Deep Contour Recovery: Repairing Breaks in Detected Contours using Deep Learning

Minyoung Kyoung,Hyunbean Yi 대한전자공학회 2020 IEIE Transactions on Smart Processing & Computing Vol.9 No.5

We present a contour recovery framework based on a deep learning model to connect broken contours (breaks) produced by contour detection methods. The idea is that the convolutional neural network iteratively predicts vectors that can grow along the direction of the true contour from the end points of the breaks. For this prediction, we use residual connections training, which models continuous predictions from the previous inference. However, conventional residual connections training is prone to gradually accumulating errors at each inference step. In this work, we propose a ground truth selection algorithm and sub-iteration training to efficiently and reliably train a deep learning model. The ground truth selection extracts a small set of coordinates to represent an actual contour. The sub-iteration training creates the next input that is predicted by additional training of a network replicated from the main network. Our experimental results demonstrate that the ground truth selection creates a ground truth suitable for contour recovery. Moreover, our approach improves the performance of contour detection when applied to the results of existing representative contour detection methods.

다중 문턱치를 이용한 입술 윤곽 검출 방법

김정엽 ( Kim Jeong Yeop ) 한국정보처리학회 2020 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.9 No.12

In this paper, the method to extract lip contour by multiple threshold is proposed. Spyridonos et. el. proposed a method to extract lip contour. First step is get Q image from transform of RGB into YIQ. Second step is to find lip corner points by change point detection and split Q image into upper and lower part by corner points. The candidate lip contour can be obtained by apply threshold to Q image. From the candidate contour, feature variance is calculated and the contour with maximum variance is adopted as final contour. The feature variance ‘D’ is based on the absolute difference near the contour points. The conventional method has 3 problems. The first one is related to lip corner point. Calculation of variance depends on much skin pixels and therefore the accuracy decreases and have effect on the split for Q image. Second, there is no analysis for color systems except YIQ. YIQ is a good however, other color systems such as HVS, CIELUV, YCrCb would be considered. Final problem is related to selection of optimal contour. In selection process, they used maximum of average feature variance for the pixels near the contour points. The maximum of variance causes reduction of extracted contour compared to ground contours. To solve the first problem, the proposed method excludes some of skin pixels and got 30% performance increase. For the second problem, HSV, CIELUV, YCrCb coordinate systems are tested and found there is no relation between the conventional method and dependency to color systems. For the final problem, maximum of total sum for the feature variance is adopted rather than the maximum of average feature variance and got 46% performance increase. By combine all the solutions, the proposed method gives 2 times in accuracy and stability than conventional method.

Saliency Detection based on Global Color Distribution and Active Contour Analysis

( Zhengping Hu ),( Zhenbin Zhang ),( Zhe Sun ),( Shuhuan Zhao ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.12

In computer vision, salient object is important to extract the useful information of foreground. With active contour analysis acting as the core in this paper, we propose a bottom-up saliency detection algorithm combining with the Bayesian model and the global color distribution. Under the supports of active contour model, a more accurate foreground can be obtained as a foundation for the Bayesian model and the global color distribution. Furthermore, we establish a contour-based selection mechanism to optimize the global-color distribution, which is an effective revising approach for the Bayesian model as well. To obtain an excellent object contour, we firstly intensify the object region in the source gray-scale image by a seed-based method. The final saliency map can be detected after weighting the color distribution to the Bayesian saliency map, after both of the two components are available. The contribution of this paper is that, comparing the Harris-based convex hull algorithm, the active contour can extract a more accurate and non-convex foreground. Moreover, the global color distribution can solve the saliency-scattered drawback of Bayesian model, by the mutual complementation. According to the detected results, the final saliency maps generated with considering the global color distribution and active contour are much-improved.

Saliency Detection based on Global Color Distribution and Active Contour Analysis

Hu, Zhengping,Zhang, Zhenbin,Sun, Zhe,Zhao, Shuhuan Korean Society for Internet Information 2016 KSII Transactions on Internet and Information Syst Vol.10 No.12

In computer vision, salient object is important to extract the useful information of foreground. With active contour analysis acting as the core in this paper, we propose a bottom-up saliency detection algorithm combining with the Bayesian model and the global color distribution. Under the supports of active contour model, a more accurate foreground can be obtained as a foundation for the Bayesian model and the global color distribution. Furthermore, we establish a contour-based selection mechanism to optimize the global-color distribution, which is an effective revising approach for the Bayesian model as well. To obtain an excellent object contour, we firstly intensify the object region in the source gray-scale image by a seed-based method. The final saliency map can be detected after weighting the color distribution to the Bayesian saliency map, after both of the two components are available. The contribution of this paper is that, comparing the Harris-based convex hull algorithm, the active contour can extract a more accurate and non-convex foreground. Moreover, the global color distribution can solve the saliency-scattered drawback of Bayesian model, by the mutual complementation. According to the detected results, the final saliency maps generated with considering the global color distribution and active contour are much-improved.

Vanishing Point Detection using Reference Objects

Lee, Sangdon,Pant, Sudarshan Korea Multimedia Society 2018 멀티미디어학회논문지 Vol.21 No.2

Detection of vanishing point is a challenging task in the situations where there are several structures with straight lines. Commonly used approaches for determining vanishing points involves finding the straight lines using edge detection and Hough transform methods. This approach often fails to perform effectively when there are a lot of straight lines found. The lines not meeting at a vanishing point are considered to be noises. In such situation, finding right candidate lines for detecting vanishing points is not a simple task. This paper proposes to use reference objects for vanishing point detection. By analyzing a reference object, it identifies the contour of the object, and derives a polygon from the contour information. Then the edges of the detected polygon are used to find the vanishing points. Our experimental results show that the proposed approach can detect vanishing points with comparable accuracy to the existing edge detection based method. Our approach can also be applied effectively even to complex situations, where too many lines generated by the existing methods make it difficult to select right lines for the vanishing points.

Vanishing Point Detection using Reference Objects

이상돈,Sudarshan Pant 한국멀티미디어학회 2018 멀티미디어학회논문지 Vol.21 No.2

Detection of vanishing point is a challenging task in the situations where there are several structures with straight lines. Commonly used approaches for determining vanishing points involves finding the straight lines using edge detection and Hough transform methods. This approach often fails to perform effectively when there are a lot of straight lines found. The lines not meeting at a vanishing point are considered to be noises. In such situation, finding right candidate lines for detecting vanishing points is not a simple task. This paper proposes to use reference objects for vanishing point detection. By analyzing a reference object, it identifies the contour of the object, and derives a polygon from the contour information. Then the edges of the detected polygon are used to find the vanishing points. Our experimental results show that the proposed approach can detect vanishing points with comparable accuracy to the existing edge detection based method. Our approach can also be applied effectively even to complex situations, where too many lines generated by the existing methods make it difficult to select right lines for the vanishing points.

활성 윤곽선 모델을 이용한 얼굴 경계선 추출

장재식,김은이,김항준,Chang Jae Sik,Kim Eun Yi,Kim Hang Joon 대한전자공학회 2005 電子工學會論文誌-CI (Computer and Information) Vol.42 No.1

본 논문에서는 복잡한 환경에서 정확한 얼굴영역의 경계를 추출하기 위한 활성 윤곽선 모델(Active Contour Model)을 제안한다. 제안된 모델에서 윤곽선은 레벨 함수 φ의 제로 레벨 집합으로 표현되고, 레벨 집합의 편미분 방정식을 통해 진화된다. 이 때, 제안된 모델에서는 윤곽선의 진화와 종교를 위해 2차원 가우시안 모델로 표현되는 피부색 정보를 이용한다. 이를 통해 잡음 및 다양한 포즈를 가지는 복잡한 영상에서도 정확한 얼굴 경계선을 얻을 수 있는 강건한 추출 방법이 구현된다. 제안된 방법의 유효성을 평가하기 위해서 다양한 영상에 대해서 실험이 이루어졌으며, 그 결과를 geodesic 활성 윤곽선 모델의 결과와 비교하였다. 실험결과는 제안된 방법의 보다 나은 성능을 보여준다. This paper presents an active contour model for extracting accurate facial regions in complex environments. In the model, a contour is represented by a zero level set of level function φ, and evolved via level set partial differential equations. Then, unlike general active contours, skin color information that is represented by 2D Gaussian model is used for evolving and slopping a curve, which allows the proposed method to be robust to noise and varying pose. To assess the effectiveness of the proposed method it was tested with several natural scenes, and the results were compared with those of geodesic active contours. Experimental results demonstrate the superior performance of the proposed method.

A Novel Flame Edge Detection Algorithm via a Novel Active Contour Model

Wanli Feng,Ying Li,Shangbing Gao,Yunyang Yan,Jianxun Xue 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.9

Flame edge detection from color images is a challenging research area recently. In this paper, an extension of active contour model is proposed by adding the two information types to both internal and external energy terms. Therefore, the combination of these two forces allows for flexible initialization of the contours. This energy is then incorporated into a level set formulation with a level set regularization term that is necessary for accurate computation in the corresponding level set method. Edge extraction of different flame images using C-V model and the classical edge detection operators are compared and analyzed. Experimental results show that the existing methods do not emphasize the continuity and clarity of the flame and fire edges while the proposed method identifies the continuous and clear edges of the flame fire.

3차원 혈관 모델에서 협착 및 팽창 영역 탐색 방안

박상진(Sang-Jin Park),김재성(Jae-Sung Kim),박형준(Hyungjun Park) 한국산학기술학회 2018 한국산학기술학회논문지 Vol.19 No.1

혈관 질환 검사는 일반적으로 혈관 조영술(angiography)과 CT 혈관 조영술(CT angiography) 등을 통해 이루어지며, 대부분 검사자의 육안을 통한 주관적 판단에 의존하여 진단이 이루어진다. 본 논문에서는 의료영상으로부터 재구성된 3차원 혈관 내벽 모델로부터 대표적 혈관질환에 해당하는 협착과 팽창 질환 의심 영역을 탐색하는 방안을 제안한다. 먼저, 의료영상에서 재구성된 3차원 혈관 내벽 모델로부터 혈관에 대한 골격 곡선(curve skeletons)과 외곽선(contours)을 생성하고, 생성된 골격 곡선을 가지 단위로 분할한 후, 가지에 속하는 각 노드에 대한 외곽선의 면적을 계산한다. 그런 다음, 계산된 외곽선들의 면적에 대해 평균 면적 및 최대/최소 면적, 그리고 인접 노드들 간의 외곽선 면적 차이를 고려하여 협착 및 팽창 질환의심 영역에 해당하는 노드들을 탐색한다. 다음으로 탐색된 의심 영역들을 적절하게 시각화함으로써 혈관질환의 진단을 지 원한다. 제안된 방안을 구현하여 몇 가지 3D 인체 혈관모델에 적용한 결과 질환 의심 영역이 잘 찾아짐을 확인하였다. 이를 통해 제안된 방안의 유용성을 보인다. Angiography and CT angiography are used widely for the examination of vascular diseases, but the diagnosis of such diseases is made mostly by the subjective judgment of the inspector. This paper proposes a method for detecting the suspicious regions of stenosis and aneurysm in the inner surfaces of 3D blood vessel models reconstructed from medical images. Initially, the 3D curve-skeletons of the blood vessel models and the contours at the nodes of the curve-skeletons were generated. Next, the 3D curve-skeletons were divided into a set of branches and the areas of normal contours of nodes located in each branch were calculated. The nodes whose contours contain suspicious regions were detected by taking into account the average area, maximum and minimum areas, and the area difference between the adjacent normal contours. The diagnosis of stenosis and aneurysm can be supported by properly visualizing the suspicious regions detected. The suspicious regions of the disease were identified by implementing and testing it using several data sets of human blood vessels, highlighting the usefulness of the proposed method.

Interactive Typography System using Combined Corner and Contour Detection

Lim, Sooyeon,Kim, Sangwook The Korea Contents Association 2017 International Journal of Contents Vol.13 No.1

Interactive Typography is a process where a user communicates by interacting with text and a moving factor. This research covers interactive typography using real-time response to a user's gesture. In order to form a language-independent system, preprocessing of entered text data presents image data. This preprocessing is followed by recognizing the image data and the setting interaction points. This is done using computer vision technology such as the Harris corner detector and contour detection. User interaction is achieved using skeleton information tracked by a depth camera. By synchronizing the user's skeleton information acquired by Kinect (a depth camera,) and the typography components (interaction points), all user gestures are linked with the typography in real time. An experiment was conducted, in both English and Korean, where users showed an 81% satisfaction level using an interactive typography system where text components showed discrete movements in accordance with the users' gestures. Through this experiment, it was possible to ascertain that sensibility varied depending on the size and the speed of the text and interactive alteration. The results show that interactive typography can potentially be an accurate communication tool, and not merely a uniform text transmission system.