Hierarchical Graph Representation for Symbol Spotting in Graphical Document Images

Broelemann, Klaus; Dutta, Anjan; Jiang, Xiaoyi; Lladós, Josep

doi:10.1007/978-3-642-34166-3_58

Cited by 10 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…section 2), , which proposed the segmentation algorithm that is used in this work, as well as Broelemann (2014), which presented a collection of algorithms for sketch map understanding. Further works on sketch map understanding from the authors are Broelemann et al (2011) for street segmentation, Broelemann et al (2012 for symbol spotting in sketch maps and floor plans and Schwering et al (2014) for the alignment of sketch maps with metric maps.…”

Section: Related Workmentioning

confidence: 99%

Automatic understanding of sketch maps using context-aware classification

Broelemann

Jiang

Schwering

2016

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Automatic understanding of sketch maps using context-aware classification

Broelemann

Jiang

Schwering

2016

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

“…In architectural floor plan analysis, images are typically binary (bi-level) or grayscale and thus shape [49], as opposed to color for instance, is the most important visual cue for describing them. The main challenges present in this step are scale and rotation changes, [35,36,37,38] Scale and rotation invariant, robust to small variations Vectors and quadrilateral primitives V Hierarchical Plausibility Graph (HPG) [39,40] Robust to various distortions Critical points and lines V Shape, topology, and Region Adjacency Graph (RAG) [41,42] Rotation and scale invariant Image regions V Boundary and RAG [43] Rotation and scale invariant Image regions V Convexity and Near Convex Region Adjacency Graph (NCRAG) [44] Rotation and scale invariant Oriented line segments V Bag-of-GraphPaths (BoGP) [45] Rotation invariant Critical points V Jacobs' statistical grouping [46] Scale and rotation invariant Contour map V Bag-of-Relations (BoR) [47] Scale and rotation invariant and robust to irregularities Thick (solid) components, circles, corners and extremities V Cassinian ovals [48] Not invariant to scaling and rotation…”

Section: Symbol Spotting: Description Phasementioning

confidence: 99%

Geometry-based symbol spotting in born-digital architectural floor plans

2021

View full text Add to dashboard Cite

Architectural floor plans are scale-accurate 2D drawings of one level of a building, seen from above, which convey structural and semantic information related to rooms, walls, symbols, textual data, etc. They consist of lines, curves, symbols, and textual markings, showing the relationships between rooms and all physical features, required for the proper construction or renovation of the building.First, this thesis provides a thorough study of state-of-the-art on symbol spotting methods for architectural drawings, an application domain providing the document image analysis and graphic recognition communities with an interesting set of challenges linked to the sheer complexity and density of embedded information, that have yet to be resolved.Second, we propose a hybrid method that capitalizes on strengths of both vector-based and pixel-based symbol spotting techniques. In the description phase, the salient geometric constituents of a symbol are extracted by a variety of vectorization techniques, including a proposed voting-based algorithm for finding partial ellipses. This enables us to better handle local shape irregularities and boundary discontinuities, as well as partial occlusion and overlap. In the matching phase, the spatial relationship between the geometric primitives is encoded via a primitive-aware proximity graph. A statistical approach is then used to rapidly yield a coarse localization of symbols within the plan. Localization is further refined with a pixel-based step implementing a modified cross-correlation function. Experimental results on the public SESYD synthetic dataset and real-world images demonstrate that our approach clearly outperforms other popular symbol spotting approaches.Traditional on-the-fly symbol spotting methods are unable to address the semantic challenge of graphical notation variability, i.e. low intra-class symbol similarity, an issue that is particularly important in architectural floor plan analysis. The presence of occlusion and clutter, characteristic of real-world plans, along with a varying graphical symbol complexity from almost trivial to highly complex, also pose challenges to existing spotting methods. iv Third, we address all the above issues by leveraging recent advances in deep learningbased neural networks and adapting an object detection framework based on the YOLO (You Only Look Once) architecture. We propose a training strategy based on tiles, avoiding many issues particular to deep learning-based object detection networks related to the relatively small size of symbols compared to entire floor plans, aspect ratios, and data augmentation. Experimental results demonstrate that our method successfully detects architectural symbols with low intra-class similarity and of variable graphical complexity,

show abstract

“…In general, hierarchical models have been successfully employed in many different domains within the computer vision and image processing field, such as, image segmentation [17,18], scene categorization [19], action recognition [49], shape classification [12], graphic recognition [50], 3D object recognition [13] etc. These approaches usually exploit some kind of pyramidal structure containing information at various resolutions.…”

Section: Hierarchical Graph Representationmentioning

confidence: 99%

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

Dutta

Riba

Lladós

et al. 2019

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Despite being very successful within the pattern recognition and machine learning community, graph-based methods are often unusable with many machine learning tools. This is because of the incompatibility of most of the mathematical operations in graph domain. Graph embedding has been proposed as a way to tackle these difficulties, which maps graphs to a vector space and makes the standard machine learning techniques applicable for them. However, it is well known that graph embedding techniques usually suffer from the loss of structural information. In this paper, given a graph, we consider its hierarchical structure for mapping it into a vector space. The hierarchical structure is constructed by topologically clustering the graph nodes, and considering each cluster as a node in the upper hierarchical level. Once this hierarchical structure of graph is constructed, we consider its various configurations of its parts, and use stochastic graphlet embedding (SGE) for mapping them into vector space. Broadly speaking, SGE produces a distribution of uniformly sampled low to high order graphlets as a way to embed graphs into the vector space.In what follows, the coarse-to-fine structure of a graph hierarchy and the statistics fetched through the distribution of low to high order stochastic graphlets complements each other and include important structural information with varied contexts. Altogether, these two techniques substantially cope with the usual information loss involved in graph embedding techniques, and it is not a surprise that we obtain more robust vector space embedding of graphs. This fact has been corroborated through a detailed experimental evaluation on various benchmark graph datasets, where we outperform the state-of-the-art methods.

show abstract

Hierarchical Graph Representation for Symbol Spotting in Graphical Document Images

Cited by 10 publications

References 8 publications

Automatic understanding of sketch maps using context-aware classification

Automatic understanding of sketch maps using context-aware classification

Geometry-based symbol spotting in born-digital architectural floor plans

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

Contact Info

Product

Resources

About