• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.7-15
• /
• 2014

This paper proposed a recognition algorithm of human facial expressions using the PCA and the template matching. Firstly, face image is acquired using the Haar-like feature mask from an input image. The face image is divided into two images. One is the upper image including eye and eyebrow. The other is the lower image including mouth and jaw. The extraction of facial components, such as eye and mouth, begins getting eye image and mouth image. Then an eigenface is produced by the PCA training process with learning images. An eigeneye and an eigenmouth are produced from the eigenface. The eye image is obtained by the template matching the upper image with the eigeneye, and the mouth image is obtained by the template matching the lower image with the eigenmouth. The face recognition uses geometrical properties of the eye and mouth. The simulation results show that the proposed method has superior extraction ratio rather than previous results; the extraction ratio of mouth image is particularly reached to 99%. The face recognition system using the proposed method shows that recognition ratio is greater than 80% about three facial expressions, which are fright, being angered, happiness.

• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.169-174
• /
• 2013

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for voice and non-voice classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a silence feature normalization and voice energy maximize. In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the voice energy. Cepstral feature distribution of voice / non-voice characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2263-2266
• /
• 2003

Three-dimensional face recognition algorithm using curvature information representing characteristics of surface form is suggested. The experiment showed more than 90 percent of recognition for the noses which had definite change value of data, and contained much information about surface curvature. Recognition ratio using a contour taken from the remaining part other than the eyes, noses, mouths which are the main components of faces showed the important role, which could be used as the important index information in the three-dimensional face recognition.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.1-8
• /
• 1994

There are many research activities in various recognition areas using high calibered computing power. Among many areas, the signature recognition and verification have more difficulties than any other recognition area because signature itself contains many problems caused by a variation of psychological status of signer and other environment. In the case of signature, therefore, it is important to extract the better parameters required for the higher verification ratio. In this paper, signature pressure is extracted and used as feature parameters to determine whether the input signature is ture or forgery, and then input signature is verified by fuzzy similarity method. As a result of appling the fuzzy similarity method to the recognition system it is proven that the system has by far better verification ratio about 10% than existing methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.628-631
• /
• 1996

This paper proposes a surface recognition algorithm which determines the types of contact surfaces by fusing the information collected by the multisensor system, consisted of the optical tactile and force/torque sensors. Since the image shape measured by the optical tactile sensor system, which is used for determining the surface type, varies depending on the forces provided at the measuring moment, the force information measured by the f/t sensor takes an important role. In this paper, an image contour is represented by the long and short axes and they are fuzzified individually by the membership function formulated by observing the variation of the lengths of the long and short axes depending on the provided force. The fuzzified values of the long and short axes are fused using the average Minkowski's distance. Compared to the case where only the contour information is used, the proposed algorithm has shown about 14% of enhancement in the recognition ratio. Especially, when imposing the optimal force determined by the experiments, the recognition ratio has been measured over 91%.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.225-239
• /
• 2003

In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the recognition results, and filler models, anti-subword models and N-best decoding results are considered as an alternative hypothesis for likelihood ratio scoring. We also examine different methods to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clustering. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance and N-best decoding method show better performance than other methods, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.817-822
• /
• 2011

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame using a neural network training by back-propagation algorithm, then proposes the spectral subtraction method which removes the noises at each frame according to detection of the speech and noise sections. In this experiment, the performance of the proposed recognition system was evaluated based on the recognition rate using various speeches that are degraded by white noise and car noise. Moreover, experimental results of the noise reduction by the spectral subtraction method demonstrate using the speech and noise sections detecting by the speech recognition algorithm at each frame. Based on measuring signal-to-noise ratio, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise using signal-to-noise ratio.

• The Journal of Information Technology
• /
• v.2 no.2
• /
• pp.139-144
• /
• 1999

This thesis is a study on using of entropy information about the additional words in the after processing step to promote an accuracy in speech recognition system. The exsisting ratio of Woodo detective method changes the efficiency of speech recognition system according to speech data and increases the probability of producing error recognition because of similarity of value of Woodo in the additional words. But we could obtain the accurate speech recognition system which heightens discrimination becoming independent of speech data by using of after processing method refusing a candidate which entropy price is lower among words except words we could recognize than entropy Price of each additional word. As a result of this experiment when the false alarm is 20 percent, we could put out the maximum 3.6 percent efficiency of recognition system through this after processing method by entropy more than the method by ratio of Woods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9C
• /
• pp.748-755
• /
• 2010

In this paper we propose an improved face recognition method using Gabor tensor. Gabor transform is known to be able to represent characteristic feature in face and reduced environmental influence. It may contribute to improve face recognition ratio. We attempted to combine three-dimensional tensor from Gabor transform with MPCA(Multilinear PCA) and LDA. MPCA with tensor which use various features is more effective than traditional one or two dimensional PCA. It is known to be robust to the change of face expression or light. Proposed method is simulated by MATALB9 using ORL and Yale face database. Test result shows that recognition ratio is improved maximum 9~27% compared with exisisting face recognition method.

• International Journal of Highway Engineering
• /
• v.15 no.1
• /
• pp.155-161
• /
• 2013

PURPOSES: This study is to develop a road traffic sign recognition and automatic positioning for road facility management. METHODS: In this study, we installed the GPS, IMU, DMI, camera, laser sensor on the van and surveyed the car position, fore-sight image, point cloud of traffic signs. To insert automatic position of traffic sign, the automatic traffic sign recognition S/W developed and it can log the traffic sign type and approximate position, this study suggests a methodology to transform the laser point-cloud to the map coordinate system with the 3D axis rotation algorithm. RESULTS: Result show that on a clear day, traffic sign recognition ratio is 92.98%, and on cloudy day recognition ratio is 80.58%. To insert exact traffic sign position. This study examined the point difference with the road surveying results. The result RMSE is 0.227m and average is 1.51m which is the GPS positioning error. Including these error we can insert the traffic sign position within 1.51m CONCLUSIONS: As a result of this study, we can automatically survey the traffic sign type, position data of the traffic sign position error and analysis the road safety, speed limit consistency, which can be used in traffic sign DB.