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
Book ChapterDOI
20 Sep 2010
TL;DR: The elaborated interface, supported by the low-level recognition algorithm, simplifies the evaluation procedures and removes both interpretation uncertainty factor and simple errors from the sketch, using the user interaction interface.
Abstract: Presentation, in a form of a sketched graphical diagram, is often used as a training approach of various didactic levels. However, the trainee examination using the hand-sketch diagrams is still not a common practice, due to the evaluation complexity; both for a teacher and for an automatic recognition system. The elaborated interface, supported by the low-level recognition algorithm, simplifies the evaluation procedures. The solution removes both interpretation uncertainty factor and simple errors from the sketch, using the user interaction interface. The users interaction is based on online pattern recognition of strokes in a colour context. Their representation is returned to the user and stored as a graph structure. Additionally, the interface tracks the sketch creation process for more precise final evaluation. The interface can support many fields as various as business, computer science, mathematics, engineering, music and so on; where a set of graphical symbols are lines and curves composition.
Posted ContentDOI
30 Nov 2022
TL;DR: This article proposed an order-invariant, semantics-aware method for graphic sketch representations, where the cropped sketch patches are linked according to their global semantics or local geometric shapes, by computing the cosine similarity between the captured patch embeddings.
Abstract: Graphic sketch representations are effective for representing sketches. Existing methods take the patches cropped from sketches as the graph nodes, and construct the edges based on sketch's drawing order or Euclidean distances on the canvas. However, the drawing order of a sketch may not be unique, while the patches from semantically related parts of a sketch may be far away from each other on the canvas. In this paper, we propose an order-invariant, semantics-aware method for graphic sketch representations. The cropped sketch patches are linked according to their global semantics or local geometric shapes, namely the synonymous proximity, by computing the cosine similarity between the captured patch embeddings. Such constructed edges are learnable to adapt to the variation of sketch drawings, which enable the message passing among synonymous patches. Aggregating the messages from synonymous patches by graph convolutional networks plays a role of denoising, which is beneficial to produce robust patch embeddings and accurate sketch representations. Furthermore, we enforce a clustering constraint over the embeddings jointly with the network learning. The synonymous patches are self-organized as compact clusters, and their embeddings are guided to move towards their assigned cluster centroids. It raises the accuracy of the computed synonymous proximity. Experimental results show that our method significantly improves the performance on both controllable sketch synthesis and sketch healing.
Proceedings ArticleDOI
17 May 2015
TL;DR: A semantic-probabilistic network to recognise human actions is proposed and a novel approach for Bayesian network nodes' weights calculation is introduced based on the weighted relation between concepts of the ontology in order to reduce the influence of incorrect object detection.
Abstract: In this paper we propose a semantic-probabilistic network to recognise human actions. We use a predefined domain ontology to describe the events and scenarios in the scene as a hierarchical decomposition of simple concepts and variables and then perform an automated conversion of the ontology into a Bayesian network. A novel approach for Bayesian network nodes' weights calculation is introduced based on the weighted relation between concepts of the ontology in order to reduce the influence of incorrect object detection. We then evaluate the performance of our approach using it to predict gestures in a human gesture recognition system, using a set of pre-recorded video sequences.
Journal ArticleDOI
TL;DR: A briefing application with gesture recognition is proposed that easily plays the slides based on gesture detection, feature extraction, and gesture recognition.
Abstract: With the growth of Human Computer Interaction (HCI) technologies, gesture recognition is one of the easiest ways to interact with computer. A briefing application with gesture recognition is proposed that easily plays the slides based on gesture detection, feature extraction, and gesture recognition. We deal with four commonly used actions which are next, previous, play from the start, and ending. The experimental results show that our system provides satisfactory results and is easy to use.
Journal ArticleDOI
TL;DR: A review of recent research efforts in Human Computer Interaction, specifically in hand gesture recognition, is performed, analyzing the state-of-the-art methodology and discussing some important issues about.
Abstract: Getting three-dimensional pose and orientation of parts of the body observed by one or more cameras is of great theoretical in- terest and widely applicable. Usually, computing devices interaction is accomplished by means of a mouse and a keyboard or by touching the screen, but otherwise, human beings relate to their surrounding world using hands, body, and voice in most of their daily activities, therefore, development of more natural and intuitive techniques for interacting with a variety of user interfaces is critical. In this paper, a review of recent research eorts in Human Computer Interaction (HCI), specically in hand gesture recognition, is performed, analyzing the state-of-the-art methodology and discussing some important issues about.

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