IMISketch: An interactive method for sketch recognition
نویسندگان
چکیده
8 In this paper, we present a new generic method for an interactive interpreta9 tion of sketches to avoid a fastidious verification phase. After a preprocess10 ing phase in which we extract a set of primitives, the interpretation process 11 consists of an interactive analysis. The analyzer is based on a competitive 12 breadth-first exploration of the analysis tree. As opposed to well known 13 structural approaches, this method allows to evaluate simultaneously several 14 possible hypotheses of recognition in a dynamic local context of document. 15 The decision process is able to solicit the user in the case of strong ambiguity: 16 when it is not sure to make the right decision. The user explicitly validates 17 the right decision. While, in practice these approaches often induce a large 18 combinatory, this paper presents optimization strategies to reduce the com19 binatory. The goal of these optimizations is to have time analysis compatible 20 with user expectations. These strategies have been integrated into both pre21 processing and analysis phases. To validate this interactive analysis method, 22 several experiments are reported in this paper on off-line handwritten 2D 23 architectural floor plans. 24 Email addresses: [email protected] (Achraf Ghorbel), [email protected] (Eric Anquetil), [email protected] (Jean Camillerapp), [email protected] (Aurélie Lemaitre) Preprint submitted to Pattern Recognition September 2, 2013
منابع مشابه
Interactive interpretation of structured documents: Application to the recognition of handwritten architectural plans
This paper addresses a whole architecture, including the IMISketch method. IMISketch method incorporates two aspects: document analysis and interactivity. This paper describes a global vision of all the parts of the project. IMISketch is a generic method for an interactive interpretation of handwritten sketches. The analysis of complex documents requires the management of uncertainty. While, in...
متن کاملPattern Recognition Strategies for Interactive Sketch Composition
The design of industrial pen-based systems for sketch composition and interpretation is still a challenging problem when dealing with complex domains. In this paper, we present a method that is based on an eager interpretation of the user strokes, i.e. on an incremental process with visual feedback to the user. We present the benefits of using such an interactive approach in order to design eff...
متن کاملHMM-Based Efficient Sketch Recognition1
Current sketch recognition systems treat sketches as images or a collection of strokes, rather than viewing sketching as an interactive and incremental process. We show how viewing sketching as an interactive process allows us to recognize sketches using Hidden Markov Models. We report results of a user study indicating that in certain domains people draw objects using consistent stroke orderin...
متن کاملComparison Between Unsupervised and Supervise Fuzzy Clustering Method in Interactive Mode to Obtain the Best Result for Extract Subtle Patterns from Seismic Facies Maps
Pattern recognition on seismic data is a useful technique for generating seismic facies maps that capture changes in the geological depositional setting. Seismic facies analysis can be performed using the supervised and unsupervised pattern recognition methods. Each of these methods has its own advantages and disadvantages. In this paper, we compared and evaluated the capability of two unsuperv...
متن کاملSMATS: Sketch-Based Modeling and Analysis of Truss Systems
The present work intends to introduce a domain-specific sketch method for modeling and analysis of forms and structures concurrently. The approach adopted particularly addresses architects, aiming to provide a natural environment for them to present and appraise structural configurations of different truss systems by means of sketching. This is achieved by developing Sketch-based Modeling and A...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Pattern Recognition Letters
دوره 35 شماره
صفحات -
تاریخ انتشار 2014