Sketch recognition

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

A limited speech recognition system

Abstract: A computer system which identifies words in continuous speech of an unknown speaker is beyond the current state of the art in speech recognition. LISPER, is a successful limited speech recognition system based on a set of assumptions which greatly simplify the recognition problem; within these restrictions it allows experimentation on the usefulness of a voice insertion system on the computer.

Improving appearance-based object recognition in cluttered backgrounds

Abstract: Appearance-based object recognition systems are currently the most successful approach for dealing with 3D recognition of arbitrary objects in the presence of clutter and occlusion. However, no current system seems directly scalable to human performance levels in this domain. We describe a series of experiments on a previously described object recognition system that try to see, if any, which design axes of such systems hold the greatest potential for improving performance. We look at the potential effect of different design modifications, and conclude that the greatest leverage lies at the level of intermediate feature construction.

A recognition and verification strategy for handwritten word recognition

Abstract: In this paper a word recognition and verification scheme based on HMMs is presented. However, the main contribution of the current work lies in the validation of such a strategy. In order to perform this task, we carried out some experiments on word recognition using a legal amount database and then we compared the results reached with other study which makes use of the same database. The experiments demonstrate the efficiency of the strategy we developed for word recognition and verification.

Head Gesture Recognition using Optical Flow based Classification with Reinforcement of GMM based Background Subtraction

Abstract: This paper describes a technique of real time head gesture recognition system. The method includes Gaussian mixture model (GMM) accompanied by optical flow algorithm which provided us the required information regarding head movement. The proposed model can be implemented in various control system. We are also presenting the result and implementation of both mentioned method. Keywords Head gesture, GMM, background subtraction, optical flow 1. and spatial position. This group is best represented by the soINTRODUCTION A primary goal of gesture recognition is to implement mathematical algorithms so that a computer can identify gestures in a efficient, powerful, and flexible way. Human gestures provide one of the most important means for non-verbal interaction among peoples. Automatic gesture recognition, particularly computer vision based techniques do not require the user to wear extra sensors, clothing or equipment for the recognition system. There are a lot of devices which are applied to sense body position and orientation, facial expression and other aspects of human behavior or state which can be used to determine the communication between the human and the environment. Combinations of human body and sensing devices can produce a wide range of interfacing techniques. To support gesture recognition, human body movement must be tracked and interpreted in order to recognize the meaningful gestures.Many methods have been developed for both hand gesture and body gesture recognition [22][9][4]. These recognition tasks are challenging because human body is highlyarticulated. In our work of gesture recognition we used Gaussian Mixture Model (GMM)[27] for background subtraction, and background subtracted image is used for further processing. For the determination of head movement we implemented optical flow method [12]. There are a lot of optical flow methods, among which we tried the Horn-Schunck optical flow algorithm [20]. The main goal of the project is to design a real time head movement detection and gesture recognition system. To support gesture recognition, human position and movement must be tracked and interpreted in order to recognize the meaningful gestures [23]. In this paper, we present a gesture recognition system that takes input from a simple camera and necessary processing steps is done to recognize the gestures from a live video.

Boosting local descriptors for matching composite and digital face images

Abstract: Sketch recognition is one of the most challenging applications of face recognition. Due to the incorrectness of features in the witness description, standard face recognition algorithms are generally not applicable to matching sketches with digital face images. This research designs a patch based face recognition algorithm that generates patches around fiducial features and extracts local information from these patches using Daisy descriptor. The information extracted from these patches are then efficiently matched using GentleBoostKO algorithm. The experiments performed on the PRIP composite face image database show that the proposed algorithm yields promising results and outperforms existing state-of-the-art algorithms and a commercial system.