• The Transactions of the Korea Information Processing Society
• /
• v.4 no.9
• /
• pp.2197-2207
• /
• 1997

In this paper, we propose a video data segmentation method using edge and color distribution of video frames and also develop a video browser by using the proposed algorithm. To segment a video, we use a 644-bin HSV color histogram and the edge information which generated with automatic threshold method. We consider scene's characteristics by using positions and colo distributions of object in each frame. We develop a hierarchical and a shot-based browser for video browsing. We also show that our proposed method is less sensitive to light effects and more robust to motion effects than previous ones like a histogram-based method by testing with various video data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.225-228
• /
• 2022

본 논문에서는 의미적 유사도 기반의 장면 분할 방법을 제안한다. 이 방법은 의미적 접근을 통해 기존 연구에서 가졌던 한계를 극복하고 정확한 장면 분할이 가능할 것으로 기대한다. 의미적 유사도 비교를 Class 종류 비교, Class별 객체의 개수 비교, 샷 간의 Histogram비교, 객체의 관심영역(ROI) Histogram비교 총 4가지 규칙으로 정의했고 이때 도출된 4가지 유사도는 전처리를 거쳐 종합 유사도를 계산한다. 또한 의미적 접근을 통해 연속되는 Shot의 유사도를 비교하고 기준값에 따라 Shot을 묶어서 최종적으로 의미적 유사도(Semantic Similarity)에 기반한 장면의 경계(Scene Boundary) 분할 방법을 제시한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11C
• /
• pp.1076-1082
• /
• 2005

Recently, there have been much efforts in the image segmentation using morphological approach. Among them, the watershed algorithm is one of powerful tools which can take advantages of both of the conventional edge-based segmentation and region-based segmentation. The concept of watershed is based on topographic analogy. But, its high sensitivity to noise yields a very large number of resulting segmented regions which leads to oversegmentation. So we suggest the restricted waterfall algorithm which reduce the oversegmentation by eliminate not only local minima but also local maxima. As a result, the restricted waterfall algorithm has a good segmented image than the other methods, and has a better binary image than the histogram thresholding method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• Proceedings of the KIPE Conference
• /
• 2001.10a
• /
• pp.104-108
• /
• 2001

In this paper, the 3-D measurement method of moving object with a laser and one camera system for image processing method is presented. The method of segmentation image in conventional method, the error are generated by the threshold values. In this paper, to improve these problem for segmentation image, the calculation of weighting factor using brightness distribution by histogram of stored images are proposed. Therefore the image erosion and spread are improved, the correct and reliable informations can be measured. In this paper, the system of 3-D extracting information using the proposed algorithm can be applied to manufactory automation, building automation, security guard system, and detecting information system for all of the industry areas.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1164-1171
• /
• 2015

The edge preserving method is important for image storage and geometric transformation. In this paper, we propose a new edge preserving method using HOG-Guide filter for image segmentation. In our approach, we extract edge information using gradient histogram to set HOG guide line. Then, we use HOG guide line to smooth image. With two to four iterations of smoothing operations, we finally obtain desirable edge preserved image. Our experimental results showed good performances showing that our proposed method is better than other methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.1 no.2
• /
• pp.105-111
• /
• 1995

This paper proposes a segmentation algorithm using gray-level discontinuity and surface reflectance ratio of input images obtained under different illumination conditions. Each image is divided by a certain number of subregions based on the thresholds. The thresholds are determined using the histogram of fusion image which is obtained by ANDing the multiple input images. The subregions of images are projected on the eigenspace where their bases are the major eigenvectors of image matrix. Points in the eigenspace are classified into two clusters. Images associated with the bigger cluster are fused by revised ANDing to form a combined edge image. Missing edges are detected using surface reflectance ration and chain code. The proposed algorithm obtains more accurate edge information and allows to more efficiently recognize the environment under various illumination conditions.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1461-1471
• /
• 2021

This paper presents a light exposure correction algorithm for less pleasant images, acquired with a light metering failure. Since conventional tone mapping and gamma correction methods adopt a function mapping with the same range of input and output, the results are pleasurable for almost symmetric distributions to their intensity average. However, their corrections gave insufficient outputs for asymmetric cases at either bright or dark regions. Also, histogram modification approaches show good results on varied pattern images, but these generate unintentional noises at flat regions because of the compulsive shift of the intensity distribution. Therefore, in order to sufficient corrections for both bright and dark areas, the proposed algorithm calculates the gamma coefficients using primary parameters extracted from the global distribution. And the fusion weights are adaptively determined with complementary parameters, considering the classification information of a binary segmentation. As the result, the proposed algorithm can obtain a good output about both the symmetric and the asymmetric distribution images even with severe exposure values.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.1
• /
• pp.1-8
• /
• 2003

Various methods have been studying to maintain and apply the multimedia inform abruptly increasing over all social fields, in recent years. For retrieval of still images, we is implemented content-based image retrieval system in this paper that make possible to retrieve similar objects from image database after segmenting query object from background if user request query. Query image is processed median filtering to remove noise first and then object edge is detected it by canny edge detection. And query object is segmented from background by using convex hull. Similarity value can be obtained by means of histogram intersection with database image after securing color histogram from segmented image. Also segmented image is processed gray convert and wavelet transform to extract spacial gray distribution and texture feature. After that, Similarity value can be obtained by means of banded autocorrelogram and energy. Final similar image can be retrieved by adding upper similarity values that it make possible to not only robust in background but also better correct object retrieval by using object segmentation method.