Showing papers on "Sketch recognition published in 1999"

Vision-Based Gesture Recognition: A Review

Abstract: The use of gesture as a natural interface serves as a motivating force for research in modeling, analyzing and recognition of gestures. In particular, human computer intelligent interaction needs vision-based gesture recognition, which involves many interdisciplinary studies. A survey on recent vision-based gesture recognition approaches is given in this paper. We shall review methods of static hand posture and temporal gesture recognition. Several application systems of gesture recognition are also described in this paper. We conclude with some thoughts about future research directions.

Multimodal integration-a statistical view

Abstract: We present a statistical approach to developing multimodal recognition systems and, in particular, to integrating the posterior probabilities of parallel input signals involved in the multimodal system. We first identify the primary factors that influence multimodal recognition performance by evaluating the multimodal recognition probabilities. We then develop two techniques, an estimate approach and a learning approach, which are designed to optimize accurate recognition during the multimodal integration process. We evaluate these methods using Quickset, a speech/gesture multimodal system, and report evaluation results based on an empirical corpus collected with Quickset. From an architectural perspective, the integration technique presented offers enhanced robustness. It also is premised on more realistic assumptions than previous multimodal systems using semantic fusion. From a methodological standpoint, the evaluation techniques that we describe provide a valuable tool for evaluating multimodal systems.

Hybrid pen-input character recognition system based on integration of online-offline recognition

Abstract: Describes a handwritten character recognition system that integrates offline recognition requiring a bitmap image and online recognition involving an input pattern as a sequence of x-y coordinates. Offline recognition performs well for painted or overwritten patterns (for which online recognition would not be suited), whereas online recognition is suitable for very deformed patterns (for which offline recognition is not suited). Because each method has different recognition capabilities, the methods complement each other when integrated together. We have implemented a hybrid handwritten character recognition system in which the recognition results of the offline and online recognizer are integrated to create an improved product. After testing several integration methods for a handwritten character database, we found that the best method increased the recognition rate from 73.8% (offline) and 84.8% (online) to 87.6% (integrated).

Computer recognition of human face—A survey

Abstract: The article presents the latest trends in computer-based human face recognition. First, methods of facial pattern representation intended to identify persons using frontal face images are introduced as well as recent studies in extending those methods by giving flexibility in terms of face orientation and view. The FERET face recognition project, which is one of the driving forces to promote robustness in face recognition technology, is considered. In addition, computer face recognition is treated as an element of media processing for content search and editing of visual databases, and studies in computer face recognition that model human cognition in the face recognition process are surveyed. Finally, the state of the art in extracting facial patterns from visual scenes is analyzed. © 1999 Scripta Technica, Syst Comp Jpn, 30(10): 76–89, 1999

Real-time context-based gesture recognition using HMM and automaton

Abstract: HMMs are often used for gesture recognition because of the robustness. However, the computational cost and accuracy of recognition are important for real applications such as gesture recognition, speech recognition or virtual reality. In this paper, we propose methods for performance improvement of gesture recognition using HMMs. For the computational cost, we use KL transform to compress the input information and propose a recursive calculation method for the HMMs' probabilities. For the accuracy of recognition, we use an automaton layered up on HMMs to deal with context information of gestures. We also show experimental results to make the efficiency of our methods clear.

Performance evaluation of a new hybrid modeling technique for handwriting recognition using identical on-line and off-line data

Abstract: The paper deals with the performance evaluation of a novel hybrid approach to large vocabulary cursive handwriting recognition and contains various innovations. 1) It presents the investigation of a new hybrid approach to handwriting recognition, consisting of hidden Markov models (HMMs) and neural networks trained with a special information theory based training criterion. This approach has only been recently introduced successfully to online handwriting recognition and is now investigated for the first time for offline recognition. 2) The hybrid approach is extensively compared to traditional HMM modeling techniques and the superior performance of the new hybrid approach is demonstrated. 3) The data for the comparison has been obtained from a database containing online handwritten data which has been converted to offline data. Therefore, a multiple evaluation has been carried out, incorporating the comparison of different modeling techniques and the additional comparison of each technique for online and offline recognition, using a unique database. The results confirm that online recognition leads to better recognition results due to the dynamic information of the data, but also show that it is possible to obtain recognition rates for offline recognition that are close to the results obtained for online recognition. Furthermore, it can be shown that for both online and offline recognition, the new hybrid approach clearly outperforms the competing traditional HMM techniques. It is also shown that the new hybrid approach yields superior results for the offline recognition of machine printed multifont characters.

Network-based approach to online cursive script recognition

Abstract: The idea of combining the network of HMMs and the dynamic programming-based search is highly relevant to online handwriting recognition. The word model of HMM network can be systematically constructed by concatenating letter and ligature HMM's while sharing common ones. Character recognition in such a network can be defined as the task of best aligning a given input sequence to the best path in the network. One distinguishing feature of the approach is that letter segmentation is obtained simultaneously with recognition but no extra computation is required.

Gesture recognition using character recognition techniques on two-dimensional eigenspace

Abstract: This paper describes a novel method for gesture recognition using character recognition techniques on two-dimensional eigenspace. An image-based approach can capture human body poses in 3D motion from multiple image sequences. The sequence of poses can be reduced into a trajectory on the two-dimensional eigenspace with preserving the main features in gesture, so that the gesture recognition equals the character recognition. Experiments for the gesture recognition using some character recognition techniques show our method is useful.

Rudiments for a 3D freehand sketch based human-computer interface for immersive virtual enviroments

Abstract: This paper investigates the applicability of context-free grammars to recognize and interpret representative 3D freehand sketches in terms of creating objects, performing transformations, and controlling the design space with the information contained by the sketches. Dynamic gesture recognition is the foundation of a two-layered concept. The subsequent layer performs multiple gesture recognition by parsing a sequence of single gestures depending on a predefined grammar, and simultaneously extracts the required information on the fly.

Statistical Gesture Recognition Through Modelling of Parameter Trajectories

Abstract: The recognition of human gestures is a challenging problem that can contribute to a natural man-machine interface. In this paper, we present a new technique for gesture recognition. Gestures are modelled as temporal trajectories of parameters. Local sub-sequences of these trajectories are extracted and used to define an orthogonal space using principal component analysis. In this space the probabilistic density function of the training trajectories is represented by a multidimensional histogram, which builds the basis for the recognition. Experiments on three different recognition problems show the general utility of the approach.

Emotion recognition and its application to computer agents with spontaneous interactive capabilities

Abstract: Nonverbal information, such as the emotions, plays an essential role in human communication. Unfortunately, only the verbal aspect of communication has been focused on in communications between humans and computer agents. In the future, however, it is expected that computer agents will have nonverbal as well as verbal communication capabilities. In this paper, we first study the recognition of the emotions involved in human speech. Then we apply this emotion recognition algorithm to a computer agent that plays a character role in the interactive movie system that we are developing.

Research advances on the theory of face recognition

Abstract: This paper first gives the concept and the research situation on the theory of face recognition, and then discusses its key techniques, difficulties and application potentials. Finally, we present our opinions about the problems that should be considered in the research of face recognition.

Hypotethical Reasoning: an application to Optical Music Recognition.

Abstract: In this paper we propose a hybrid system that bridges the gap between traditional image processing methods, used for low-level object recognition, and abductive constraint logic programming used for high-level musical interpretation. Optical Music Recognition (OMR) is the automatic recognition of a scanned page of printed music. All such systems are evaluated by their rate of successful recognition; therefore a reliable OMR program should be able to detect and eventually correct its own recognition errors. Since we are interested in dealing with polyphonic music, some additional complexity is introduced as several concurrent voices and simultaneous musical events may occur. In RIEM, the OMR system we are developing, when events are inaccurately recognized they will generate inconsistencies in the process of voice separation. Furthermore if some events are missing a consistent voice separation may not even be possible. In this work we propose an improved architecture for RIEM to allow the system to hypothesize on possible missing events, to overcome the major failure in the voice assignment due to minor recognition failures. We formalize the process of voice assignment and present a practical implementation using Abductive Constraint Logic Programming. Once we abduce these missing events and know where to look for them in the original score image, we may provide the proper feedback to the recognition algorithms, relaxing the recognition thresholds gradually, until some minimum quality recognition criteria is reached.

Neural networks in off-line text recognition: a review

Abstract: This paper provides a brief review of the state-of-the-art of neural networks in off-line text recognition. We discuss the role that neural networks have played in text recognition. We also assess the state of the art of neural networks in character and word recognition. Despite the success of neural networks in character and word recognition, there are still many challenging problems.

A novel, fast-learning, non-iterative neural network used in pattern recognition

Abstract: In the author's previous works (1990-1999), a one-layered, hard-limited perceptron can be used to classify analog pattern vectors if the latter satisfy the PLI condition. For most pattern recognition applications, this condition should be satisfied. When this condition is satisfied, then an automatic feature extraction scheme can be derived using some N-dimension Euclidean geometry theories. The scheme will automatically extract the most distinguished parts of the pattern vectors used in the training. It selects the feature vectors automatically according to the descending order of the volumes of the parallelepiped spanned by these sub-vectors. Theoretical derivation and numerical examples revealing the physical nature of this process and its effect in optimizing the robustness of this novel pattern recognition system are reported in detail. An experiment shows that the system gives the learning of 4 handwritten characters near to real time. The recognition of untrained handwritten characters is above 90% correct and the recognition is in real time.

Holographic technology applied to face location and identification

Abstract: Holographic technology has been successfully applied on a number of applications in the fields of pattern recognition and prediction. A short review of the face recognition problem introduces one to the fundamental aspects of holographic technology, which are briefly discussed so that their similarities and differences from typical neural nets are shown. Some of the applications of this tool are mentioned in this paper. The image base used is of 31 images of 10 different faces with different facial expressions (happiness, anger and sadness). Data describing these human faces is explained including the sets of data for supervised training and generalization of the holographic cell. The results of applying this technology to face location, for this data set, show that performance is well above 99% accuracy which supports holographic cells as a sound tool for pattern recognition.

A model of human knowledge and recognition system based on similarity transformation

Abstract: We propose a model of human knowledge acquisition and recognition process based on a theoretical foundation: similarity transformation. The model is an artificial neural network for pattern recognition (PRANN). Different from conventional ANNs, PRANN has the ability to retrieve individual stored objects, and the recognition process can stop at any sensitivity level at which an abstract image of any abject can be obtained. Based on abstract images, full details of stored images can be recovered approximately.