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 Sep 2016TL;DR: The improved method could analyze hand-drawn animals such as cat, dog and sheep, and could synthesize cries of each animal interactively by extracting and learning features of complex objects in a machine learning method.
Abstract: "RAKUGACKY" is an interactive media system that could generate sounds from a hand-drawn sketch. It is necessary to analyze a sketch to generate sounds suitable for the sketch. The former system used colors and simple shape feature values of objects in a sketch such a circularity and an area, to recognize each object. Thus the system could recognize only simple objects in a sketch. In this paper, we improve our system to use more complex features of objects and recognize complex objects in a sketch by extracting and learning features of complex objects in a machine learning method. For example, the improved method could analyze hand-drawn animals such as cat, dog and sheep, and could synthesize cries of each animal interactively.
••
21 Aug 2022TL;DR: Zhang et al. as mentioned in this paper proposed to use sketches as the expression of the target image, which can not only represent the pose and shape simultaneously but is also flexible to manipulate at the semantic level.
Abstract: Person image generation is a challenging problem due to the complexity of human body structure and the richness of clothing texture. Recent works have made great progress on pose transfer by using keypoints, but cannot characterize the personalized shape attributes. Hence, they have limited person image editing ability, especially in respect of shape editing. In this paper, we propose to use sketches as the expression of the target image, which can not only represent the pose and shape simultaneously but is also flexible to manipulate at the semantic level. We propose DesignerGAN, a novel two-stage model for pose transfer and shape-related attributes editing. The first stage predicts the target semantic parsing using the target sketch and obtains parsing feature maps. In the second stage, with the parsing feature maps and the scaled target sketch, we devise a domain-matching spatially-adaptive normalization method to guide target image generation in multi-level. Qualitative and quantitative comparison results demonstrate our method’s superiority over state-of-the-arts on pose transfer. Besides, we achieve flexible person image editing through simple hand-drawings on sketches.
••
TL;DR: A gesture recognition method with enhanced generality and processing speed is proposed and verified through the learning and subsequent recognition of 29 postures and 8 gestures.
Abstract: Recently, the recognition of posture and gesture has been widely used in fields such as medical treatment and human---computer interaction. Previous research into the recognition of posture and gesture has mainly used human skeletons and an RGB-D camera. The resulting recognition methods utilize models of the human skeleton, with different numbers of joints. The processing of the resulting large amounts of feature data needed to recognize a gesture leads to the recognition being delayed. To overcome this issue, we designed and developed a system for learning and recognizing postures and gestures. This paper proposes a gesture recognition method with enhanced generality and processing speed. The proposed method consists of feature collection part, feature optimization part, and a posture and gesture recognition part. We have verified the solution proposed in this paper through the learning and subsequent recognition of 29 postures and 8 gestures.
••
16 Jan 2013TL;DR: This result shows that competitive co evolution and camouflage are expected to aid in the problem of over fitting and reliability without expert tuning, and also in the generation of a larger and more diverse data set.
Abstract: A complete document analysis system involves multiple techniques and indifferent processing steps. Even a character recognition or word recognition module (subsystem) needs techniques combining a few algorithms. To exemplify how the techniques are practically used and how they are performing, some concrete examples of using multiple techniques to build practical recognition systems are presented, and experimental results on real image data are showed. In the paper, evolutionary generation of pattern recognizers will be discussed and a co evolution algorithm in the image recognition system will be researched. This result shows that competitive co evolution and camouflage are expected to aid in the problem of over fitting and reliability without expert tuning, and also in the generation of a larger and more diverse data set.