Sketch recognition

About: Sketch recognition is a research topic. Over the lifetime, 1611 publications have been published within this topic receiving 40284 citations.

Sketch interpretation using multiscale stochastic models of temporal patterns

Abstract: Sketching is a natural mode of interaction used in a variety of settings. For example, people sketch during early design and brainstorming sessions to guide the thought process; when we communicate certain ideas, we use sketching as an additional modality to convey ideas that can not be put in words. The emergence of hardware such as PDAs and Tablet PCs has enabled capturing freehand sketches, enabling the routine use of sketching as an additional human-computer interaction modality. But despite the availability of pen based information capture hardware, relatively little effort has been put into developing software capable of understanding and reasoning about sketches. To date, most approaches to sketch recognition have treated sketches as images (i.e., static finished products) and have applied vision algorithms for recognition. However, unlike images, sketches are produced incrementally and interactively, one stroke at a time and their processing should take advantage of this. This thesis explores ways of doing sketch recognition by extracting as much information as possible from temporal patterns that appear during sketching. We present a sketch recognition framework based on hierarchical statistical models of temporal patterns. We show that in certain domains, stroke orderings used in the course of drawing individual objects contain temporal patterns that can aid recognition. We build on this work to show how sketch recognition systems can use knowledge of both common stroke orderings and common object orderings. We describe a statistical framework based on Dynamic Bayesian Networks that can learn temporal models of object-level and stroke-level patterns for recognition. Our framework supports multi-object strokes, multi-stroke objects, and allows interspersed drawing of objects---relaxing the assumption that objects are drawn one at a time. Our system also supports real-valued feature representations using a numerically stable recognition algorithm. We present recognition results for hand-drawn electronic circuit diagrams. The results show that modeling temporal patterns at multiple scales provides a significant increase in correct recognition rates, with no added computational penalties. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

Machine-based Intelligent Face Recognition

Abstract: Machine-based Intelligent Face Recognition discusses the general engineering method of imitating intelligent human brains for video-based face recognition in a fundamental way, which is completely unsupervised, automatic, self-learning, self-updated and robust It also overviews state-of-the-art research on cognitive-based biometrics and machine-based biometrics, and especially the advances in face recognition This book is intended for scientists, researchers, engineers, and students in the field of computer vision, machine intelligence, and particularly of face recognition Dr Dengpan Mou, Dr-Ing and MSc from University of Ulm, Germany, is with Harman/Becker Automotive Systems GmbH, working on video processing, computer vision and machine learning research and development topics

Visual languages for sketching documents

Abstract: We present a visual approach to layout documents as hand-drawn compositions of simple geometric shapes. This approach is based on a grammatical method to support document design through sketch recognition which explicitly addresses visual ambiguity. We use fuzzy relational adjacency grammars to provide a natural handling of fuzzy logic and spatial relation syntax in a single unified formalism. Fuzzy relations enable us to replace spatial constraints such as "a is above b" or "a is parallel to c" by quantities that express a degree of uncertainty. Their use allows us to associate a "measure of goodness" to all data and to intermediate and final results. We developed a prototype application that supports document layout sketching in a simple way.

Accelerometer-based hand gesture recognition system for interaction in digital TV

Abstract: This paper presents the design and implementation of a system of accelerometer-based hand gesture recognition This system will be embedded within a modern remote control to improve human-machine interaction in the context of digital TV of Argentina As the recognition of hand gestures is a pattern classification problem, two techniques based on artificial neural networks are explored: multilayer perceptron and support vector machine This is performed in order to compare results and select the tool that best fits the problem Jointly, signal digital processing techniques are used for preprocessing and adapting of the input signals to pattern recognition models A gestural vocabulary of 8 types of gestures was used, which was also used by other similar works in order to compare results An appropriate trade-off between the classifier recognition precision and resource utilization of the hardware platform is required in order to implement the solution within an embedded system The obtained results of precision and utilization of resources are excellent