• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.9
• /
• pp.1299-1305
• /
• 2013

In this paper, we investigate a method of reducing the computational cost in speech recognition by dimensionality reduction of MFCC feature vectors. Eigendecomposition of the feature vectors renders linear transformation of the vectors in such a way that puts the vector components in order of variances. The first component has the largest variance and hence serves as the most important one in relevant pattern classification. Therefore, we might consider a method of reducing the computational cost and achieving no degradation of the recognition performance at the same time by dimensionality reduction through exclusion of the least-variance components. Experimental results show that the MFCC components might be reduced by about half without significant adverse effect on the recognition error rate.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.1
• /
• pp.31-36
• /
• 2003

This paper describes the quantitative analysis and the pattern recognition of partial discharge signals generated by particles in GIS. Four states of particles were simulated in this paper. Partial discharge signals from each state was measured and the Ф-Q-N distribution of partial discharge signals was displayed and then the Ф-Q, the Ф-Qm, the Ф-N and the Q-N distribution were displayed. Each distribution can be quantitatively represented by statistical parameters and the parameters were used for input data of pattern recognition. As the results, it was found that the forms of each distribution were different according to the particle states. Recognition rate using neural network was about 92〔%〕 and the more input data number, the more accurate results.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• Journal of Sensor Science and Technology
• /
• v.13 no.1
• /
• pp.20-26
• /
• 2004

For the disabled persons who can't use their limbs, motorized wheelchair that is activated by voice recognition module employing speaker independent method, was implemented. The wireless voice transfer device was designed and employed for the user convenience. And the wheelchair was designed to operate using voice and keypad by selection of the user because they can manipulate it using keypad if necessary. The speaker independent method was used as the voice recognition module in order that anyone can manipulate the wheelchair in case of assistance. Using the implemented wheelchair, performance and motion of the system was examined and it has over than 97% of voice recognition rate and proper movements.

• Journal of Intelligence and Information Systems
• /
• v.10 no.3
• /
• pp.105-114
• /
• 2004

In the past year, the increasing concern about the biometric recognition makes the great activities on the security fields, such as the entrance control or user authentication. In particular, although the features of face recognition, such as user friendly and non-contact made it to be used widely, unhappily it has some disadvantages of low accuracy or low Re-attempts Rates. For this reason, I suggest the new approach to re-classify the classified data of recognition result data to solve the problems. For this study, I will use the typical appearance-based, PCA(Principal Component Analysis) algorithm and verify the performance improvement by adopting the re-classification approach using 200 peoples (10 pictures per one person).

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.191-204
• /
• 2018

To combat the adverse impact imposed by illumination variation in the face recognition process, an effective and feasible algorithm is proposed in this paper. Firstly, an enhanced local texture feature is presented by applying the central symmetric encode principle on the fused component images acquired from the wavelet decomposition. Then the proposed local texture features are combined with Deep Belief Network (DBN) to gain robust deep features of face images under severe illumination conditions. Abundant experiments with different test schemes are conducted on both CMU-PIE and Extended Yale-B databases which contain face images under various illumination condition. Compared with the DBN, LBP combined with DBN and CSLBP combined with DBN, our proposed method achieves the most satisfying recognition rate regardless of the database used, the test scheme adopted or the illumination condition encountered, especially for the face recognition under severe illumination variation.

• Journal of Korea Multimedia Society
• /
• v.10 no.9
• /
• pp.1143-1152
• /
• 2007

The objective of this paper is to develop the real time motion recognition method for the rehabilitation program of the people with physical disabilities. Using the infrared ray LED, this method gets the Teal time information of the user's motion and tells the difference between the information we get and the pre-defined information. In order to get the fast recognition and comparison, this method positions the specific coordinates of infrared ray LED in the pre-classified sector which keeps certain distance and angle from the point of origin. The result In our experiment shows the speed over 20 frames per second in every motion, and we are satisfied the rate for the recognition of the motions which is near 98%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.1
• /
• pp.23-34
• /
• 1991

This paper is studied for the recognition of occluded objects by fuzzy inference. The images are transformed a group of linear line segments, which is formed local features extracted from curvature points, using polygonal approximation. The features extracted from images are representes to the fuzzified data which is mapped into fuzzy concepts to represent the fuzziness, and the recognition of a model from scenes is performed by fuzzy inference using the production rulse which is generated from the model image. It is considered that the recognition results according to the change of degree of fuzziness in the experiments, and the experimental results for 30 scenes contained 120 models is obtained 92.5% of recognition rate.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.6
• /
• pp.151-156
• /
• 2018

Because of its large differences in writing style, context-independency and high recognition accuracy requirement, free handwritten digital identification is still a very difficult problem. Analyzing the characteristic of handwritten digits, this paper proposes a new handwritten digital identification method based on combining structural features. Given a handwritten digit, a variety of structural features of the digit including end points, bifurcation points, horizontal lines and so on are identified automatically and robustly by a proposed extended structural features identification algorithm and a decision tree based on those structural features are constructed to support automatic recognition of the handwritten digit. Experimental result demonstrates that the proposed method is superior to other general methods in recognition rate and robustness.