Texture sparseness for pixel classification of business document images

Cote, Melissa; Albu, Alexandra Branzan

doi:10.1007/s10032-014-0217-8

Cited by 21 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent TGS approaches such as Cote et al [29] attempt to classify each pixel instead of the CCs. This method assigned each pixel into text, graphics, images or background layers by using texture descriptors based on filter banks and on the measurement of sparseness.…”

Section: Holistic Shape Detectionmentioning

confidence: 99%

New trends on digitisation of complex engineering drawings

Moreno‐García

Elyan

Jayne

2018

Neural Comput & Applic

View full text Add to dashboard Cite

Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming increasingly important. This is mainly due to the legacy of drawings and documents that may provide rich source of information for industries. Analysing these drawings often requires applying a set of digital image processing methods to detect and classify symbols and other components. Despite the recent significant advances in image processing, and in particular in deep neural networks, automatic analysis and processing of these engineering drawings is still far from being complete. This paper presents a general framework for complex engineering drawing digitisation. A thorough and critical review of relevant literature, methods and algorithms in machine learning and machine vision is presented. Real-life industrial scenario on how to contextualise the digitised information from specific type of these drawings, namely piping and instrumentation diagrams, is discussed in details. A discussion of how new trends on machine vision such as deep learning could be applied to this domain is presented with conclusions and suggestions for future research directions.

show abstract

Section: Holistic Shape Detectionmentioning

confidence: 99%

New trends on digitisation of complex engineering drawings

Moreno‐García

Elyan

Jayne

2018

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…The nine first descriptors correspond to the nine H P l =8,R l =1 bins which represent the uniform patterns (cf. equation (19)), while the last one represents the last H P l =8,R l =1 bin which characterizes all the non-uniform patterns (cf. equation (20)).…”

Section: Lbp Featuresmentioning

confidence: 99%

“…This scheme is considered as the support of this comparative study or benchmarking of the nine different texture-based feature sets. Since we aim at characterizing a wide variety of HDI contents and layouts by analyzing the textural properties of HDI contents, a pixelbased approach is adopted in this study due to its advantage to overcome the limits and constraints of region and boundary-based approaches [19]. The pixel-labeling scheme used in our experiments to compare different texture features, is illustrated in Figure 1 The pixel-labeling scheme can be considered as a prerequisite step in the pipeline of DIA and particularly region segmentation and classification.…”

Section: Pixel-labeling Scheme For Comparing Texture Featuresmentioning

confidence: 99%

“…Especially, their processing time depends even more on the image size and resolution due to the use of pixel-based computation, large DI size and high complexity of texture analysis approaches. On the other side, Cote and Albu [19] classified the most widely used texture-based methods by the DIA community into two categories, the statistical and spectral methods. The statistical approaches investigate the spatial distribution of gray-levels within a region of interest, while the spectral ones describe texture by frequency descriptors obtained by computing the response of an image to a given filter bank.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Texture feature benchmarking and evaluation for historical document image analysis

Mehri

Héroux

Gomez‐Krämer

et al. 2017

IJDAR

View full text Add to dashboard Cite

The use of different texture-based methods is pervasive in different sub-fields and tasks of document image analysis and particularly in historical document image analysis. Nevertheless, faced with a large diversity of texturebased methods used for historical document image analysis, few questions arise. Which texture methods are firstly well suited for segmenting graphical contents from textual ones, discriminating various text fonts and scales, and separating different types of graphics? Then, which texture-based method represents a constructive compromise between the performance and the computational cost? Thus, in this article a benchmarking of the most classical and widely used texture-based feature sets has been conducted using a classical texture-based pixel-labeling scheme on a large corpus of historical documents to have satisfactory and clear answers to the above questions. We focus on determining the performance of each texture-based feature set according to the document content. The results reported in this study provide firstly a qualitative measure of which texture-based feature sets are the most appropriate, and secondly a useful benchmark in terms of performance and computational cost for current and future research efforts in historical document image analysis.

show abstract

“…Recently, Cote et.al. [3] propose a method to label pixels in business documents. This approach is based on texture analysis, as many other approaches cited in their state of the art.…”

Section: Related Workmentioning

confidence: 99%

Visual Perception of Unitary Elements for Layout Analysis of Unconstrained Documents in Heterogeneous Databases

Poirriez

Lemaitre

Coüasnon

2014

2014 14th International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

The document layout analysis is a complex task in the context of heterogeneous documents. It is still a challenging problem. In this paper, we present our contribution for the layout analysis competition of the international Maurdor Campaign. Our method is based on a grammatical description of the content of elements. It consists in iteratively finding and then removing the most structuring elements of documents. This method is based on notions of perceptive vision: a combination of points of view of the document, and the analysis of salient contents. Our description is generic enough to deal with a very wide range of heterogeneous documents. This method obtained the second place in Run 2 of Maurdor Campaign (on 1000 documents), and the best results in terms of pixel labeling for text blocs and graphic regions.

show abstract

Texture sparseness for pixel classification of business document images

Cited by 21 publications

References 43 publications

New trends on digitisation of complex engineering drawings

New trends on digitisation of complex engineering drawings

Texture feature benchmarking and evaluation for historical document image analysis

Visual Perception of Unitary Elements for Layout Analysis of Unconstrained Documents in Heterogeneous Databases

Contact Info

Product

Resources

About