Topic
Sketch recognition
About: Sketch recognition is a research topic. Over the lifetime, 1611 publications have been published within this topic receiving 40284 citations.
Papers published on a yearly basis
Papers
More filters
•
01 Jan 2012TL;DR: A novel framework for sketch recognition that seamlessly combines a rich representation of local visual appearance with a probabilistic graphical model for capturing higher level relationships is presented, which is one of the first direct comparisons that shows a sketch recognition interface significantly outperforming a professional industry-standard CAD-based tool.
Abstract: As our interaction with computing shifts away from the traditional desktop model (eg, towards smartphones, tablets, touch-enabled displays), the technology that drives this interaction needs to evolve as well Wouldn't it be great if we could talk, write, and draw to a computer just like we do with each other? This thesis addresses the drawing aspect of that vision: enabling computers to understand the meaning and semantics of free-hand diagrams We present a novel framework for sketch recognition that seamlessly combines a rich representation of local visual appearance with a probabilistic graphical model for capturing higher level relationships This joint model makes our system less sensitive to noise and drawing variations, improving accuracy and robustness The result is a recognizer that is better able to handle the wide range of drawing styles found in messy freehand sketches To preserve the fluid process of sketching on paper, our interface allows users to draw diagrams just as they would on paper, using the same notations and conventions For the isolated symbol recognition task our method exceeds state-of-the-art performance in three domains: handwritten digits, PowerPoint shapes, and electrical circuit symbols For the complete diagram recognition task it was able to achieve excellent performance on both chemistry and circuit diagrams, improving on the best previous results Furthermore, in an on-line study our new interface was on average over twice as fast as the existing CAD-based method for authoring chemical diagrams, even for novice users who had little or no experience using a tablet This is one of the first direct comparisons that shows a sketch recognition interface significantly outperforming a professional industry-standard CAD-based tool (Copies available exclusively from MIT Libraries, Rm 14-0551, Cambridge, MA 02139-4307 Ph 617-253-5668; Fax 617-253-1690)
3 citations
••
01 Jan 1997
TL;DR: This real-time human gesture recognition system does not require any sensors or cables to be attached to the subject’s body and the key technology here is optical information processing.
Abstract: V IS U A L P R O C E E D IN G S E L E C T R IC G A R D E N In this real-time human gesture recognition system, video images of a person are sent to a recognition module. The system does not require any sensors or cables to be attached to the subject’s body. The key technology here is optical information processing. In the recognition module, video images taken by a CCD camera are presented to a holographic device that generates a vector representation of the gesture. The vector is then analyzed electronically to determine the gesture in real time. Optical Gesture Recognition System Seiji Kobayshi •
3 citations
•
3 citations
••
24 Aug 2014TL;DR: This work proposes the use of shape features for a preliminary selection of the candidate photos to be successively analyzed by more complex state-of-the-art techniques, and can be computed and matched in a very short time.
Abstract: Sketch recognition for forensic applications is a very challenging task and several solutions have been recently proposed. Considering that real mug shot databases can be very large, one important aspect to consider in this scenario is also the efficiency of the search procedure. This work proposes the use of shape features for a preliminary selection of the candidate photos to be successively analyzed by more complex state-of-the-art techniques. The proposed features can be computed and matched in a very short time, and at the same time they are able to significantly reduce the search space, thus allowing to speed up the recognition process.
3 citations
••
29 Nov 2010TL;DR: A 3D multi-touch recognition method based on a quantitative touch feedback mechanism to achieve the input and erasing gesture of characters for the applications in virtual exhibition.
Abstract: Multi-touch interaction is a more free interaction means, however, recent related applications limit in the 2D area, such as interaction desktop, shop window. For the applications in virtual exhibition, this paper proposes a 3D multi-touch recognition method. The different gestures firstly are defined for gesture recognition. Then a character recognition algorithm based on directions is presented to achieve the input and erasing gesture of characters. Further, based on a quantitative touch feedback mechanism, the three-dimensional multi-touch interaction algorithm is presented. Finally, we implement the multi-touch interaction display in different conditions, including moving, rotating, zoom for three-dimensional scene.
3 citations