• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.877-889
• /
• 2006

This paper introduces a simple but effective method for recognizing vehicle models corresponding to each maker by information and images for moving vehicles. The proposed approach is implemented by combination of the breadth detection mechanism using the vehicle's pressure, exact height detection by a laser scanning, and license plate recognition for classifying specific vehicles. The implemented system is therefore capable of robust classification with real-time vehicle's moving images and established sensors. Simulation results using the proposed method on synthetic data as well as real world images demonstrate that proposed method can maintain an excellent recognition rate for moving vehicle models because of image acquisition by 2-D CCD and various image processing algorithms.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.1
• /
• pp.20-28
• /
• 1992

Co-articulation is one of major factors that make connected word recognition difficult. This Study Considers the fact that the head Part Of the following word is changed by the Preceding word in a connection point, by applying the co-articulation model, and adj usting the following word .We choose a critical damping second order linear system for the co-articulation model, combining a one-stage DP matching recognition algorithm with this model, and Investigating the effects. The recognition experiment is carried out for 35 Korean 4 connected digits spoken by 5 male speakers, and recognition rate Is upgraded by 4.7 percent.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.4
• /
• pp.86-93
• /
• 1999

This paper proposes the multi-modular neural network and compensative input algorithm. The former is to reduce convergence speed which is one of the neural network's inveterate problems, and the latter is to improve the recognition performance of the neural network. This paper consists of two major parts and a simulation. First, it shows the structure of mu1ti-modular neural network, which is applied to the recognition of Korean, English characters and numbers. Second, it describes the compensative input algorithm and shows the steps that determine the compensative input. The proposed algorithm was tested and compared with the existing neural networks in the recognition of Korean and English characters and numbers. The convergence speed is three times or more faster than the existing neural network. In the case that compensative input was applied to neural network, the recognition rate was improved more than 10%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.120-126
• /
• 2009

In order to reduce the noise quantity in a conversation under the noisy environment it is necessary for the signal processing system to process adaptively according to the noise quantity in order to enhance the performance. Therefore this paper presents a recognition method for noise quantity by linear predictive coefficient using a three layered neural network, which is trained using three kinds of speech that is degraded by various background noises. The performance of the proposed method for the noise quantity was evaluated based on the recognition rates for various noises. In the experiment, the average values of the recognition results were 98.4% or more for such noise using Aurora2 database.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.569-579
• /
• 2011

This paper presents a novel approach for human activity recognition (HAR) using the joint angles from a 3D model of a human body. Unlike conventional approaches in which the joint angles are computed from inverse kinematic analysis of the optical marker positions captured with multiple cameras, our approach utilizes the body joint angles estimated directly from time-series activity images acquired with a single stereo camera by co-registering a 3D body model to the stereo information. The estimated joint-angle features are then mapped into codewords to generate discrete symbols for a hidden Markov model (HMM) of each activity. With these symbols, each activity is trained through the HMM, and later, all the trained HMMs are used for activity recognition. The performance of our joint-angle-based HAR has been compared to that of a conventional binary and depth silhouette-based HAR, producing significantly better results in the recognition rate, especially for the activities that are not discernible with the conventional approaches.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.251-258
• /
• 2011

Applying face alignment after face detection exerts a heavy influence on face recognition. Many researchers have recently investigated face alignment using databases collected from images taken at close distances and with low magnification. However, in the cases of home-service robots, captured images generally are of low resolution and low quality. Therefore, previous face alignment research, such as eye detection, is not appropriate for robot environments. The main purpose of this paper is to provide a new and effective approach in the alignment of small and blurred faces. We propose a face alignment method using the confidence value of Real-AdaBoost with a modified census transform feature. We also evaluate the face recognition system to compare the proposed face alignment module with those of other systems. Experimental results show that the proposed method has a high recognition rate, higher than face alignment methods using a manually-marked eye position.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.496-504
• /
• 2009

This paper presents a recognition performance of VOR (Vestibular-Ocular Reflex) based vision tracking system for mobile robot. The VOR is a reflex eye movement which, during head movements, produces an eye movement in the direction opposite to the head movement, thus maintaining the image of interested objects placed on the center of retina. We applied this physiological concept to the vision tracking system for high recognition performance in mobile environments. The proposed method was implemented in a vision tracking system consisting of a motion sensor module and an actuation module with vision sensor. We tested the developed system on an x/y stage and a rate table for linear motion and angular motion, respectively. The experimental results show that the recognition rates of the VOR-based method are three times more than non-VOR conventional vision system, which is mainly due to the fact that VOR-based vision tracking system has the line of sight of vision system to be fixed to the object, eventually reducing the blurring effect of images under the dynamic environment. It suggests that the VOR concept proposed in this paper can be applied efficiently to the vision tracking system for mobile robot.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1
• /
• pp.96-99
• /
• 1997

This paper proposes a very fast preprocessor for isolated word recognition. The proposed preprocessor has a small computational cost for extracting candidate words. In the preprocessor, we used a feature sorting algorithm instead of vector quantization to reduce the computational cost. In order to show the effectiveness of our preprocessor, we compared it to a speech recognition system based on semi-continuous hidden Markov Model and a VQ-based preprocessor by computing their recognition performances of a speaker independent isolated word recognition. For the experiments, we used the speech database consisting of 244 words which were uttered by 40 male speakers. The set of speech data uttered by 20 male speakers was used for training, and the other set for testing. As the results, the accuracy of the proposed preprocessor was 99.9% with 90% reduction rate for the speech database.