• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.239-248
• /
• 2010

Leukocyte in blood smear image provides significant information to doctors for diagnosis of patient health status. Therefore, it is necessary step to separate leukocyte from blood smear image among various blood cells for early disease prediction. In this paper, we present a saliency map and stepwise region merging based leukocyte segmentation method. Since leukocyte region has salient color and texture, we create a saliency map using these feature map. Saliency map is used for sub-image separation. Then, clustering is performed on each sub-image using mean-shift. After mean-shift is applied, stepwise region-merging is applied to particle clusters to obtain final leukocyte nucleus. The experimental results show that our system can indeed improve segmentation performance compared to previous researches with average accuracy rate of 71%.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.70-80
• /
• 1999

In this paper, a new hierarchical image segmentation algorithm based on human visual system(HVS) characteristic is proposed which can efficiently reduce and control transmission information quantity without the degradation of the subjective and objective image quality. It consists of image segmentation based on mathematical morphology and region merging considering HVS characteristic for the pairs of two adjacent regions at each level of the hierarchy. Image segmentation is composed of 3-level hierarchical structure. In the region merging structure of each level, we extract the pairs of two adjacent regions which human vision can't discriminate, and then merge them. The proposed region merging method extracts pairs of two neighbor regions to be merged and performs region merging according to merging priority based on HVS characteristics. The merging priority for each adjacent pair is determined by the proposed merging priority function(MPF). First of all, the highest priority pair is merged. The information control factor is used to regulate the transmission information at each level. The proposed segmentation algorithm can efficiently improve bottleneck problem caused by excessive contour information at region-based very low bit rate coding. And it shows that it is more flexible structure than that of conventional method. In experimental results, though PSNR and the subjective image quality by the proposed algorithm is similar to that of conventional method, the contour information quantity to be transmitted is reduced considerably. Therefore it is an efficient image segmentation algorithm for region-based very low bit rate coding.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.33-42
• /
• 2005

In this paper, we propose an efficient segmentation algerian using morphological grayscale reconstruction for region-based coding. Each segmentation stage consists of simplification, marker extraction and decision. The simplification removes unnecessary components to make an easier segmentation. The marker extraction finds the flat zones which are the seed points from the simplified image. The decision is to locate the contours of regions detected by the marker extraction. For the simplification, we use a new connected operator based on the size and contrast. In the marker extraction stage, the regions reconstructed to original values we excluded from the candidate marker. For the other regions, the regions which are larger than structuring elements or have higher contrast than a threshold value are selected as markers. For the initial segmentation, the conventional hierarchical watershed algorithm and the extracted markers are used. Finally in the region merging stage, we propose an efficient region merging algorithm which preserves a high quality in terms of the number of regions. At the same time, the pairs which have higher contrast than a threshold are excluded from the region merging stage. Experimental results show that the proposed marker extraction method produces a small number of markers, while maintaining high quality and that the proposed region merging algorithm achieves a good performance in terms of the image quality and the number of regions.

• Journal of Broadcast Engineering
• /
• v.21 no.3
• /
• pp.425-435
• /
• 2016

In this paper, we propose a classification model by analyzing raw material images recorded using a color CCD camera to automatically classify good and defective agricultural products such as rice, coffee, and green tea, and raw materials. The current classifying agricultural products mainly depends on visual selection by skilled laborers. However, classification ability may drop owing to repeated labor for a long period of time. To resolve the problems of existing human dependant commercial products, we propose a vision based automatic raw material classification combining mean shift clustering and stepwise region merging algorithm. In this paper, the image is divided into N cluster regions by applying the mean-shift clustering algorithm to the foreground map image. Second, the representative regions among the N cluster regions are selected and stepwise region-merging method is applied to integrate similar cluster regions by comparing both color and positional proximity to neighboring regions. The merged raw material objects thereby are expressed in a 2D color distribution of RG, GB, and BR. Third, a threshold is used to detect good and defective products based on color distribution ellipse for merged material objects. From the results of carrying out an experiment with diverse raw material images using the proposed method, less artificial manipulation by the user is required compared to existing clustering and commercial methods, and classification accuracy on raw materials is improved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1049-1059
• /
• 2019

We propose a learning-based image segmentation algorithm. Starting from super-pixels, our method learns the probability of merging two regions based on the ground truth made by humans. The learned information is used in determining whether the two regions should be merged or not in a segmentation stage. Unlike exiting learning-based algorithms, we use both local and object information. The local information represents features computed from super-pixels and the object information represent high level information available only in the learning process. The object information is considered as privileged information, and we can use a framework that utilize the privileged information such as SVM+. In experiments on the Berkeley Segmentation Dataset and Benchmark (BSDS 500) and PASCAL Visual Object Classes Challenge (VOC 2012) data set, out model exhibited the best performance with a relatively small training data set and also showed competitive results with a sufficiently large training data set.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.105-115
• /
• 2011

In Vision-based Intelligent Transportation System(ITS) the segmentation of road region is a very basic functionality. Accordingly, in this paper, we propose a region segmentation method using adaptive pattern extraction technique to segment road regions and sky regions from original images. The proposed method consists of three steps; firstly we perform the initial segmentation using Mean Shift algorithm, the second step is the candidate region selection based on a static-pattern matching technique and the third is the region growing step based on a dynamic-pattern matching technique. The proposed method is able to get more reliable results than the classic region segmentation methods which are based on existing split and merge strategy. The reason for the better results is because we use adaptive patterns extracted from neighboring regions of the current segmented regions to measure the region homogeneity. To evaluate advantages of the proposed method, we compared our method with the classical pattern matching method using static-patterns. In the experiments, the proposed method was proved that the better performance of 8.12% was achieved when we used adaptive patterns instead of static-patterns. We expect that the proposed method can segment road and sky areas in the various road condition in stable, and take an important role in the vision-based ITS applications.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.473-481
• /
• 2005

In this paper, we propose an image segmentation method preserving object's boundaries by using the number of quantized colors and merging regions using adaptive threshold values. First of all, the proposed method quantizes an original image by a vector quantization and the number of quantized colors is determined differently using PSNR each image. We obtain initial regions from the quantized image, merge initial regions in CIE Lab color space and RGB color space step by step and segment the image into semantic regions. In each merging step, we use color distance between adjacent regions as similarity-measure. Threshold values for region-merging are determined adaptively according to the global mean of the color difference between the original image and its split-regions and the mean of those variations. Also, if the segmented image of RGB color space doesn't split into semantic objects, we merge the image again in the CIE Lab color space as post-processing. Whether the post-processing is done is determined by using the color distance between initial regions of the image and the segmented image of RGB color space. Experiment results show that the proposed method splits an original image into main objects and boundaries of the segmented image are preserved. Also, the proposed method provides better results for objective measure than the conventional method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.587-590
• /
• 2003

얼굴영역을 분할하기 위해서 Watershed Algorithm 와 Object Grouping 을 이용한 얼굴영역 분할기법을 제안한다. 영상분할에 단점은 단일 알고리즘으로 영역분할이 어렵고, 또한 복잡한 영상에서 정확한 영역을 분할하기가 어렵다는 것이다. 그래서 본 논문에서는 Watershed Segmentation 기법과 Grouping 작업을 통한 병합, 그리고 색상의 선형회귀분석을 이용한 분석법을 적용하여 분할하고자 한다. 얼굴영역 분할방법을 전처리 과정과 영역 병합 그리고 얼굴 부분을 추출하는 3 단계의 과정으로 나누고, 전처리 과정에서는 수리형태학적(Mophological) 연산자를 이용한 영상 분할기법을 이용하여 분할한 후 얼굴 후보 영역을 검출, 영역병합과정에서 기존의 학습데이터와의 유사도를 측정, 얼굴객체추출 조건에 맞지 않는 객체들을 모두 제거함으로써, 정확한 얼굴부분을 분할해 낸다. 실험결과 제안한 방법을 통해 비교적 정확한 얼굴영역을 분할 할 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.26 no.1
• /
• pp.25-39
• /
• 1999

지리 정보 시스템에서 공간 분석을 위해 사용되는 중요한 연산인 공간 조인은 대상이 되는 공간 객체의 수가 증가함에 따라서 연산 시간이 지수적으로 증가하는 특징을 가지고 있다. 그러므로 다량의 공간 데이터에 대해서 공간 연산시간을 줄이기 위한 병렬처리가 필요하다. 이 논문에서는 비겹침 정규분할 방식의 사분트리를 이용한 공간 조인 알고리즘을 제시하고 MIMD 구조 및 공유 디스크 방식의 병렬 처리시스템에 적용하여 성능을 평가한다. 사분트리를 이용한 공간조인 방법으로서 중복 표현된 공간객체를 줄이기 위한 사분면(quadrant)의 병합 방법,영역 제한을 통해 연산 대상 객체를 줄이기 위한 사분면의 분할 방법, 그리고 병합 및 분할 방법을 혼용하여 공간 조인 연산의 숫자를 최소화하는 혼합 방법을 제시한다. 실험 평가에서는 각 방법들을 병렬 처리 시스템에 적용하여 여과단계 및 정제단계에서의 연산량과 수행 시간을 통해 성능을 비교 평가한다. 실험결과, 여과 단계에서는 분할 방법이 가장 우수했지만, 정제 단계에서는 병합 방법이 가장 우수했다. 따라서 전체적인 고려할 때 두 방법의 장점을 수용한 혼합 방법이 가장 우수한 성능을 나타냈다.

• Journal of Broadcast Engineering
• /
• v.4 no.1
• /
• pp.44-58
• /
• 1999

In this paper, a rate-distortion based image segmentation algorithm is presented using a recursive merging with region adjacency graph (RAG). In the method, the dissimilarity between a pair of adjacent regions is represented as a Lagrangian cost function considered in rate-distortion sense. Lagrangian multiplier is estimated in each merging step, a pair of adjacent regions whose cost is minimal is searched and then the pair of regions are merged into a new region. The merging step is recursively performed until some termination criterion is reached. The proposed method thus is suitable for region-based coding or segmented-based coding. Experiment results for 256x256 Lena show that segmented-based coding using the proposed method yields PSNR improvement of about 2.5 - 3.5 dB. 0.8 -1.0 dB. 0.3 -0.6 dB over mean-difference-based method. distortion-based method, and JPEG, respectively.