A Few Steps Towards On-the-Fly Symbol Recognition with Relevance Feedback

Rendek, Jan; Tombre, Karl

doi:10.1007/11669487_54

Cited by 4 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current consensus is that the most appropriate way of dealing with these classes of problems is to use weakly supervised classification and user relevance feedback to implement a symbol spotting approach … and hope for the best. [Rendek 2006] This is one of the harder cases, where there is a fairly well, although insufficiently formalized interpretation context, but without sufficient visual support in the data (i.e. there is a large semantic gap) In this case, the most appropriate approach is likely to investigate further whether there are classes of interpretation contexts that can be better specified and reduce the problem to a more constrained one.…”

Section: Lowmentioning

confidence: 99%

Analysis and Interpretation of Graphical Documents

Ogier

2014

Handbook of Document Image Processing and Recognition

Self Cite

View full text Add to dashboard Cite

This chapter is dedicated to the analysis and the interpretation of graphical documents, and as such, builds upon many of the topics covered in other parts of this handbook. It will therefore not focus on any of the technical issues related to graphical documents, such as low level filtering and binarization, primitive extraction and vectorization as developed in Chapters 2.1 and 5.1 or symbol recognition, for instance, as developed in Chapter 5.2. These tools are put in a broader framework and threaded together in complex pipelines to solve interpretation questions. This chapter provides an overview of how analysis strategies have contributed to constructing these pipelines, how specific domain knowledge is integrated in these analyses, and which interpretation contexts have been contributed to successful approaches.

show abstract

Section: Lowmentioning

confidence: 99%

Analysis and Interpretation of Graphical Documents

Ogier

2014

Handbook of Document Image Processing and Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Work in our group [45,35] has used the latter to construct an unconstrained navigation tool in handwritten documents.…”

Section: Relevance Feedbackmentioning

confidence: 99%

Pattern Recognition Methods for Querying and Browsing Technical Documentation

Tombre

2008

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

To cite this version:Karl Tombre, Bart Lamiroy. Abstract. Graphics recognition deals with the specific pattern recognition problems found in graphics-rich documents, typical technical documentation of all kinds. In this paper, we propose a short journey through 20 years of involvement and contributions within this scientific community, and explore more precisely a few interesting issues found when the problem is to browse, query and navigate in a large and complex set of technical documents.

show abstract

“…This process can be more complex when no library of models is available at first and the input query is selected interactively by user. In this case, which is known as on-the-fly symbol recognition [17], learning-based methods cannot be used, and no initial assumption can be made about the shape of the input model. Finding and locating architectural symbols in context, i.e.…”

Section: Introduction 11 Overviewmentioning

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

A Few Steps Towards On-the-Fly Symbol Recognition with Relevance Feedback

Cited by 4 publications

References 24 publications

Analysis and Interpretation of Graphical Documents

Analysis and Interpretation of Graphical Documents

Pattern Recognition Methods for Querying and Browsing Technical Documentation

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

Contact Info

Product

Resources

About