Text and non-text separation in offline document images: a survey

Bhowmik, Showmik; Sarkar, Ram; Nasipuri, Mita; Doermann, David

doi:10.1007/s10032-018-0296-z

Cited by 50 publications

(23 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Text and symbol recognition techniques on images, technical drawings and maps have been researched for a long time [61], but new approaches have been proposed in recent years [21,25,62]. The general problem of text/non-text separation is relevant for a wide range of documents, such as manuscripts, images and video, in every situation in which a semantic analysis is used to index and rank them.…”

Section: Text and Symbol Removalmentioning

confidence: 99%

“…Text/non-text separation is usually performed by the classification of features on the image in text and non-text classes. This classification can be done at the pixel level, using only the radiometric information, or at feature level, using radiometric and morphological, shape-based, information [25]. The latter approach allows the use of additional information, such as texture, which can be derived from pixels' radiometric information.…”

Section: Text and Symbol Removalmentioning

confidence: 99%

“…A survey of techniques for text/non-text separation on maps can be found in [25]: methods described there are mostly based on the combination of pixelwise classification and thresholding and the application of filter rules based on a priori knowledge of the morphological features of the characters, symbols and lines to recognize. Other approaches include binarization and template matching [66,67], "text areas" detection and the application of standard optical character recognition (OCR) software [68], or the use of a tailored connected component analysis and segmentation [69].…”

Section: Text and Symbol Removalmentioning

confidence: 99%

“…Together with thematic maps created from orthoimages [23] will form a comprehensive dataset (Trentinoland) for the study of the forest landscape evolution in the last few centuries [24] in the Italian region of Trentino. Several techniques are available for text extraction from printed documents [25], but they focus on the development of effective document processing methods rather than map categories' preservation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

New Tools for the Classification and Filtering of Historical Maps

Gobbi

Ciolli

Porta

et al. 2019

IJGI

View full text Add to dashboard Cite

Historical maps constitute an essential information for investigating the ecological and landscape features of a region over time. The integration of heritage maps in GIS models requires their digitalization and classification. This paper presents a semi-automatic procedure for the digitalization of heritage maps and the successive filtering of undesirable features such as text, symbols and boundary lines. The digitalization step is carried out using Object-based Image Analysis (OBIA) in GRASS GIS and R, combining image segmentation and machine-learning classification. The filtering step is performed by two GRASS GIS modules developed during this study and made available as GRASS GIS add-ons. The first module evaluates the size of the filter window needed for the removal of text, symbols and lines; the second module replaces the values of pixels of the category to be removed with values of the surrounding pixels. The procedure has been tested on three maps with different characteristics, the “Historical Cadaster Map for the Province of Trento” (1859), the “Italian Kingdom Forest Map” (1926) and the “Map of the potential limit of the forest in Trentino” (1992), with an average classification accuracy of 97%. These results improve the performance of classification of heritage maps compared to more classical methods, making the proposed procedure that can be applied to heterogeneous sets of maps, a viable approach.

show abstract

Section: Text and Symbol Removalmentioning

confidence: 99%

Section: Text and Symbol Removalmentioning

confidence: 99%

Section: Text and Symbol Removalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

New Tools for the Classification and Filtering of Historical Maps

Gobbi

Ciolli

Porta

et al. 2019

IJGI

View full text Add to dashboard Cite

show abstract

“…Técnicas de descoberta de subimagens podem ser encontradas em [10]. Um survey de abordagens a esse problema pode ser encontrado em [11]. Outros trabalhos que abordam algoritmos específicos são [12][13][14].…”

Section: Segmentação De Subimagens De Textounclassified

Processamento e Navegação por Tópicos em Imagens de Páginas de Jornais Históricos

Sá¹,

Maia²

2020

Anais Do XI Computer on the Beach - COTB '20

View full text Add to dashboard Cite

This paper presents the architecture and operation of a HistoricalNewspaper Page Image Topic Navigation System designed tofacilitate the access and use of social and historical research tothe historical newspaper collection. The system consists of fourmodules which are: Text Subimage Segmentation, Text Extractionand Preprocessing, Topic Network Extraction, and Document Viewingand Retrieval Interface. The algorithmic and technological approachesof each module are described and the initial test resultsare presented.

show abstract