Proceedings ArticleDOI
DANIEL: A Deep Architecture for Automatic Analysis and Retrieval of Building Floor Plans
Divya Sharma,Nitin Gupta,Chiranjoy Chattopadhyay,Sameep Mehta +3 more
- pp 420-425
TLDR
This paper proposes Deep Architecture for fiNdIng alikE Layouts (DANIEL), a novel deep learning framework to retrieve similar floor plan layouts from repository and creation of a new complex dataset ROBIN, having three broad dataset categories with 510 real world floor plans.Abstract:
Automatically finding out existing building layouts from a repository is always helpful for an architect to ensure reuse of design and timely completion of projects. In this paper, we propose Deep Architecture for fiNdIng alikE Layouts (DANIEL). Using DANIEL, an architect can search from the existing projects repository of layouts (floor plan), and give accurate recommendation to the buyers. DANIEL is also capable of recommending the property buyers, having a floor plan image, the corresponding rank ordered list of alike layouts. DANIEL is based on the deep learning paradigm to extract both low and high level semantic features from a layout image. The key contributions in the proposed approach are: (i) novel deep learning framework to retrieve similar floor plan layouts from repository; (ii) analysing the effect of individual deep convolutional neural network layers for floor plan retrieval task; and (iii) creation of a new complex dataset ROBIN (Repository Of BuildIng plaNs), having three broad dataset categories with 510 real world floor plans.We have evaluated DANIEL by performing extensive experiments on ROBIN and compared our results with eight different state-of-the-art methods to demonstrate DANIEL’s effectiveness on challenging scenarios.read more
Citations
More filters
Book ChapterDOI
Deep Vectorization of Technical Drawings
Vage Egiazarian,Oleg Voynov,Alexey Artemov,Denis Volkhonskiy,Aleksandr Safin,Maria Taktasheva,Denis Zorin,Denis Zorin,Evgeny Burnaev +8 more
TL;DR: This work presents a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images, that quantitatively and qualitatively outperforms a number of existing techniques on a collection of representative technical drawings.
Journal ArticleDOI
Shall deep learning be the mandatory future of document analysis problems
Nicole Vincent,Jean-Marc Ogier +1 more
TL;DR: In insights about how document analysis systems are built, the examination of the practices of researchers in this field allows us to conclude that the tools that are used, and related issues, have become more and more complex over time.
Book ChapterDOI
Deep Vectorization of Technical Drawings
Vage Egiazarian,Oleg Voynov,Alexey Artemov,Denis Volkhonskiy,Aleksandr Safin,Maria Taktasheva,Denis Zorin,Denis Zorin,Evgeny Burnaev +8 more
TL;DR: In this paper, a transformer-based network is used to estimate vector primitives and an optimization procedure is performed to obtain the final primitive configurations, which outperforms a number of existing techniques on a collection of representative technical drawings.
Journal ArticleDOI
Gaps and requirements for automatic generation of space layouts with optimised energy performance
TL;DR: This paper investigates 10 relevant studies combining GSL and EPO and analyses their gaps and extends the analysis to the research on GSL andEPO.
Journal ArticleDOI
High-level feature aggregation for fine-grained architectural floor plan retrieval
TL;DR: A novel algorithm to extract high-level semantic features from an architectural floor plan using weighted sum of the features is proposed, where a feature can be given more preference over others, during retrieval.
References
More filters
Book ChapterDOI
Line Moments and Invariants for Real Time Processing of Vectorized Contour Data
Georg Lambert,Hua Gao +1 more
TL;DR: A new concept for real time analysis of images based on the vectorized contours is presented and the formalism to apply the geometric moments to contour patterns is derived and an analysis system for structured textures is presented.
Proceedings ArticleDOI
A unified framework for semantic matching of architectural floorplans
TL;DR: A framework for the matching and retrieval of similar architectural floorplans under the query by example paradigm is proposed and a novel graph spectral embedding feature is proposed to uniquely represent the layout of the architectural floorplan.
Proceedings ArticleDOI
Near Convex Region Adjacency Graph and Approximate Neighborhood String Matching for Symbol Spotting in Graphical Documents
TL;DR: A new type of convexity of regions is defined, which allows convex regions to have concavity to some extend and is called Near Convex Region Adjacency Graph (NCRAG), which is formulated as a sub graph matching problem for symbol spotting in graphical documents.
Book ChapterDOI
Runlength Histogram Image Signature for Perceptual Retrieval of Architectural Floor Plans
Lluís-Pere de las Heras,David Fernández,Alicia Fornés,Ernest Valveny,Gemma Sánchez,Josep Lladós +5 more
TL;DR: Runlength histograms extracted in vertical, horizontal and diagonal directions are proposed as a characterization of line and space properties in floorplans, so it can be roughly associated to a description of walls and room structure.
Proceedings ArticleDOI
Extracting information from a query image, for content based image retrieval
TL;DR: A RADAR (Retrieval After Detection and Recognition) framework is proposed, to solve the problem of object-centric CBIR, which retrieves a set of samples from a database of identified categories, similar to the categories in a query image using a matching criteria based on features extracted from the localized region.