• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.1-9
• /
• 2008

One of the problems for implementing the spot detection phase in the 2-DE gel image analysis program is the eliminating noises in the image. Remained noises after the preprocessing phase cause the over-segmented regions by the segmentation phase. To identify and exclude the over-segmented background regions, if we use the fixed thresholding method that is choosing an intensity value for the threshold, the spots that is invisible by the eyes but mean a very small amount proteins which have important role in the biological samples could be eliminated. This paper propose an adaptive thresholding method that come from an idea that is got on statistical analysing for the prominences of the peaks. The adaptive thresholding method works as following. Firstly we calculate an average prominence value curve and fit it to exponential function curve, as a result we get parameters for the exponential function. And then we calculate a threshold value by using the parameters and probability distribution of errors. Lastly we apply the threshold value to the region for determining the region is a noise or not. According to the probability distribution of errors, the reliability is 99.85% and we show the correctness of the proposed method by representing experiment results.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.81-92
• /
• 1999

In this paper, we propose a new image segmentation algorithm which can be use din object-based image coding applications such as MPGA-4. Since the conventional objet segmentation methods based on mathematical morphology tend to yield oversegmented results, they normally need a postprocess which merges small regions to obtain a larger one. To solve this oversegmentation problem, in this paper, we prosed a block-based segmentation algorithm that can identify large texture regions in the image. Also, by applying the watershed algorithm to the image blocks between the homogeneous regions, we can obtain the exact pixel-based contour. Experimental results show that the proposed algorithm yields larger segments, particularly in the textural area, and reduces the computational complexities.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.610-616
• /
• 2012

In this paper, we present a method to detect an object such as ship, rock and buoy from sea IR image for the safety navigation. To this end, we do the image smoothing first and the apply watershed algorithm to segment image into subregions. Since watershed algorithm almost always produces over-segmented regions, it requires posterior merging process to get meaningful segmented regions. We propose an efficient merger algorithm that requires only two times of direct access to the pixels regardless of the number of regions. Also by analyzing IR image obtained from sea environments, we could find out that most horizontal edge come out from object regions. For the given input IR image we extract horizontal edge and eliminate isolated edges produced from background and noises by adopting morphological operator. Among the segmented regions, the regions that have horizontal edges are extracted as final results. Experimental results show the adequacy of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.3
• /
• pp.237-246
• /
• 2001

A high speed context-free marker-controlled and minima imposition-free watershed transform is proposed for efficient multi-object detection and segmentation from a complex background. The context-free markers are extracted from a complex backgrounded multi-object image using a noise tolerant attention operator. These make marker-controlled watershed possible for the over-segmentation reduction without region merging. The proposed method presents a marker-constrained labeling that can speed up the segmentation of a marker-controlled watershed transform by eliminating the necessity of the minima imposition. Simulation results show that the proposed method can efficiently detects and segments multiple objects from a complex background while reducing over- segmentation and the computation time.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.1
• /
• pp.38-46
• /
• 2004

Image segmentation is the task which partitions the image into meaningful regions and considered to be one of the most important steps in computer vision and image processing. Image segmentation is also widely used in object-based video compression such as MPEG-4 to extract out the object regions from the given frame. Watershed algorithm is frequently used to obtain the more accurate region boundaries. But, it is well known that the watershed algorithm is extremely sensitive to gradient noise and usually results in oversegmentation. To solve such a problem, we propose an image segmentation method which is robust to noise by using stabilized inverse diffusion equation (SIDE) and is more efficient in segmentation by employing multiresolution approach. In this paper, we apply both the region projection method using labels of adjacent regions and the region merging method based on region adjacency graph (RAG). Experimental results on noisy image show that the oversegmenation is reduced and segmentation efficiency is increased.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1520-1527
• /
• 2019

Superpixel methods are widely used in the preprocessing stage as a method to reduce computational complexity by simplifying images while maintaining the characteristics of images in the field of computer vision. It is common to generate superpixels with a regular size and form based on the pixel values rather than considering the characteristics of the image. In this paper, we propose a method to generate superpixels considering the characteristics of an image according to the application. The proposed method consists of two steps, and the first step is to oversegment an image so that the boundary information of the image is well preserved. In the second step, superpixels are merged based on similarity to produce the desired number of superpixels, where the form of superpixels are controlled by limiting the maximum size of superpixels. Experimental results show that the proposed method preserves the boundaries of an image more accurately than the existing method.

• Radiation Oncology Journal
• /
• v.18 no.1
• /
• pp.27-31
• /
• 2000

Purpose : The aim of this study was to investigate treatment results, toxicity and efficacy of hypefractionated radiation therapy combined with paclitaxel for paraaortic node recurrence in cervix cancer. Materials and Methods: Between September 1997 to March 1999, 12 patients with paraaortic node recurrence in cervix cancer who previously received radical or postoperative radiotherapy were treated with hypefractionated radiation therapy combined with paclitaxel. Of these, 2 patients who irradiated less than 30 Gy were excluded, 10 patients were eligible for this study. Median age was 51 years. Initial FIGO stage was 1 stage IBI, 2 stage IIA, 7 stage IIB. For initial treatment, 7 patients received radical radiotherapy and 3 received postoperative radiotherapy. The paraaortic field encompassed the gross recurrent disease with superior margin at T12, and inferior margin was between L5 and S1 with gap for previously pelvic radiation field. The radiation field was initially anterior and posterior opposed field followed by both lateral field. The daily dose was 1.2 Gy, twice daily fractions, and total radiotherapy dose was between 50.4 and 60 Gy(median, 58.8 Gy). Concurrent chemotherapy was done with paclitaxel as a radiosensitizer. Dose range was from 20 mg/m$^{3}$ to 30 mg/m$^{3}$ (median, 25 mg/m$^{3}$), and cycle of chemotherapy was from 3 to 6 (median, 4.5 cycle). Follow-up period ranged from 3 to 21 months. Results : Interval between initial diagnosis and paraaortic node recurrence was range from 2 to 63 months (median, 8 months). The 1 year overall survival rate and median survival were 75$\%$ and 9.5 months, respectively. The 1 year disease free survival rate and median disease free survival were 30$\%$ and 7 months, respectively. At 1 month after treatment, 4 (40$\%$) achieved a complete response and 6 (60$\%$) experienced a partial response and all patients showed response above the partial response. There was distant metastasis in 6 patients and pelvic node recurrence In 2 patients after paraaortic node irradiation. There was 2 patients with grade 3 to 4 leukopenla and 8 patients with grade 1 to 2 nausea/ vomiting which was usually tolerable with antlemetic drug. There was no chronic complication in abdomen and pelvis during follow up period. Conclusion : hypefractionated radiation therapy combined with paclitaxel chemotherapy diosensitizer showed high response rate and few complication rate in paraaortic node recurrence in cervix cancer Therefore, present results suggest that hypefractionated radiation therapy combined with paclitaxel chemotherapy can be used as optimal treatment modality in this patients.

• Journal of Plant Biology
• /
• v.36 no.4
• /
• pp.383-389
• /
• 1993

The effects of light and $CO_2$ on the electrophysiological characteristics of guard cells in the intact leaf and in the detached epidermis have been investigated. Guard cells in intact leaves showed the membrane hyperpolarization in response to light. The biggest induced change of the membrane potential difference (PD) in the guard cells of the intact leaf was 13 m V by light and 42 mV by $CO_2$ in Commelina communis. Similar results were obtained with Tradescantia virginiana. However, there were no changes of membrane PD in detached epidermis. In order to determine the influence of the mesophyll on the changes of membrane PD, infiltration of the mesophyll cells with photosynthetic inhibitors was performed. In CCCP infiltrated leaf discs the guard cell membrane was depolarized slightly by red-light and hyperpolarized by $CO_2$, but in leaf discs infiltrated with DCCD and DCMU the guard cell membrane was hyperpolrized by both red-light and $CO_2$ as the control leaf discs. In azide infiltrated leaf discs the guard cell membrane showed no response to light and there was a much reduced membrane hyperpolarization by $CO_2$ compared to other responses. It was likely that azide caused leaf damage and the activity of cell metabolism was decreased greatly, resulting in small membrane PD changes by $CO_2$ and no changes by redlight. Therefore, it can be suggested that red light was sensed by the mesophyll and the light induced guard cell membrane hyperpolarization was related to energy produced by cyclic-photophosphorylation, but ${CO_2}-induced$ guard cell membrane hyperpolarization was not related to photosynthesis. Alkalisation of the vacuole was observed when the intact leaf was exposed to $CO_2$, indicating that membrane hyperpolarization was mainly the result of proton efflux.efflux.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.349-352
• /
• 2000

영상으로부터 의미있는 객체를 영역화하기 위하여, 움직임에 의한 시간적 정보를 이용하거나, 형태학적(Morphological) 기법과 같이 공간적 정보를 이용하는 방법이 있다. 그러나, 단지 시간적 정보나 공간적 정보만을 이용하는 방법은 그 한계를 가지고 있으며, 본 논문에서는 시공간 정보를 이용하여 분할하는 방법을 채택하였다. 시간적 분할에서는, 두 프레임에서 움직임 정보를 찾아내었던 기존 방법을 보완하여 연속되는 세 프레임을 사용하도록 하였다. 이렇게 하면 움직임이 미세한 영상에 대해서도 객체를 분리해 낼 가능성을 높일 수 있게 된다. 공간적 분할시에는, Watershed 알고리즘을 이용하는 형태학적 분할(Morphological Segmentation)[1][2]을 하게 되는데, 전처리 과정의 단일척도경사(Monoscale Gradient) 대신 다중척도 경사(Multiscale Gradient)[3][4]를 사용하여 미세한 경사는 누그러뜨리고 에지 부분의 경사만을 강조하게 하였다. 또한 개선된 Watershed 알고리즘을 제안하여 기존의 Watershed 알고리즘의 과분할 문제를 보완하였다.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.122-128
• /
• 1997

대부분의 한국어 형태소 분석기는 파생명사나 합성명사가 포함된 어절을 오분석 또는 과분석하는 경향이 있다. 이는 하나의 어절에서 오분석이나 과분석을 방지하기 위하여 획득할 수 있는 정보가 제한적이기 때문이다. 이에 본 논문은 파생명사나 합성명사 후보가 포함된 어절뿐만 아니라 주변 및 전문에서 분석에 필요한 정보를 수집하여 이용하는 방법을 제시한다. 제안한 방법은 오분석된 파생명사나 합성명사에만 나타나는 저빈도 단어를 제거하고, 파생명사나 합성명사 후보의 주변 어휘들을 실마리로 이용하며, 문서 전역에서 동일한 파생명사나 합성명사 후보가 포함된 둘 이상의 어절을 비교분석하여 파생명사 및 합성명사 후보가 포함된 어절을 처리한다. 실험 결과 제안한 방법은 99.8%의 정확도와 95.3%의 재현율로 파생명사나 합성명사 후보가 포함된 어절을 올바르게 분석할 수 있었다.