchmarking scheme for page segmentation</title>

1994

View full text Add to dashboard Cite

show abstract

“…For example, MRC representation structures a compound image into three layers: mask (texts), foreground (graphics), and background (pictures). Extensive studies have been done on the problem of document segmentation [4,5,6], that is, separate texts, graphics, and pictures apart. We note that although document segmentation is a trivial task for human eyes, it has been one of the long open problems in computer vision research.…”

Section: Two-class Model For Compound Image Sourcementioning

confidence: 99%

“…We argue that computationally expensive document segmentation [4,5,6] is not an indispensable component to compound image coding system. Instead, we propose a simple yet effective two-class segmentation strategy to accommodate the compound nature of document images.…”

Section: Introductionmentioning

confidence: 99%

A Fast and Efficient Topological Coding Algorithm for Compound Images

2003

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

We present a fast and efficient coding algorithm for compound images. Unlike popular mixture raster content (MRC) based approaches, we propose to attack compound image coding problem from the perspective of modeling location uncertainty of image singularities. We suggest that a computationally simple two-class segmentation strategy is sufficient for the coding of compound images. We argue that jointly exploiting topological properties of image source in classification and coding stages is beneficial to the robustness of compound image coding systems. Experiment results have justified effectiveness and robustness of the proposed topological coding algorithm.

show abstract

“…Se define el umbral de segmentation como cl-.alor de luminantia por enrima del cual la imagen de salida sera blanca, y por debajo del cual sera negra. El umbral de segmentation es un tema muy ensayado en la literatura (6,30,36,37,38,42,43,44,45), con una revision de tipo general en (41), pero deja muchas puertas abiertas.…”

Section: Segmentationunclassified

“…Muchos son los intentos de ir resolviendo eficazmente los casos particulares de los algoritmos clasicos en graficos (1,2,4,5,6), con metodos cada vez mas efitientes. Por ejemplo, en el caso de segmentation y tratamiento de histogramas se pueden encontrar experimentos (30,36,23,24,37,38,41,43,44,45), donde hay intentos de introdutir tratamiento y parametros de texturas. El tratamiento de histogramas es una operation que no aparece normalmente en la bibliografia como previa para adecuar una imagen a su vectorization, aunque implititamente va combinada con la segmentation, que es un operation previa obligada a la vectorization que se propone, y eso si se puede leer en algunos antecedentes.…”

Section: Introduccionunclassified

Tratamiento y representación de estructuras gráficas

Pérez¹

View full text Add to dashboard Cite

tiones entre superficies. El algoritmo trabaja perfectamente en los vertices agudos, lo que le hace ampliamente superior a todos los existentes hasta la fecha. Todas las operationes se realizan vectorialmente, eliminando el uso de determinantes que normalmente conduce a problemas mal condirionados.Las coordenadas homogeneas son sustituidas por coordenadas parametricas. Para la realization de este algoritmo son necesarias operariones primitivas de corte entre estructuras en los dibujos. A tal efecto se ha desaxrollado tambien un conjunto de algoritmos con operariones vectoriales, que simplifica los calculos respecto a las formulas corrientes geometria analitica, ademas de aumentar la exactitud. Los mismos algoritmos se emplean para la extraction de curvas de nivel de las estructuras multiformes, lo cual reduce el espario ocupado por el paquete grafico.

show abstract

Document segmentation and coding techniques

Cited by 3 publications

References 0 publications

<title>Automatic benchmarking scheme for page segmentation</title>

<title>Automatic benchmarking scheme for page segmentation</title>

A Fast and Efficient Topological Coding Algorithm for Compound Images

Tratamiento y representación de estructuras gráficas

Contact Info

Product

Resources

About