Sketch recognition

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

Dynamically constructed Bayes nets for multi-domain sketch understanding

Abstract: This paper presents a novel form of dynamically constructed Bayes net, developed for multidomain sketch recognition. Our sketch recognition engine integrates shape information and domain knowledge to improve recognition accuracy across a variety of domains using an extendible, hierarchical approach. Our Bayes net framework integrates the influence of stroke data and domain-specific context in recognition, enabling our recognition engine to handle noisy input. We illustrate this behavior with qualitative and quantitative results in two domains: hand-drawn family trees and circuits.

Deep Graphical Feature Learning for Face Sketch Synthesis

Abstract: The exemplar-based face sketch synthesis method generally contains two steps: neighbor selection and reconstruction weight representation. Pixel intensities are widely used as features by most of the existing exemplar-based methods, which lacks of representation ability and robustness to light variations and clutter backgrounds. We present a novel face sketch synthesis method combining generative exemplar-based method and discriminatively trained deep convolutional neural networks (dCNNs) via a deep graphical feature learning framework. Our method works in both two steps by using deep discriminative representations derived from dCNNs. Instead of using it directly, we boost its representation capability by a deep graphical feature learning framework. Finally, the optimal weights of deep representations and optimal reconstruction weights for face sketch synthesis can be obtained simultaneously. With the optimal reconstruction weights, we can synthesize high quality sketches which is robust against light variations and clutter backgrounds. Extensive experiments on public face sketch databases show that our method outperforms state-of-the-art methods, in terms of both synthesis quality and recognition ability.

Human Computer Interaction for Vision Based Hand Gesture Recognition: A Survey

Abstract: The ultimate aim is to bring Human Computer Interaction to a regime where interactions with computers will be as natural as an interaction between humans, and to this end, incorporating gestures in HCI is an important research area Gestures have long been considered as an interaction technique that can potentially deliver more natural, creative and intuitive methods for communicating with our computers This paper provides a summary of previous surveys done in this area and focuses on the different application domain which employs hand gestures for efficient interaction The use of hand gestures as a natural interface serves as a motivating force for research in gesture taxonomies, its representations and recognition techniques Also provides an analysis of existing literature related to gesture recognition systems for human computer interaction by categorizing it based on different parameters The main goal of this survey is to provide researchers in the field with a summary of progress achieved to date and to help identify areas where further research is needed

Multi-Graph Transformer for Free-Hand Sketch Recognition

Abstract: Learning meaningful representations of free-hand sketches remains a challenging task given the signal sparsity and the high-level abstraction of sketches. Existing techniques have focused on exploiting either the static nature of sketches with Convolutional Neural Networks (CNNs) or the temporal sequential property with Recurrent Neural Networks (RNNs). In this work, we propose a new representation of sketches as multiple sparsely connected graphs. We design a novel Graph Neural Network (GNN), the Multi-Graph Transformer (MGT), for learning representations of sketches from multiple graphs which simultaneously capture global and local geometric stroke structures, as well as temporal information. We report extensive numerical experiments on a sketch recognition task to demonstrate the performance of the proposed approach. Particularly, MGT applied on 414k sketches from Google QuickDraw: (i) achieves small recognition gap to the CNN-based performance upper bound (72.80% vs. 74.22%), and (ii) outperforms all RNN-based models by a significant margin. To the best of our knowledge, this is the first work proposing to represent sketches as graphs and apply GNNs for sketch recognition. Code and trained models are available at this https URL.