scispace - formally typeset
Search or ask a question
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
More filters
Journal Article
TL;DR: A real-time non-photorealistic rendering technique that generates a sketch from a real photograph is presented, and the authors draw the contours according to the conceptual color difference, and generate the shadow with the importance map which is produced from the intensity of light.
Abstract: A real-time non-photorealistic rendering technique that generates a sketch from a real photograph is presented in this paper. In accordance with the features of sketch and human vision,the authors draw the contours according to the conceptual color difference,and generate the shadow with the importance map which is produced from the intensity of light,and combine them to create the final desired sketch. Compared with current methods,the framework design doesn’t demand human-computer interaction,and can get better visual effects as well as allow real-time implementation.

1 citations

Proceedings Article
05 Aug 2011
TL;DR: These proceedings contain the papers presented at the eighth instantiation of the annual academic gathering on "Sketch-Based Interfaces and Modeling," and present a mix of innovative ideas in sketch recognition, 3D modeling, and sketch-based interface usability.
Abstract: These proceedings contain the papers presented at the eighth instantiation of the annual academic gathering on "Sketch-Based Interfaces and Modeling." SBIM was initiated as a workshop in 2004 to provide a unique venue to discuss novel algorithms, interfaces, perspectives, and uses for sketch-based technologies. Since that time, SBIM has become a popular and respected symposium (in 2009) associated with both ACM SIGRGRAPH and Eurographics, and remains the top venue dedicated to the discussion and presentation of 2D or 3D sketch-based academic work representing recognition, interfaces, and modeling research perspective. SBIM is an international conference that alternates between North American and European locations. Last year, SBIM was located in Annecy, France for the second time, in conjunction with the Annecy Animation Film Festival. This year, SBIM is located in Vancouver, Canada for the first time. Additionally, this is the first year that SBIM is a joint and is co-located with SIGGRAPH and is joint with Computational Aesthetics and Non-Photorealistic Animation and Rendering. We had 36 paper submissions this year, which matches the number we had last year. Each paper was double blind reviewed by at least four members of our international program committee and we were able to accept 18 of them for the symposium. As in previous years, the quality of the submitted papers was strong, resulting in a high acceptance rate, a testament to those researchers who work in this field. The papers in these proceedings present a mix of innovative ideas in sketch recognition, 3D modeling, and sketch-based interface usability.

1 citations

Proceedings ArticleDOI
27 May 2016
TL;DR: The system recognized the state of user's hand and fingers via the proposed algorithm and could overcome the effects of environments and provide high quality gesture recognition.
Abstract: We presented a “Design of Three Dimensional Gestures Interactive Displays Based on Complex Background.” The system recognized the state of user's hand and fingers via the proposed algorithm. This system could overcome the effects of environments and provide high quality gesture recognition.

1 citations

Proceedings ArticleDOI
31 Mar 2001
TL;DR: The work of this group on the use of computer vision to complement existing modes of human-interaction has been the development of an iris tracker and a hand tracker for HCI similar to a "visual mouse", and a deformable model of a generic face for facial feature extraction.
Abstract: In this paper, we describe the work of our group on the use of computer vision to complement existing modes of human-interaction. Our main achievements have been the development of an iris tracker and a hand tracker for HCI similar to a "visual mouse", and a deformable model of a generic face for facial feature extraction, for emotion recognition.

1 citations

Proceedings ArticleDOI
03 Sep 2000
TL;DR: The method using linear combination is simple and needs only a few learning samples and is able to distinguish objects with very similar patterns and is more accurate than other conventional methods in the literature.
Abstract: Presents a method for visualization, understanding and recognition of artificial objects. The method using linear combination is simple and needs only a few learning samples. Furthermore, it can strengthen the advantages of conventional methods while overcoming their drawbacks. Also, it is able to distinguish objects with very similar patterns and is more accurate than other conventional methods in the literature. Four experiments are included to demonstrate the method's simplicity and accuracy.

1 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
84% related
Object detection
46.1K papers, 1.3M citations
83% related
Feature extraction
111.8K papers, 2.1M citations
82% related
Image segmentation
79.6K papers, 1.8M citations
81% related
Convolutional neural network
74.7K papers, 2M citations
80% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202326
202271
202130
202029
201946
201827