• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.2
• /
• pp.157-165
• /
• 2009

Existing methods for image segmentation using diffusion can't preserve contour information, or noises with high gradients become more salient as the umber of times of the diffusion increases, resulting in over-segmentation when applied to watershed. This thesis proposes a method for image segmentation by applying morphology operation together with robust anisotropic diffusion. For an input image, transformed into LUV color space, closing by reconstruction and anisotropic diffusion are applied to obtain a simplified image which preserves contour information with noises removed. With gradients computed from this simplifed images, watershed algorithm is applied. Experiments show that color images are segmented very effectively without over-segmentation.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.5
• /
• pp.735-740
• /
• 2005

Video segmentation is an essential part in region-based video coding and any other fields of the video processing. Among lots of methods proposed so far, the watershed method in which the region growing is performed for the gradient image can produce well-partitioned regions globally without any influence on local noise and extracts accurate boundaries, But, it generates a great number of small regions, which we call over segmentation problem. Therefore we proposes that adaptive trimmed mean filter for resolving the over segmentation of image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.891-894
• /
• 2004

This paper proposes an improved image segmentation algorithm by the watershed algorithm based on the local adaptive threshold on local minima search and the fixing threshold on label allocation. The previous watershed algorithm generates the problem of over-segmentation. The over-segmentation makes the boundary in the inaccuracy region by occurring around the object. In order to solve those problems we quantize the input color image by the vector quantization, remove noise and find the gradient image. We sorted local minima applying the local adaptive threshold on local minima search of the input color image. The simulation results show that the proposed algorithm controls over-segmentation and makes the fine boundary around segmented region applying the fixing threshold based on sorted local minima on label allocation.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.431-434
• /
• 2003

In this paper, we propose an efficient method not only f3r producing accurate region segmentation, solving the over-segmentation problem of watershed algorithm but also f3r reducing post-processing time by reducing computation loads. Through this proposed method, region segmentation of neighboring objects and discrimination of similar intensities were effectively obtained. Input image of watershed algorithm has used the derivative-based detectors such as Sobel and Canny. But proposed method uses the pixels-similarity-based detector, that is, SUSAN. By adopting this proposed method, we can reduce the noise problem and solve the problem of over-segmentation and not lose the edge information of objects. We also propose Zero-Crossing SUSAN. With Zero-Crossing SUSAN, the edge localization, times and computation loads can be improved over those obtained from existing SUSAN

• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.21-29
• /
• 2007

Anisotropic diffusion is one of the widely used techniques in the field of image segmentation. In the conventional anisotropic diffusion [1]-[6], usually 4-neighborhood directions are used: north, south, west and east, except the image diagonal directions, which results in the loss of image details and causes false contours. Existing methods for image segmentation using conventional anisotroplc diffusion can't preserve contour information, or noises with high gradients become more salient as the umber of times of the diffusion increases, resulting in over-segmentation when applied to watershed. In this paper, to overcome the shortcoming of the conventional anisotropic diffusion method, a new arusotropic diffusion method based on diagonal edges is proposed. And a method of watershed segmentation is applied to the proposed method. Experimental results show that the process time of the proposed method including diagonal edges over conventional methods can be up to 2 times faster and the Circle image quality improvement can be better up to $0.45{\sim}2.33(dB)$. Experiments also show that images are segmented very effectively without over segmentation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.165-173
• /
• 2004

Since the conventional image segmentation methods using mathematical morphology tend to yield over-segmented results, they normally need postprocess which merges small regions to obtain larger ones. To solve this over-segmentation problem without postprocess had to increase size of structuring element used marker extraction. As size of structuring element is very large, edge of region segments incorrectly. Therefore, this paper selectively applies structuring element of mathematical morphology to improve performance of image segmentation and classifies input image into texture region, edge region and simple region using averaged local variance and image gradient. Proposed image segmentation method removes the cause for over-segmentation of image as selectively applies size of structuring element to each region. Simulation results show that proposed method correctly segment for pixel region of similar luminance value and more correctly search texture region and edge region than conventional methods.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2345-2358
• /
• 2022

This paper presents a method to generate stained-glass animation from video inputs. The method initially segments an input video volume into several regions considered as fragments of glass by mean-shift segmentation. However, the segmentation predominantly results in over-segmentation, causing several tiny segments in a highly textured area. In practice, assembling significantly tiny or large glass fragments is avoided to ensure architectural stability in stained glass manufacturing. Therefore, we use low-frequency components in the segmentation to prevent over-segmentation and subdivide segmented regions that are oversized. The subdividing must be coherent between adjacent frames to prevent temporal artefacts, such as flickering and the shower door effect. To temporally subdivide regions coherently, we obtain a panoramic image from the segmented regions in input frames, subdivide it using a weighted Voronoi diagram, and thereafter project the subdivided regions onto the input frames. To render stained glass fragment for each coherent region, we determine the optimal match glass fragment for the region from a dataset consisting of real stained-glass fragment images and transfer its color and texture to the region. Finally, applying lead came at the boundary of the regions in each frame yields temporally coherent stained-glass animation.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.923-928
• /
• 2003

A severe drawback to the calculation of watershed images is over segmentation. Relevant object contours are lost in a sea of irrelevant ones. This is partly caused by random noise, inherent to a data, which gives rise to additional local minima, such that many catchments basins are further subdivided. Proposed watershed image segmentation algorithm is iteratively merging neighboring regions that have similar gray level distributions, to restore image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.307-310
• /
• 2009

In this paper, we present a robust shape matching approach based on bottom-up segmentation. We show how over-segmentation results can be used to overcome both ambiguity of contour matching and occlusion. To measure the shape difference between a template and the object in the input, we use oriented chamfer matching. However, in contrast to previous work, we eliminate the affection of the background clutters before calculating the shape differences using over-segmentation results. By this method, we can increase the matching cost interval between true matching and false matching, which gives reliable results. Finally, our experiments also demonstrate that our method is robust despite the presence of occlusion.