• The KIPS Transactions:PartB
• /
• v.8B no.1
• /
• pp.59-65
• /
• 2001

워터쉐드 변환은 영상분할을 위한 강력한 도굴로 이용되고 있으나, 일반적으로 다수의 국부적 최소점들로 인한 과분할 현상을 초래하여 이를 해결하기 위한 많은 방법들이 연구되어지고 있다. 본 논문에서는 동시정보행렬을 분석하여 비 관련 최소점들을 억제함과 동시에 의미 있는 화소 집합들만을 마커로 선택하고 레이블링하는 자동마커 추출단계와 각 마커로부터 범랑과정 및 재 레이블링에 의한 워터쉐드 추출단계를 수행하여 영상을 분할하는 자동마커 기반 워터쉐드 영상분할 알고리즘을 제안한다. 제안한 알고리즘이 과분할 정도로 현격히 줄이는 것을 보이기 위해 일반영상과 텍스쳐 특성이 강한 ICQ(Indo Cyanine Green) 망막영상에 적용하여 실험 분석하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.546-550
• /
• 2010

In this paper, we propose a method for the postprocessing of cursive script recognition in Wine Label Images. The proposed method mainly consists of three steps: combination matrix generation, character combination filtering, string matching. Firstly, the combination matrix generation step detects all possible combinations from a recognition result for each of the pieces. Secondly, the unnecessary information in the combination matrix is removed by comparing with bigram of word in the lexicon. Finally, string matching step decides the identity of result as a best matched word in the lexicon based on the levenshtein distance. An experimental result shows that the recognition accuracy is 85.8%.

• Horticultural Science & Technology
• /
• v.28 no.5
• /
• pp.762-767
• /
• 2010

This study was conducted to investigate the influence of formulation of fungicides on epicuticular waxes in 'Campbell Early' grapes. Non-bagged and bagged berries were treated with wettable powder, suspension concentrate and emulsifiable concentrate 15 days after full bloom (DAFB) and 48 DAFB (veraison), respectively. Fruit skin was observed by naked eye and scanning electron microscope (SEM) at harvest. Remarkable white blots were observed on the berries treated 48 DAFB in the order of wettable powder, suspension concentrate, and emulsifiable concentrate. The observation by SEM showed all formulations of fungicides damaged the ultra-structure of epicuticular waxes; also, an unknown substance was observed on treatment with wettable powder and suspension concentrate. Moreover epicuticular wax appeared to be melting on the grapes treated with emulsifiable concentrate. Also, non-bagged grapes showed serious contamination of epicuticular wax by some unknown substance, but bagged grapes had only fungicides' traces.

• The Korean Journal of Physiology
• /
• v.17 no.1
• /
• pp.1-11
• /
• 1983

1) The two microelectrode method was used to voltage clamp small preparations of rabbit sinoatrial node. The kinetics of hyperpolarization activated inward current, $i_f$ were analysed. 2) The hrperpolarization pulses activated $i_f$ current in the presence of $10^{-7}g/ml$ TTX and 2 mM $Mn^{2+}$. The activation range was in between -45 mV to -75 mV. The current magnitude was increased and time course was faster by strong hyperpolarization pulses. 3) Standard envelope tests indicated that this current is exponentially controlled by single gate. 4) Semilogarithmic plot of $i_f$ activation versus time was found to be linear in the activation range. The decrease in current magnitude and the shifts in activation curve and rate constants curve to the hyperpolarizing direction were obtained with $Ba^{2+}$, indicating that $Ba^{2+}$ shifts the voltage dependence of the gating kinetics, were partially reversed by 24 mM $K^+$.

• Radiation Oncology Journal
• /
• v.26 no.1
• /
• pp.24-34
• /
• 2008

Purpose: To assess the efficacy of the use of accelerated hyperfractionated radiotherapy(AHRT) for locally advanced uterine cervix cancers. Materials and Methods: Between May 2000 and September 2002, 179 patients were identified with FIGO stage IIB, IIIB, and IVA cancers. Of the 179 patients, 45 patients were treated with AHRT(AHRT group) and 134 patients were treated with conventional radiotherapy(CRT group), respectively. Patients undergoing the AHRT regimen received a dose of 30 Gy in 20 fractions(1.5 $Gy{\times}2$ fractions/day) to the whole pelvis. Subsequently, with a midline block, we administered a parametrial boost with a dose of 20 Gy using 2 Gy fractions. Patients also received two courses of low-dose-rate brachytherapy, up to a total dose of 85{\sim}90 Gy to point A. In the CRT group of patients, the total dose to point A was $85{\sim}90$ Gy. The overall treatment duration was a median of 37 and 66 days for patients that received AHRT and CRT, respectively. Statistical analysis was calculated by use of the Kaplan-Meier method, the log-rank test, and Chi-squared test. Results: For patients that received cisplatin-based concurrent chemotherapy and radiotherapy, the local control rate at 5 years was 100% and 79.2% for the AHRT and CRT group of patients, respectively(p=0.028). The 5-year survival rate for patients with a stage IIB bulky tumor was 82.6% and 62.1% for the AHRT group and CRT group, respectively(p=0.040). There was no statistically significant difference for severe late toxicity between the two groups(p=0.561). Conclusion: In this study, we observed that treatment with AHRT with concurrent chemotherapy allows a significant advantage of local control and survival for locally advanced uterine cervix cancers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.687-696
• /
• 2014

This paper presents a semantic object extraction method using user's stroke input, color, and depth information. It is supposed that a semantically meaningful object is surrounded with a few strokes from a user, and has similar depths all over the object. In the proposed method, deciding the region of interest (ROI) is based on the stroke input, and the semantically meaningful object is extracted by using color and depth information. Specifically, the proposed method consists of two steps. The first step is over-segmentation inside the ROI using color and depth information. The second step is semantically meaningful object extraction where over-segmented regions are classified into the object region and the background region according to the depth of each region. In the over-segmentation step, we propose a new marker extraction method where there are two propositions, i.e. an adaptive thresholding scheme to maximize the number of the segmented regions and an adaptive weighting scheme for color and depth components in computation of the morphological gradients that is required in the marker extraction. In the semantically meaningful object extraction, we classify over-segmented regions into the object region and the background region in order of the boundary regions to the inner regions, the average depth of each region being compared to the average depth of all regions classified into the object region. In experimental results, we demonstrate that the proposed method yields reasonable object extraction results.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.472-474
• /
• 2001

본 논문은 wavelet 기반의 watershed를 이용한 효율적인 영상 분할을 기법을 제안한다. 영상 분할을 위해 입력 영상을 wavelet transform을 사용하여 low-resolution 영상을 생성한 후 watershed 알고리즘을 이용해 분할하고, 이를 Inverse wavelet transform함으로써 원 영상으로 복원한다. 복원된 영상을 의미 있는 영역들로 분할하기 위해 wavelet 특징값의 유사성을 두 인접한 영역에 비교하여 병합한다. 실험 결과 제안한 방법은 영상의 잡음에 대한 강인함과 영상의 과분할 문제를 해결할 수 있다.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.709-721
• /
• 2009

This paper discusses an efficient image segmentation using morphological watershed algorithm that is robust to noise. Morphological image segmentation consists of four steps: image simplification, computation of gradient image and watershed algorithm and region merging. Conventional watershed segmentation exhibits a serious weakness for over-segmentation of images. In this paper we present a morphological edge detection methods for detecting edges under noisy condition and apply our watershed algorithm to the resulting gradient images and merge regions using Kolmogorov-Smirnov test for eliminating irrelevant regions in the resulting segmented images. Experimental results are analyzed in both qualitative analysis through visual inspection and quantitative analysis with percentage error as well as computational time needed to segment images. The proposed algorithm can efficiently improve segmentation accuracy and significantly reduce the speed of computational time.

• Journal of Korean Society of Transportation
• /
• v.22 no.1 s.72
• /
• pp.63-72
• /
• 2004

In conducting traffic safety programs, it is very important to identify hazardous sites in appropriate manner. The rate qualify control method is generally used in identifying hazardous sites since it can interpret the sites in the statistic aspects. The rate qualify control method is based on the assumption that the occurrences of traffic crashes follow the Poisson's distribution in which the expected value of traffic crashes equals the variance of those. However, there is greater variability than expected statistically, we call this phenomenon over dispersion. This study analyzed the problem related to the rate quality control method under the over dispersed data, and established a methodology to solve the problem. As a result of test on the basis of the field data, the new approach produced more reasonable results than those of the Poisson based rate quality control method.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.449-463
• /
• 2015

Video object tracking is important for variety of applications, such as security, video indexing and retrieval, video surveillance, communication, and compression. This paper proposes an object tracking method in HEVC bitstreams. Without pixel reconstruction, motion vector (MV) and size of prediction unit in the bitstream are employed in an Spatio-Temporal Markov Random Fields (ST-MRF) model which represents the spatial and temporal aspects of the object's motion. Coefficient-based object shape adjustment is proposed to solve the over-segmentation and the error propagation problems caused in other methods. In the experimental results, the proposed method provides on average precision of 86.4%, recall of 79.8% and F-measure of 81.1%. The proposed method achieves an F-measure improvement of up to 9% for over-segmented results in the other method even though it provides only average F-measure improvement of 0.2% with respect to the other method. The total processing time is 5.4ms per frame, allowing the algorithm to be applied in real-time applications.