Sketch recognition

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

Representation of Human Postures for Vision-Based Gesture Recognition in Real-Time

Abstract: Using computer vision to sense and perceive the user and his/her actions in a Human-Computer Interaction context is often referred to as Vision-Based Interfaces In this paper, we present a Vision-Based Interface guided by the user gestures Previously to recognition, the user's movements are obtained through a real-time vision-based motion capture system This motion capture system is capable to estimate the user 3D body joints position in real-time By means of an appropriate representation of limbs orientations based on temporal histograms, we present a scheme of gesture recognition that also works in real-time This scheme of recognition has been tested through control of a classical computer videogame showing an excellent performance in on-line classification and it allows the possibility to achieve a learning phase in real-time due to its computational simplicity

Hand Gesture Recognition System

Abstract: Gestures are a major form of human communication. Hence gestures can be found to be an appealing way to interact with computers, since they are already a natural part of how people communicate. A primary goal of gesture recognition is to create a system which can identify specific human gestures and use them to convey information for controlling device and by implementing real time gesture recognition a user can control a computer by doing a specific gesture in front of a video camera which is linked to the computer. A primary goal of this gesture recognition research is to create a system which can identify specific human gestures for the control the traffic signals and mouse. This project also covers various issues like what are gesture, their classification, their role in implementing a gesture recognition system for traffic and mouse control, system architecture concepts for implementing a gesture recognition system, major issues involved in implementing gesture recognition system, and future scope of gesture recognition system. For implementation of this system real-time hand tracking and extraction algorithm, and feature extraction are used.

Control Virtual Human with Speech Recognition and Gesture Recognition Technology

Abstract: In accordance with the few kinds of virtual human control device, the application of speech recognition and gesture recognition in virtual human control was researched. The development status of limited collection isolated word recognition technology was introduced, the basic principle of data glove was analyzed, its correcting and data process technology were discussed. The principle of gesture recognition based on vision and its research status was introduced in detail. The realization of control virtual human with speech recognition and gesture recognition in engineering were introduced, and got anticipated result.

Towards a Framework for Truly Natural Low-level Sketch Recognition

Abstract: Although stroke-based systems may be considered the stateof-the-art in low-level sketch recognition, they still contain constraints and intricacies that may be invisible to most novice users. In this paper, we identify some common assumptions and problems of stroke-based systems and propose a plan for the development of a new low-level framework to deal with these issues. The broader impact of this framework will be the development of sketch recognition systems which place fewer (and hopefully no) drawing constraints on users and will allow for more natural sketching, starting at the lowest and most fundamental level. Author Keywords sketch recognition, primitive recognition, low-level framework

DoodleIt: A Novel Tool and Approach for Teaching How CNNs Perform Image Recognition

Abstract: To introduce middle school students to key concepts in image recognition, we created an interactive web application that performs sketch recognition and an afterschool curriculum for its use. Our app, called DoodleIt, was inspired by Google’s Quick, Draw!, and makes use of its accompanying open-source sketch library. With DoodleIt, students make simple line drawings on a canvas area and a previously-trained convolutional neural network (CNN) identifies the object drawn. The application dynamically visualizes the different layers that are involved in the process of CNNs, including a display of kernels, the resulting feature maps, and the percentage of match at output neurons. We used DoodleIt in an 18-hour curriculum to introduce middle school students to artificial intelligence, machine learning, and data science. Four hours of content were related to image recognition and the ethics of using AI. Here, we describe the design of the DoodleIt application, the approach we used to introduce the associated ideas to the students, and how we assessed student learning. Qualitative data collected from students are presented and discussed. Our findings indicate that students were able to understand the functionality of the kernels and feature maps involved in the CNN to perform rudimentary image recognition.