• Journal of Digital Contents Society
• /
• v.16 no.4
• /
• pp.605-613
• /
• 2015

This paper addresses the problem to make sparse the projection matrix in pattern recognition method. Recently, the size of computer program is often restricted in embedded systems. It is very often that developed programs include some constant data. For example, many pattern recognition programs use the projection matrix for dimension reduction. To improve the recognition performance, very high dimensional feature vectors are often extracted. In this case, the projection matrix can be very big. Recently, RSR(roated sparse regression) method[1] was proposed. This method has been proved one of the best algorithm that obtains the sparse matrix. We propose three methods to improve the RSR; outlier removal, sampling and elastic net RSR(E-RSR) in which the penalty term in RSR optimization function is replaced by that of the elastic net regression. The experimental results show that the proposed methods are very effective and improve the sparsity rate dramatically without sacrificing the recognition rate compared to the original RSR method.

• Journal of Broadcast Engineering
• /
• v.21 no.1
• /
• pp.87-96
• /
• 2016

Recently, there is a need for automatic recognition of a variety of symbols on roads because of activation of information services using digital maps on the Web or mobile devices. This paper proposes a method which automatically recognizes 11 kinds of symbolic road markings on the road surface with HOG-SP(Histogram of oriented Gradients-Split Projection) descriptor and shows improvement of lane position detection with recognized symbolic road markings. With the proposed method, recognition rate of 81.99% has been proven on NAVER road view images and the experiments proves the superiority of proposed method by comparisons with other existing methods. Moreover, this paper shows 7.64% higher lane position detection rate by recognizing road surface marking beforehand than only detecting lanes' positions.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.5-14
• /
• 1994

This paper is about an experiment of speaker-independent automatic Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The object words are 50 citynames of D.D.D local numbers. 43 of those are 2 syllables and the rest 7 are 3 syllables. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. That led independent result on the speech duration, and the PARCOR coefficients calculated from the frames using linear predictive analysis were employed as feature components. This paper tried to find out the optimum conditions through 4 differerent experiments which are comparison between total and pre-classified training, dependency of recognition rate on the number of frames and PAROCR order, recognition change due to the number of neurons in the hidden layer, and the comparison of the output pattern composition method of output neurons. As a result, the recognition rate of $89.6\%$ is obtaimed through the research.

• Journal of Ocean Engineering and Technology
• /
• v.28 no.6
• /
• pp.552-559
• /
• 2014

In general, the number of underwater transient signals is very limited for research on automatic recognition. Data-dependent feature extraction is one of the most effective methods in this case. Therefore, we suggest WPCC (Wavelet packet ceptsral coefficient) as a feature extraction method. A wavelet packet best tree for each data set is formed using an entropy-based cost function. Then, every terminal node of the best trees is counted to build a common wavelet best tree. It corresponds to flexible and non-uniform filter bank reflecting characteristics for the data set. A GMM (Gaussian mixture model) is used to classify five classes of underwater transient data sets. The error rate of the WPCC is compared using MFCC (Mel-frequency ceptsral coefficients). The error rates of WPCC-db20, db40, and MFCC are 0.4%, 0%, and 0.4%, respectively, when the training data consist of six out of the nine pieces of data in each class. However, WPCC-db20 and db40 show rates of 2.98% and 1.20%, respectively, while MFCC shows a rate of 7.14% when the training data consists of only three pieces. This shows that WPCC is less sensitive to the number of training data pieces than MFCC. Thus, it could be a more appropriate method for underwater transient recognition. These results may be helpful to develop an automatic recognition system for an underwater transient signal.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.439-448
• /
• 2006

Previous recognition/clustering algorithms such as Kohonen SOM(Self-Organizing Map), MLP(Multi-Layer Percecptron) and SVM(Support Vector Machine) might not adapt to unexpected input pattern. And it's recognition rate depends highly on the complexity of own training patterns. We could make up for and improve the weak points with lowering complexity of original problem without losing original characteristics. There are so many ways to lower complexity of the problem, and we chose a kernel concepts as an approach to do it. In this paper, using a kernel concepts, original data are mapped to hyper-dimension space which is near infinite dimension. Therefore, transferred data into the hyper-dimension are distributed spasely rather than originally distributed so as to guarantee the rate to be risen. Estimating ratio of recognition is based on a new similarity-probing and learning method that are proposed in this paper. Using CEDAR DB which data is written in cursive letters, 0 to 9, we compare a recognition/clustering performance of kSOM that is proposed in this paper with previous SOM.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.7
• /
• pp.209-214
• /
• 2012

RFID(Radio Frequency IDentification) is an emerging technology which brings enormous productivity benefits in applications where objects have to be identified automatically. But despite of RFID's advantage, it is not easy to realize the RFID technology in business world. The failure to read RFID tags is the most urgent problem that should be solved for RFID application. Specially, in metal and liquid material, recognition rate of RFID tag is lower than others. Though some special tags for metal and liquid have been invented, it has not prevalent in business world on account of high price. In this paper, styrofoam pad is suggested to improve recognition rate of RFID tag for metal pipe which is used in fish cultivating industry. We makes experiment using Taguchi method and analyze the effects on styrofoam thickness, attachment location of tag, and angle of antenna.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.1
• /
• pp.157-166
• /
• 2004

Consequently substantial research has been done on the development of the bio-metric recognition method as well as technical research in the field of authentication. As a method of bio-metric recognition, personal and unique information such as fingerprints, voice, face, Iris, hand-geometry and vein-pattern are used. The face image system in bio-metric recognition and information authentication reduces the denial response from the users because it is a non-contact system the face image system operates through a PC camera attached to a computer base this makes the system economically viable as well as user friendly. Conversely, the face image system is very sensitive to illumination, hair style and appearance and consequently creates recognition errors easily, therefore we must build a stable authentication system which is not too sensitive to changes in appearance and light. In this study, I proposed user authentication protocol to serve a confidentiality and integrity and to obtain a least Equal Error Rate to minimize the wrong authentication rate when it authenticates the user.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.471-476
• /
• 2016

This paper presents our study on speech recognition performance prediction. Our initial study shows that a combination of speech quality measures effectively improves correlation with Word Error Rate (WER) compared to each speech measure alone. In this paper we demonstrate a new combination of various types of speech quality measures shows more significantly improves correlation with WER compared to the speech measure combination of our initial study. In our study, SNR, PESQ, acoustic model score, and MFCC distance are used as the speech quality measures. This paper also presents our speech database verification system for speech recognition employing the speech measures. We develop a WER prediction system using Gaussian mixture model and the speech quality measures as a feature vector. The experimental results show the proposed system is highly effective at predicting WER in a low SNR condition of speech babble and car noise environments.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1129-1135
• /
• 1999

isolated word recognition using the Dynamic Time warping algorithm has shown good recognition rate on speaker dependent environment. But, practically, since the searching time of the dynamic Time Warping algorithm is rapidly increased as searching data is increased. it is hard to implement. In the context-dependent-short-query system such as educational children's workbook on the Web, the number of responses to the specific questions is limited. Therefore, the searching space for the answers can be reduced depending on the questions. In this paper, low cost implementation method using DTW for the Web has been proposed. To cover the weakness of DTW, the searching space is reduced by the context. the searching space, depends on the specific questions, is chosen from interest searchable candidates. In the real implementation, the proposed method show better performance of both time and recognition rate.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.2
• /
• pp.148-161
• /
• 2015

The examples that used camera in the vehicle is increasing with the growth of the automotive market, and the importance of the image processing technique is expanding. In particular, the Lane Departure Warning System (LDWS) and related technologies are under development in various fields. In this paper, in order to improve the lane recognition rate more than the conventional method, we extract a Normalized Luminance Descriptor value and a Normalized Contrast Descriptor value, and adjust image gamma values to modulate Normalized Image Quality by using the correlation between the extracted two values. Then, we apply the Hough transform using the optimized accumulator cells to the four-channel ROI. The proposed algorithm was verified in 27 frame/sec and $640{\times}480$ resolution. As a result, Lane recognition rate was higher than the average 97% in day, night, and late-night road environments. The proposed method also shows successful lane recognition in sections with curves or many lane boundary.