• Journal of Multimedia Information System
• /
• 제7권3호
• /
• pp.197-204
• /
• 2020

Superpixel methods are widely used in the preprocessing stage as a method to reduce computational complexity by simplifying images while maintaining the characteristics of the images in the computer vision applications. It is common to generate superpixels of similar size and shape based on the pixel values rather than considering the characteristics of the image. In this paper, we propose a method to control the sizes and shapes of generated superpixels, considering the contents of an image. The proposed method consists of two steps. The first step is to over-segment an image so that the boundary information of the image is well preserved. In the second step, generated superpixels are merged based on similarity to produce the target number of superpixels, where the shapes of superpixels are controlled by limiting the maximum size and the proposed roundness metric. Experimental results show that the proposed method preserves the boundaries of the objects in an image more accurately than the existing method.

• 한국정보기술학회논문지
• /
• 제16권12호
• /
• pp.85-92
• /
• 2018

복잡한 영상처리 알고리즘을 사용할 때 계산량을 줄이기 위해 슈퍼픽셀을 사용한다. 슈퍼픽셀은 특성이 유사한 픽셀들을 군집화하여 하나의 그룹으로 만드는 방법이다. 슈퍼픽셀은 영상처리의 전단계로 사용되기 때문에 빠르게 생성할 수 있어야 하고 영상의 에지 성분들을 잘 보존하여야 한다. 본 논문에서는 에지 성분을 잘 보존하면서도 계산량이 많지 않은 슈퍼픽셀 생성 방법을 제안한다. 제안하는 방법에서는 먼저 기존의 k-mean 방법을 이용하여 영상의 슈퍼픽셀을 충분히 생성하고, 생성된 슈퍼픽셀들을 분석하여 유사한 슈퍼픽셀을 병합하는 방식으로 최종 슈퍼픽셀을 생성한다. 슈퍼픽셀을 병합할 때는 슈퍼픽셀에 대해서만 유사도를 측정하기 때문에 추가되는 계산량은 많지 않다. 실험 결과는 제안하는 방법으로 생성된 슈퍼픽셀이 기존 방법에 의해 생성된 슈퍼픽셀에 비해 보다 정확하게 에지 성분들을 보존하는 것을 보여준다.

• 한국정보통신학회논문지
• /
• 제23권12호
• /
• pp.1520-1527
• /
• 2019

컴퓨터 비전 분야에서 영상의 특성을 유지하면서 영상을 간소화하여 계산량을 줄이는 방법으로 전처리 단계에서 슈퍼픽셀 방법이 많이 사용되고 있다. 하지만 슈퍼픽셀 단계에서는 영상의 특성을 고려하는 것 보다는 화소의 값을 기준으로 일정한 크기와 형태의 슈퍼픽셀을 생성하는 것이 일반적이다. 본 논문에서는 응용에 맞게 영상의 특성을 고려하여 슈퍼픽셀을 생성할 수 있는 방법을 제안한다. 제안하는 방법은 두 단계로 이루어지며, 첫 번째 단계에서 영상을 과분할 하여 영상의 경계 정보들이 잘 보존되게 한다. 두 번째 단계에서는 과분할 된 슈퍼픽셀들을 유사도를 기준으로 병합하여 원하는 개수의 슈퍼픽셀을 생성한다. 이때 슈퍼픽셀의 최대 크기를 제한함으로써 슈퍼픽셀의 형태를 제어한다. 실험 결과는 제안하는 방법으로 생성된 슈퍼픽셀이 기존 방법에 의해 생성된 슈퍼픽셀 보다 정확하게 경계 정보를 보존하는 것을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권7호
• /
• pp.2400-2419
• /
• 2014

Pre-segmented pixels can reduce the difficulty of segmentation and promote the segmentation performance. This paper proposes a novel segmentation method based on merging texture superpixels by computing inner similarity. Firstly, we design a set of Gabor filters to compute the amplitude responses of original image and compute the texture map by a salience model. Secondly, we employ the simple clustering to extract superpixles by affinity of color, coordinates and texture map. Then, we design a normalized histograms descriptor for superpixels integrated color and texture information of inner pixels. To obtain the final segmentation result, all adjacent superpixels are merged by the homogeneity comparison of normalized color-texture features until the stop criteria is satisfied. The experiments are conducted on natural scene images and synthesis texture images demonstrate that the proposed segmentation algorithm can achieve ideal segmentation on complex texture regions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5015-5038
• /
• 2018

In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

• 디지털산업정보학회논문지
• /
• 제11권4호
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.

• 한국멀티미디어학회논문지
• /
• 제15권6호
• /
• pp.761-769
• /
• 2012

본 논문에서는 슈퍼픽셀과 FCM을 이용한 클러스터 초기값 설정방법과 이를 사용한 칼라영상분할을 연구한다. 클러스터링을 이용한 대표적인 칼라영상분할 방법으로 Fuzzy C-menas (FCM) 알고리즘을 많이 사용한다. FCM은 하나의 데이터가 각 클러스터에 서로 다른 소속도를 갖도록 한다. 그러나 FCM은 초기값 설정에 따라 국부적인 수렴문제가 발생한다. 따라서 초기값 설정문제는 매우 중요한데 본 연구에서는 슈퍼픽셀을 이용하여 클러스터의 초기값을 구하는 방법을 제안한다. 슈퍼픽셀은 원 영상에서 특성이 비슷한 화소들의 묶음으로 표현되는데 먼저 원 영상으로부터 슈퍼픽셀을 구하고 이를 $La^*b^*$ 칼라특징공간에 투영하여 클러스터 초기값을 구한다. 제안방법에서 슈퍼픽셀의 수는 원영상의 화소 수보다 일반적으로 매우 적어서 클러스터 초기값 설정을 위한 고속처리가 가능하다. 제안된 알고리즘의 성능평가를 위해 다양한 칼라영상을 사용하여 컴퓨터 모의실험을 수행하였으며 실험결과 제안방법이 기존방법에 비해 영상분할 성능이 우수함을 알 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.649-651
• /
• 2012

본 논문에서는 슈퍼픽셀특성을 이용한 칼라영상분할을 연구한다. 슈퍼픽셀은 특성이 비슷한 인접화소들을 묶어서 하나의 큰 화소로 취급하는 것으로 고속영상처리 및 영상인식을 위해 사용될 수 있다. 본 연구에서는 슈퍼픽셀특성이 비교적 우수한 $La^*b^*$ 칼라특징공간에서 슈퍼픽셀을 구하고 클러스터링 및 기울기기반 분할 알고리즘을 적용한 영상분할을 연구한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4968-4986
• /
• 2017

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1712-1731
• /
• 2016

In this paper, we propose a novel saliency detection framework via multiple random walks (MRW) which simulate multiple agents on a graph simultaneously. In the MRW system, two agents, which represent the seeds of background and foreground, traverse the graph according to a transition matrix, and interact with each other to achieve a state of equilibrium. The proposed algorithm is divided into three steps. First, an initial segmentation is performed to partition an input image into homogeneous regions (i.e., superpixels) for saliency computation. Based on the regions of image, we construct a graph that the nodes correspond to the superpixels in the image, and the edges between neighboring nodes represent the similarities of the corresponding superpixels. Second, to generate the seeds of background, we first filter out one of the four boundaries that most unlikely belong to the background. The superpixels on each of the three remaining sides of the image will be labeled as the seeds of background. To generate the seeds of foreground, we utilize the center prior that foreground objects tend to appear near the image center. In last step, the seeds of foreground and background are treated as two different agents in multiple random walkers to complete the process of salient object detection. Experimental results on three benchmark databases demonstrate the proposed method performs well when it against the state-of-the-art methods in terms of accuracy and robustness.