• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.3
• /
• pp.97-107
• /
• 1997

Image segmentation is teh important step in image infromation extraction for computer vison sytems. Fuzzy clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are derived from the fuzzy c-means (FCM) algorithm. The FCM algorithm uses th eprobabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belongingor compatibility. moreover, the FCM algorithm has considerable trouble above under noisy environments in the feature space. Recently, the possibilistic C-mean (PCM) for solving growing for color image segmentation. In the PCM, the membersip values may be interpreted as degrees of possibility of the data points belonging to the classes. So, the problems in the FCM can be solved by the PCM. The clustering results by just PCM are not smoothly bounded, and they often have holes. So, the region growing was used as a postprocessing. In our experiments, we illustrated that the proposed method is reasonable than the FCM in noisy enviironments.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.736-739
• /
• 2006

While hyperspectral data are very rich in information, their processing poses several challenges such as computational requirements, noise removal and relevant information extraction. In this paper, the application of advanced scale-space filtering to selected hyperspectral bands was investigated. In particular, a pre-processing tool, consisting of anisotropic diffusion and morphological leveling filtering, has been developed, aiming to an edge-preserving smoothing and simplification of hyperspectral data, procedures which are of fundamental importance during feature extraction and object detection. Two scale space parameters define the extent of image smoothing (anisotropic diffusion iterations) and image simplification (scale of morphological levelings). Experimental results demonstrated the effectiveness of the developed scale space filtering for the enhancement and smoothing of hyperspectral remote sensing data and their advantage against watershed over-segmentation problems and edge detection.

• Journal of Biomedical Engineering Research
• /
• v.16 no.2
• /
• pp.121-128
• /
• 1995

Information about retinal blood vessels can be used in grading disease severity or as part of the process of automated diagnosis of diseases with ocular menifestations. In this paper, we address the problem of detecting retinal blood vessels and optic disk (papilla) in eye-fundus images. We introduce an algorithm for feature extraction based on Fuzzy Clustering algorithm (fuzzy c-means). A method of finding the optic disk (papilla) is proposed in the eye-fundus images. Additionally, the inrormations such as position and area of the optic disk are extracted. The results are compared to those obtained from other methods. The automatic detection of retinal blood vessels and optic disk in the eye-rundus images could help physicians in diagnosing ocular diseases.

• The Journal of Korea Robotics Society
• /
• v.10 no.1
• /
• pp.33-41
• /
• 2015

Recent developments in robotics and intelligent vehicle area, bring interests of people in an autonomous driving ability and advanced driving assistance system. Especially fully automatic parking ability is one of the key issues of intelligent vehicles, and accurate parked vehicles detection is essential for this issue. In previous researches, many types of sensors are used for detecting vehicles, 2D LiDAR is popular since it offers accurate range information without preprocessing. The L shape feature is most popular 2D feature for vehicle detection, however it has an ambiguity on different objects such as building, bushes and this occurs misdetection problem. Therefore we propose the accurate vehicle detection method by using a 3D complete vehicle model in 3D point clouds acquired from front inclined 2D LiDAR. The proposed method is decomposed into two steps: vehicle candidate extraction, vehicle detection. By combination of L shape feature and point clouds segmentation, we extract the objects which are highly related to vehicles and apply 3D model to detect vehicles accurately. The method guarantees high detection performance and gives plentiful information for autonomous parking. To evaluate the method, we use various parking situation in complex urban scene data. Experimental results shows the qualitative and quantitative performance efficiently.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.2
• /
• pp.11-20
• /
• 2010

In this paper we propose a face detection system which consists of a method of face candidate extraction using skin color and a method of face verification using the feature of facial structure. Firstly, the proposed extraction method of face candidate uses the image segmentation and merging algorithm in the regions of skin color and the neighboring regions of skin color. These two algorithms make it possible to select the face candidates from the variety of faces in the image with complicated backgrounds. Secondly, by using the partial face classifier, the proposed face validation method verifies the feature of face structure and then classifies face and non-face. This classifier uses face images only in the learning process and does not consider non-face images in order to use less number of training images. In the experimental, the proposed method of face candidate extraction can find more 9.55% faces on average as face candidates than other methods. Also in the experiment of face and non-face classification, the proposed face validation method obtains the face classification rate on the average 4.97% higher than other face/non-face classifiers when the non-face classification rate is about 99%.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2020

The image analysis is an important and predominant task for classifying the different parts of the image. The analysis of complex image analysis like histopathological define a crucial factor in oncology due to its ability to help pathologists for interpretation of images and therefore various feature extraction techniques have been evolved from time to time for such analysis. Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis. The paper highlights how both techniques differ in feature extraction from complex images and discusses the potential pros and cons. The use of Convolution Neural Network (CNN) in image segmentation, detection and diagnosis of tumour, feature extraction is important but there are several challenges that need to be overcome before Deep Learning can be applied to digital pathology. The one being is the availability of sufficient training examples for medical image datasets, feature extraction from whole area of the image, ground truth localized annotations, adversarial effects of input representations and extremely large size of the digital pathological slides (in gigabytes).Even though formulating Histopathological Image Analysis (HIA) as Multi Instance Learning (MIL) problem is a remarkable step where histopathological image is divided into high resolution patches to make predictions for the patch and then combining them for overall slide predictions but it suffers from loss of contextual and spatial information. In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.

• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1171-1181
• /
• 2014

In this paper, we propose improved methods which are image conversion and extraction method of watershed seed using morphological characteristic of teeth on complement image. Conventional tooth segmentation methods are occurred low detection ratio at molar region and over, overlap segmentation owing to specular reflection and morphological feature of molars. Therefore, in order to solve the problems of the conventional methods, we propose the image conversion method and improved extraction method of watershed seed. First, the image conversion method is performed using RGB, HSI space of tooth image for to extract boundary and seed of watershed efficiently. Second, watershed seed is reconstructed using morphological characteristic of teeth. Last, individual tooth segmentation is performed using proposed seed of watershed by watershed algorithm. Therefore, as a result of comparison with marker controlled watershed algorithm and the proposed method, we confirmed higher detection ratio and accuracy than marker controlled watershed algorithm.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.227-236
• /
• 1997

Manual grading and sorting of red-ginsengs are inherently unreliable due to its subjective nature. A computerized technique based on optical and geometrical characteristics was studied for the objective quality evalution. Spectral reflectance of three categories of red-ginsengs - "Chunsam", "Chisam", "Yangsam" - were measured and analyzed. Variation of reflectance among parts of a single ginseng was more significant than variation among the quality categories of ginsengs. A PC-based image processing algorithm was developed to extract geometrical features such as length and thickness of body, length and number of roots, position of head and branch point, etc. The algorithm consisted of image segmentation, calculation of Euclidean distance, skeletonization and feature extraction. Performance of the algorithm was evaluated using sample ginseng images and found to be mostly sussessful.