• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.137-150
• /
• 2002

Speech segmentation at phoneme level is important for corpus-based text-to-speech synthesis. In this paper, we examine acoustic modeling methods to improve the performance of automatic speech segmentation system based on Hidden Markov Model (HMM). We compare monophone and triphone models, and evaluate several model training approaches. In addition, we employ an energy-based postprocessing scheme to make correction of frequent boundary location errors between silence and speech sounds. Experimental results show that our system provides 71.3% and 84.2% correct boundary locations given tolerance of 10 ms and 20 ms, respectively.

• 음성과학
• /
• 제9권4호
• /
• pp.265-274
• /
• 2002

In this paper we propose an automatic segmentation system that outputs the time alignment information of phoneme boundary using Viterbi search with HMM (Hidden Markov Model) and corrects these results by an UVS (unvoiced/voiced/silence) classification algorithm. We selecte a set of 39 monophones and a set of 647 extended phones for HMM models. For the UVS classification we use the feature parameters such as ZCR (Zero Crossing Rate), log energy, spectral distribution. The result of forced alignment using the extended phone set is 11% better than that of the monophone set. The UVS classification algorithm shows high performance to correct the segmentation results.

• 대한의용생체공학회:의공학회지
• /
• 제30권2호
• /
• pp.153-161
• /
• 2009

Mammogram is one of the important techniques for mass detection, which is the early diagnosis stage of a breast cancer. Especially, the CAD(Computer Aided Diagnosis) using mammogram improves the working performance of radiologists as it offers an effective mass detection. There are two types of CAD systems using mammogram; automatic and semi-automatic CAD systems. However, the automatic segmentation is limited in performance due to the difficulty of obtaining an accurate segmentation since mass occurs in the dense areas of the breast tissue and has smoother boundaries. Semi-automatic CAD systems overcome these limitations, however, they also have problems including high FP (False Positive) rate and a large amount of training data required for training a classifier. The proposed system which overcomes the aforementioned problems to detect mass is composed of the suspected area selection, the level set segmentation and SVM (Support Vector Machine) classification. To assess the efficacy of the system, 60 test images from the FFDM (Full-Field Digital Mammography) are analyzed and compared with the previous semi-automatic system, which uses the ANN classifier. The experimental results of the proposed system indicate higher accuracy of detecting mass in comparison to the previous systems.

• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.139-146
• /
• 2023

Osteoporosis is a disease in which the risk of bone fractures increases due to a decrease in bone density caused by aging. Osteoporosis is diagnosed by measuring bone density in the total hip, femoral neck, and lumbar spine. To accurately measure bone density in the lumbar spine, the vertebral region must be segmented from the lumbar X-ray image. Deep learning-based automatic spinal segmentation methods can provide fast and precise information about the vertebral region. In this study, we used 695 lumbar spine images as training and test datasets for a deep learning segmentation model. We proposed a lumbar automatic segmentation model, CM-Net, which combines the center point of the spine and the modified U-Net network. As a result, the average Dice Similarity Coefficient(DSC) was 0.974, precision was 0.916, recall was 0.906, accuracy was 0.998, and Area under the Precision-Recall Curve (AUPRC) was 0.912. This study demonstrates a high-performance automatic segmentation model for lumbar X-ray images, which overcomes noise such as spinal fractures and implants. Furthermore, we can perform accurate measurement of bone density on lumbar X-ray images using an automatic segmentation methodology for the spine, which can prevent the risk of compression fractures at an early stage and improve the accuracy and efficiency of osteoporosis diagnosis.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.72-75
• /
• 2008

Image segmentation techniques becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification. This paper presents a new method for image segmentation in High Resolution Remote Sensing Image based on Seeded Region Growing (SRG) and Edge Information. Firstly, multi-spectral edge detection was done using an entropy operator in pan-sharpened QuickBird imagery. Then, the initial seeds were automatically selected from the obtained edge map. After automatic selection of significant seeds, an initial segmentation was achieved by applying SRG. Finally the region merging process, using region adjacency graph (RAG), was carried out to get the final segmentation result. Experimental results demonstrated that the proposed method has good potential for application in the segmentation of high resolution satellite images.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.887-890
• /
• 2012

Image recognition is one of the most important research directions of pattern recognition. Image based road automatic identification technology is widely used in current society, the intelligence has become the trend of the times. This paper studied the image segmentation algorithm theory and its application in road signs recognition system. With the help of image processing technique, respectively, on road signs automatic recognition algorithm of three main parts, namely, image segmentation, character segmentation, image and character recognition, made a systematic study and algorithm. The experimental results show that: the image segmentation algorithm to establish road signs recognition model, can make effective use of smart phone system and application.

• Computers and Concrete
• /
• 제21권6호
• /
• pp.727-739
• /
• 2018

Crack is the most common typical feature of concrete deterioration, so routine monitoring and health assessment become essential for identifying failures and to set up an appropriate rehabilitation strategy in order to extend the service life of concrete structures. At present, image segmentation algorithms have been applied to crack analysis based on inspection images of concrete structures. The results of crack segmentation offering crack information, including length, width, and area is helpful to assist inspectors in surface inspection of concrete structures. This study proposed an algorithm of image segmentation enhancement, named morphological segmentation based on edge detection-II (MSED-II), to concrete crack segmentation. Several concrete pavement and building surfaces were imaged as the study materials. In addition, morphological operations followed by cross-curvature evaluation (CCE), an image segmentation technique of linear patterns, were also tested to evaluate their performance in concrete crack segmentation. The result indicates that MSED-II compared to CCE can lead to better quality of concrete crack segmentation. The least area, length, and width measurement errors of the concrete cracks are 5.68%, 0.23%, and 0.00%, respectively, that proves MSED-II effective for automatic measurement of concrete cracks.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1986년도 추계학술발표회 논문집
• /
• pp.186-190
• /
• 1986

This paper describes a way of implementing the segmentation of 128*128 pixel images to be used as the inputs. to a real-time automatic video tracker. The suggested method uses the lowest valley-value of the computed intensity historgram with 16 levels. This method improves smoothing effects and also significantly reduces hardware requirements. Entire segmentation process is caried out in 10msec thus making a real time application possible.

• 대한전자공학회논문지SP
• /
• 제41권2호
• /
• pp.41-50
• /
• 2004

MPEG-4 표준에서는 객체 단위의 부호화를 수행하기 위해 자연영상으로부터 비디오 객체를 분리하는 영상분할(segmentation) 기술이 필요하다. 영상분할 방법은 크게 자동 영상분할(automatic segmentation)과 반자동 영상분할(semi-automatic segmentation)의 두 부류로 나눌 수 있다. 지금까지 개발된 대부분의 자동 영상분할 방법은 비디오 객체의 명확한 수학적인 모델을 제시하기 곤란하며 한 화면에서 개별 객체를 추출하기 어렵기 때문에 그 성능에 한계가 있다. 본 논문에서는 이러한 문제점을 극복하기 위해 active contour 알고리즘을 이용한 반자동 영상분할 알고리즘을 제안한다. 초기 곡선으로부터 변화 가능한 모든 곡선의 집합을 모양공간으로 정의하고 그 공간을 선형공간이라고 가정하면, 모양공간(shape space)은 모양 행렬에 의해 행(column) 공간과 남은 빈(left null) 공간으로 나뉘어진다. 본 논문에서 제안하는 알고리즘은 행공간의 모양공간 벡터를 이용하여 초기 곡선으로부터 영상의 특징점까지의 변화를 기술하고 동적 그래프 검색 알고리즘을 이용하여 객체의 세밀한 부분을 묘사한다. 모양 행렬과 객체의 윤곽을 추정하기 위한 SUSAN 연산자의 사용으로 제안한 알고리즘은 저수준 영상처리로부터 생성되는 불필요한 특징점을 무시할 수 있다. 또한, 모양 행렬의 사용으로 생긴 제약은 동적 그래프 검색 알고리즘으로 보상한다.

• 제어로봇시스템학회논문지
• /
• 제17권6호
• /
• pp.587-595
• /
• 2011

In this paper, we focus on the issue of automatic selection for multi-level threshold, and we greatly improve the efficiency of Otsu's method for image segmentation based on genetic algorithm. We have investigated and evaluated the performance of the Otsu and Valley-emphasis threshold methods. Based on this observation we propose a method for automatic threshold method that segments an image into more than two regions with high performance and processing in real-time. Our paper introduced new peak detection, combines with evolution algorithm using MAGA (Modified Adaptive Genetic Algorithm) and HCA (Hill Climbing Algorithm), to find the best threshold automatically, accurately, and quickly. The experimental results show that the proposed evolutionary algorithm achieves a satisfactory segmentation effect and that the processing time can be greatly reduced when the number of thresholds increases.