• ETRI Journal
• /
• v.38 no.4
• /
• pp.703-713
• /
• 2016

In this paper, we present a segmentation-based method for offline Farsi handwritten word recognition. Although most segmentation-based systems suffer from segmentation errors within the first stages of recognition, using the inherent features of the Farsi writing script, we have segmented the words into sub-words. Instead of using a single complex classifier with many (N) output classes, we have created N simple recurrent neural network classifiers, each having only true/false outputs with the ability to recognize sub-words. Through the extraction of the number of sub-words in each word, and labeling the position of each sub-word (beginning/middle/end), many of the sub-word classifiers can be pruned, and a few remaining sub-word classifiers can be evaluated during the sub-word recognition stage. The candidate sub-words are then joined together and the closest word from the lexicon is chosen. The proposed method was evaluated using the Iranshahr database, which consists of 17,000 samples of Iranian handwritten city names. The results show the high recognition accuracy of the proposed method.

• Phonetics and Speech Sciences
• /
• v.14 no.3
• /
• pp.11-25
• /
• 2022

From simultaneous recordings of the external photoglottography, intra-oral air pressure (P_io), airflow and acoustic data from four native Seoul Korean speakers (2 male and 2 female), we have found that the two fricatives are not significantly different in glottal opening peak and airflow peak height either word-initially or word-medially and that the duration of aspiration is significantly reduced in word-medial /s/, compared to those in word-initial /s/, not in /s'/. We have also found that the duration of a high P_io plateau is significantly longer in /s/ than in /s'/ both word-initially and word-medially and that airflow resistance (R=P_io/U) at the onset and offset of a P_io plateau and at the time of airflow peak height is significantly higher in /s'/ than in /s/ across the contexts. However, the differences in P_io peak and F0 are not significant. In addition, the transition time to reach airflow peak height from the offset of a P_io plateau is found to be significantly longer in /s/ than /s'/ in both word-initial and word-medial positions. No significant differences in glottal opening peak and airflow peak height confirm that /s/ is specified as [-spread glottis] like /s'/. As for the other significant differences, we propose that /s/ is [-tense], and /s'/ [+tense].

• The Korean Journal of Rehabilitation Nursing
• /
• v.5 no.2
• /
• pp.145-155
• /
• 2002

Purpose: This study tries to analyze the differences of memory performance and the metamemory of the elderly women according to degree of depression. And also it attempts to find the correlations among the sub-concepts of metamemory which have close relationships to the memory performance followed by the depression. Methods: The subjects of this study are 60 the elderly women who are older than sixty years in Busan city, Korea. We use the MIA(Dixon, et al., 1988) to measure metamemory and measure the memory performances such as the immeadiate word recall, the delayed word recall, the word recognition task, and face recognition. Results: 1. The average point of deprssed elderly womens' metamemory was significantly lower than non-depressed womens' point(t=10.86 p<.0017). Looking into subconcept of metamemory, depressed elderly womens' strategy, capacity, change, achievement point were significantly lower than non-depressed women. 2. In terms of immediate word recall and delayed word recall performances, depressed elderly women are significantly lower than non-depressed elderly women. 3. The degree of depressed elderly womens' metamemory(strategy, achievement, change, capacity) has significant correlations with immediate word recall performances. Conclusion: Metamemory has close relationship with the memory performance of elderly women. And also depressed elderly's sub-concepts of metamemory which have influences on their memory performance are different from non-depressed elderly's sub-concepts. Therefore, when we try to develop some programs to prevent memory decrease of elderly women, we should take these point into consideration.

• Journal of the Chungcheong Mathematical Society
• /
• v.29 no.4
• /
• pp.573-584
• /
• 2016

Invertible transformations over n-bit words are essential ingredients in many cryptographic constructions. Such invertible transformations are usually represented as a composition of simpler operations such as linear functions, S-P networks, Feistel structures and T-functions. Among them T-functions are probably invertible transformations and are very useful in stream ciphers. In this paper we will characterize a secure trinomial on ${\mathbb{Z}}_{2^n}$ which generates an n-bit word sequence without consecutive elements of period $2^n$.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.293-297
• /
• 1998

전화망에서의 연결 숫자 인식 시스템의 개발에 대한 내용을 다루며, 이 시스템에서 다양한 숫자 모델링 방법들을 구현하고 비겨하였다. Word 모델의 경우 문맥독립 whole-word 모델을 구현하였으며, sub-word 모델로는 triphone 모델과 불파음화 자음을 모음에 포함시킨 modified triphone 모델을 구현하였다. 그리고 tree-based clustering 방법을 sub-word 모델과 문맥종속 whole-word 모델에 적용하였다. 이와 같은 숫자모델들에 대해 연속 HMM을 이용하여 화자독립 연결숫자 인식 실험을 수행한 결과, 문맥종속 단어 모델이 문맥독립 단어 모델보다 우수한 성능을 나타냈으며, triphone 모델과 modified triphone 모델은 유사한 성능을 나타냈다. 특히 tree-based clustering 방법을 적용한 문맥종속 단어 모델이 4연 숫자열에 대해 99.8%의 단어 dsltlr률 및 99.1%의 숫자열 인식률로서 가장 우수한 성능을 나타내었다.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.250-262
• /
• 2024

Air-writing recognition is relevant in areas such as natural human-computer interaction, augmented reality, and virtual reality. A trajectory is the most natural way to represent air writing. We analyze the recognition accuracy of words written in air considering five features, namely, writing direction, curvature, trajectory, orthocenter, and ellipsoid, as well as different parameters of a hidden Markov model classifier. Experiments were performed on two representative datasets, whose sample trajectories were collected using a Leap Motion Controller from a fingertip performing air writing. Dataset D₁ contains 840 English words from 21 classes, and dataset D₂ contains 1600 English words from 40 classes. A genetic algorithm was combined with a hidden Markov model classifier to obtain the best subset of features. Combination ftrajectory, orthocenter, writing direction, curvatureg provided the best feature set, achieving recognition accuracies on datasets D₁ and D₂ of 98.81% and 83.58%, respectively.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.395-398
• /
• 1994

In this paper the word recognition using sub-model based Hidden Markov Model was studied. Phoneme models were composed of 61 phonemes in therms of Korean language pronunciation characteristic. Using this, word model was maded by serial concatenation. But, in case of this phoneme concatenation, the second and the third phoneme of syllable are overlapped in distribution at the same time. So considering this, the method that combines the second and the third phoneme to one model was proposed. And to prevent the increase in number of model, similar phonemes were combined to one, and finially, 57 models were created. In experiment proper model structure of sub-model was searched for, and recognition results were compared. So similar recognition results were maded, and overall recognition rates were increased in case of using parameter tying method.

• Korean Journal of Materials Research
• /
• v.14 no.6
• /
• pp.402-406
• /
• 2004

$WSi_2$, $TiSi_2$, $CoSi_2$, and $TaSi_2$ are general silicides used today in semiconductor devices. $WSi_2$ thin films have been proposed, studied and used recently in CMOS technology extensively to reduce sheet resistance of polysilicon and $n^{+}$ region. However, there are several serious problems encountered because $WSi_2$ is oxidized and forms a native oxide layer at the interface between $WSi_2$ and $Si_3$$N_4$. In this study, we have introduced 20 $slm-N_2$ gas from top to bottom of the furnace in order to control native oxide films between $WSi_2$ and $Si_3$$N_4$ film. In resulting SEM photographs, we have observed that the native oxide films at the surface of $WSi_2$ film are removed using the long injector system.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.167-170
• /
• 2000

일반적인 한국어 대용량 어휘인식에 사용되는 triphone 모델은 한국어의 특성을 잘 표현한다는 장점이 있으나 인식시간이 길어지게 된다. 이러한 triphone 모델의 단점을 극복하기 위해 음절단위 HMM 모델을 사용하는 방법이 있는데 이 모델은 인식시간을 줄일 수 있으나 triphone 모델에 비해서 인식률이 낮다. 본 논문에서는 음성 인식시간을 단축시키고 조음현상을 고려하기 위하여 초성과 종성 자음은 각각의 biphones으로 나타내고 중성 모음은 1개의 monophone으로 나타내는 모델을 제안하였다. PBW445 음성 데이터베이스에 대한 실험결과, 제안한 인식모델이 triphone 모델에 가까운 인식률을 나타내었으며, 인식시간을 크게 단축하였다.

• Honam Mathematical Journal
• /
• v.45 no.3
• /
• pp.542-554
• /
• 2023

Given a real number α, the Lagrange number of α is the supremum of all real numbers L > 0 for which the inequality |α - p/q| < (Lq²)^-1 holds for infinitely many rational numbers p/q. All Lagrange numbers less than 3 can be arranged as a set {l_p/q : p/q ∈ ℚ ∩ [0, 1]} using the Farey index. The present paper considers a function C(α) devised from Sturmian words. We demonstrate that the function C(α) contains all information on Lagrange numbers less than 3. More precisely, we prove that for any real number α ∈ (0, 1], the value C(α) - C(0) is equal to the sum of all numbers 3 - l_p/q where the Farey index p/q is less than α.