• 대한전자공학회논문지TE
• /
• 제37권3호
• /
• pp.45-52
• /
• 2000

본 연구에서는 인체 상반신영상에서 얼굴부위를 분할하기 위한 영상분할 알고리즘을 제안하였다. 제안한 알고리즘은 HWT를 적용하여 영상의 경계를 이루는 차분영상인 고주파대역과 평균영상인 저주파대역으로 분리하고, 저주파대역에서 고립점과 돌출부위, 경계중복점을 제거하였다. 또한 제안한 경계검출 알고리즘으로 경계를 검출하고 단순화시켰으며, 1픽셀 단위의 세선화과정을 통하여 경계를 선명하게 하였다. 그리고 제안 한 폐곡선추적 알고리즘으로 얼굴부위 경계만을 추출한 뒤, 마스크를 구성하고 원영상과의 정합을 통하여 얼굴부위분할을 하였다. 제안한 알고리즘을 적용하여 얼굴부위 분할실험을 실행한 결과 95.88%의 분할값을 갖는 얼굴분할이 이루어졌다.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.59-71
• /
• 2012

Since mobile phones are used as common communication devices, their applications are increasingly important to human's life. Using smart-phones camera to collect daily life environment's information is one of targets for many applications such as text recognition, object recognition or context awareness. Studies have been conducted to provide important information through the recognition of texts, which are artificially or naturally included in images and movies acquired from mobile phones. In this study, a character segmentation method that improves character-recognition accuracy in images obtained from mobile phone cameras is proposed. The proposed method first classifies texts in a given image to printed letters and handwritten letters since segmentation approaches for them are different. For printed letters, rough segmentation process is conducted, then the segmented regions are integrated, deleted, and re-segmented. Segmentation for the handwritten letters is performed after skews are corrected and the characters are classified by integrating them. The experimental result shows our method achieves a successful performance for both printed and handwritten letters as 95.9% and 84.7%, respectively.

• International Journal of CAD/CAM
• /
• 제7권1호
• /
• pp.31-40
• /
• 2007

Reverse engineering of reliefs aims to turn an existing relief superimposed on an underlying surface into a geometric model which may be applied to a different base surface. Steps in this process include segmenting the relief from the background, and describing it as an offset height field relative to the underlying surface. We have previously considered relief segmentation using a geometric snake. Here, we show how to use this initial segmentation to estimate the background surface lying under the relief, which can be used (i) to refine the segmentation and (ii) to express the relief as an offset field. Our approach fits a B-spline surface patch to the measured background data surrounding the relief, while tension terms ensure this background surface smoothly continues underneath the relief where there are no measured background data points to fit. After making an initial estimate of relief offset height everywhere within the patch, we use a support vector machine to refine the segmentation. Tests demonstrate that this approach can accurately model the background surface where it underlies the relief, providing more accurate segmentation, as well as relief height field estimation. In particular, this approach provides significant improvements for relief concavities with narrow mouths and can segment reliefs with small internal holes.

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.201-210
• /
• 2021

In Korean medicine, tongue diagnosis is one of the important diagnostic methods for diagnosing abnormalities in the body. Representative features that are used in the tongue diagnosis include color, shape, texture, cracks, and tooth marks. When diagnosing a patient through these features, the diagnosis criteria may be different for each oriental medical doctor, and even the same person may have different diagnosis results depending on time and work environment. In order to overcome this problem, recent studies to automate and standardize tongue diagnosis using machine learning are continuing and the basic process of such a machine learning-based tongue diagnosis system is tongue segmentation. In this paper, image data is augmented based on the main tongue features, and backbones of various famous deep learning architecture models are used for automatic tongue segmentation. The experimental results show that the proposed augmentation technique improves the accuracy of tongue segmentation, and that automatic tongue segmentation can be performed with a high accuracy of 99.12%.

• ETRI Journal
• /
• 제45권5호
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• 전자공학회논문지
• /
• 제50권8호
• /
• pp.225-231
• /
• 2013

의료영상분할은 다양한 의료영상처리를 수행하기에 앞서 먼저 수행되어야 하는 영상처리 기술이다. 그래서 빠르고 정확한 의료영상분할이 요구되고 있으며 다양한 의료영상분할 방법이 연구되고 있다. 의료영상에는 특성이 유사한 다양한 장기가 존재하기 때문에 분할영역의 정확한 판단이 필요하다. 그러나 의료영상은 장기의 일부가 작게 촬영되는 경우가 발생된다. 이 경우에는 분할영역을 판단하기 위한 정보가 부족하게 되며 그 결과 분할과정에서 분할영역이 제거된다. 본 논문에서는 볼륨 데이터와 선형 방정식을 이용하여 작은 영역에서의 분할결과를 개선하였다. 제안한 방법의 성능을 확인하기 위하여 흉부 CT 영상의 폐 분할을 수행하였다. 실험 결과, 의료영상의 분할 정확도는 0.978에서 0.981로 표준편차는 0.281에서 0.187로 개선되는 것을 확인하였다.

• 정보처리학회논문지B
• /
• 제12B권3호
• /
• pp.239-246
• /
• 2005

생물학자가 단백질을 검색하고 분석하기 위해서는 2차원 젤 전기영동(2DGE : Two Dimensional Gel Electrophoresis) 실험을 해야 한다. 실험 결과는 2차원 영상이 생성된다. 2차원 영상에서 단백질 반점의 패턴 분석을 위해 2차원 젤 영상에 펼쳐진 단백질 반점들을 영상처리를 통해 분할하고, 대조 그룹의 단백질 패턴과 비교분석을 통해 밝히고자하는 단백질 반점을 찾아내야 한다. 단백질 반점을 분할하는 알고리즘에 있어서 기존에는 가우시안 함수를 적용하였지만, 최근 들어 형태학 분리개념에 의한 Watersheds 영역기반 분할(Watersheds region-based segmentation) 알고리즘을 활용하고 있다. 그러나 Watersheds 영역기반 분할 알고리즘은 크기가 큰 영상에서 원하는 영역을 신속하게 분할한다는 장점이 있지만, 영상 화소의 그레이 값이 연속적인 경우 실제 반점의 개수 에 비해 과다분할(over-segmentation)되거나 과소분할(under-segmentation)의 문제점을 안고 있다. 이는 마커(marker) 포인트의 설정에 의해 어느 정도 해결할 수 있지만 병합(merge)과 분할(split) 과정을 반복해야 한다. 본 논문은 Watersheds 기반 계층적 이진화 기법을 적용하여 마커 드리븐 Watersheds 영상분할의 문제점을 해결하고자 한다.

• 센서학회지
• /
• 제6권2호
• /
• pp.123-130
• /
• 1997

이 논문은 다음과 같은 두가지 요소로 구성되는 독창적인 stereo vision system을 논술한다. declivity라는 새로운 개념을 도입한 자동선택 영상 분할처리 (self-adaptive image segmentation process) 와 자동선택 결정변수 (self-adaptive decision parameters) 를 응용하여 설계된 신속한 stereo matching algorithm. 현재, 실내 image의 depth map을 완성하는데 SUN-IPX 에서 3sec가 소요되나 연구중인 DSP Chip의 조합은 이 시간을 1초 이하로 단축시킬 수 있을 것이다.

• Nuclear Engineering and Technology
• /
• 제56권5호
• /
• pp.1733-1737
• /
• 2024

In order to specify the location of the scintillation pixel that interacted with gamma rays in the positron emission tomography (PET) detector, conventionally, after acquiring a flood image, the location of interaction between the scintillation pixel and gamma ray could be specified through a pixel-segmentation process. In this study, the experimentally acquired signal was specified as the location of the scintillation pixel directly, without any conversion process, through the simulation data and the deep learning algorithm. To evaluate the accuracy of the specification of the scintillation pixel location through deep learning, a comparative analysis with experimental data through pixel segmentation was performed. In the same way as in the experiment, a detector was configured on the simulation, a model was built using the acquired data through deep learning, and the location was specified by applying the experimental data to the built model. Accuracy was calculated through comparative analysis between the specified location and the location obtained through the segmentation process. As a result, it showed excellent accuracy of about 85 %. When this method is applied to a PET detector, the position of the scintillation pixel of the detector can be specified simply and conveniently, without additional work.