• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.737-747
• /
• 2019

Shape description is an important and fundamental issue in content-based image retrieval (CBIR), and a number of shape description methods have been reported in the literature. For shape description, both global information and local contour variations play important roles. In this paper a new included-angular ternary pattern (IATP) based shape descriptor is proposed for shape image retrieval. For each point on the shape contour, IATP is derived from its neighbor points, and IATP has good properties for shape description. IATP is intrinsically invariant to rotation, translation and scaling. To enhance the description capability, multiscale IATP histogram is presented to describe both local and global information of shape. Then multiscale IATP histogram is combined with included-angular histogram for efficient shape retrieval. In the matching stage, cosine distance is used to measure shape features' similarity. Image retrieval experiments are conducted on the standard MPEG-7 shape database and Swedish leaf database. And the shape image retrieval performance of the proposed method is compared with other shape descriptors using the standard evaluation method. The experimental results of shape retrieval indicate that the proposed method reaches higher precision at the same recall value compared with other description method.

• 한국기계가공학회지
• /
• 제13권1호
• /
• pp.30-38
• /
• 2014

The purpose of this study is to build and manage environment models with line segments from sonar range data on obstacles in unknown and varied environments. The proposed method therefore employs a two-stage data-transform process in order to extract environmental line segments from range data on obstacles. In the first stage, the occupancy grid extracted from the range data is accumulated to form a two-dimensional local histogram grid. In the second stage, a line histogram extracted from a local histogram grid is based on a Hough transform, and matching serves as a means of comparing each of the segments on a global line segments map against the line segments to detect the degree of similarity in the overlap, orientation, and arrangement. Each of these tests is formulated by comparing one of the parameters in the segment representation. After the tests, new line segments can be found at maximum-density cells in the line histogram, and they are composed onto the global line segment map. The proposed technique is demonstrated in experiments in an indoor environment.

• 전자공학회논문지S
• /
• 제36S권12호
• /
• pp.58-66
• /
• 1999

본 논문에서는 영상의 콘트래스트 (이하 대비)를 높이기 위한 개선된 히스토그램 등화 기법을 제안한다. 기존의 글로벌 히스토그램 등화 기법은 간단하나 영상의 각 부분에 맞는 충분한 대비를 얻을 수 없다. 이를 해결하기 위한 블록 중첩 서브블록 히스토그램 등화 기법은, 높은 대비를 얻을 수 있으나 그 계산량이 엄청나다는 단점이 있다. 본 논문에서는 두 방법의 장점을 모두 얻기 위한 부분 중첩 서브블록 히스토그램 등화기법(Partially Overlapped Sub-block Histogram Equalization : POSHE)을 제안한다. 이 방법에서는 서브블록들의 히스토그램 등화 함수를 저역 통과 필터 형태의 마스크를 이용하여 얻음으로써 그 계산량을 블록 중첩 서브블록 히스토그램 등화에 비해 크게 줄여서 훨씬 빠른 시간에 블록 중첩 서브블록 히스토그램 등화 기법과 비슷한 정도의 높은 대비를 얻을 수 있게 되었다.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1453-1461
• /
• 2015

Since digital images and videos are rapidly increasing in the internet with the spread of mobile computers and smartphones, research on image retrieval has gained tremendous momentum. Color, shape, and texture are major features used in image retrieval. Especially, color information has been widely used in image retrieval, because it is robust in translation, rotation, and a small change of camera view. This paper proposes a new method for histogram refinement based on local color difference. Firstly, the proposed method converts a RGB color image into a HSV color image. Secondly, it reduces the size of color space from 256³ to 32. It classifies pixels in the 32-color image into three groups according to the color difference between a central pixel and its neighbors in a 3x3 local region. Finally, it makes a color difference vector(CDV) representing three refined color histograms, then image retrieval is performed by the CDV matching. The experimental results using public image database show that the proposed method has higher retrieval accuracy than other conventional ones. They also show that the proposed method can be effectively applied to search low resolution images such as thumbnail images.

• International Journal of Contents
• /
• 제8권1호
• /
• pp.30-38
• /
• 2012

Text extraction and binarization are the important pre-processing steps for text recognition. The performance of text binarization strongly related to the accuracy of recognition stage. In our proposed method, the first stage based on line detection and shape feature analysis applied to locate the position of a business card and detect the shape from the complex environment. In the second stage, several local regions contained the possible text components are separated based on the projection histogram. In each local region, the pixels grouped into several connected components based on the connected component labeling and projection histogram. Then, classify each connect component into text region and reject the non-text region based on the feature information analysis such as size of connected component and stroke width estimation.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1603-1613
• /
• 1995

The goal of enhancement is to improve the perceptual aspect and visual appearance of images for human viewers. The objectives of image enhancement vary according to its specific application and an image enhancement algorithms used for a specific objective may not be accepted in some other applications. In this paper we review some of conventional enhancement techniques, such as global histogram equalization(GHE), local histogram equalization(LHE), clipped histogram equalization(CHE). We also describe some modified version of these algorithms. The proposed method is to detect detail information. We distinquish edge from nonedge and apply histigram equalization respectively. Simulation results demonstrate the performance of the proposed method for medical image.

• 한국컴퓨터정보학회논문지
• /
• 제21권11호
• /
• pp.23-30
• /
• 2016

In this paper, we propose an adaptive histogram projection technique for dynamic range compression and an efficient detail enhancement method which is enhancing strong edge while reducing noise. First, The high dynamic range image is divided into low-pass component and high-pass component by applying 'guided image filtering'. After applying 'guided filter' to high dynamic range image, second, the low-pass component of the image is compressed into 8-bit with the adaptive histogram projection technique which is using global standard deviation value of whole image. Third, the high-pass component of the image adaptively reduces noise and intensifies the strong edges using standard deviation value in local path of the guided filter. Lastly, the monitor display image is summed up with the compressed low-pass component and the edge-intensified high-pass component. At the end of this paper, the experimental result show that the suggested technique can be applied properly to the IR images of various scenes.

• Journal of Advanced Marine Engineering and Technology
• /
• 제39권6호
• /
• pp.649-655
• /
• 2015

본 논문에서는 효과적인 단일 영상 안개 제거 알고리즘을 제안한다. 잘 알려진 안개 제거 알고리즘인 dark channel prior(DCP)는 경계선 영역에서의 후광 현상(halo artifact) 및 결과 영상의 저대비를 초래하고 전달량 정제(refinement) 과정에서 긴 계산 시간을 필요로 한다. 이러한 문제들을 해결하기 위해 제안한 방법은 전달량을 추정할 때 DCP와 히스토그램 정보로 구성된 비용함수를 이용하고, 빠른 처리를 위해 다해상도 기법을 이용한다. 히스토그램 정보는 안개 제거 결과의 저대비 현상을 방지해주고, 에지 정보를 참고하는 다해상도 기법은 계산 시간을 감소시키고 후광 현상을 방지할 수 있다. 다수의 안개 영상에 대한 실험을 통해 제안한 방법이 기존의 방법들보다 효율적이고 우수함을 확인하였다.

• Journal of Computing Science and Engineering
• /
• 제9권1호
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.

• 전자공학회논문지B
• /
• 제33B권12호
• /
• pp.1-12
• /
• 1996

A new local path planning algorithm using DPH (distance profile histogram) is suggested in this paper. The proposed method makes a grid type world map using distance values from multiple ultrasonic sensors and genrates local points through which the mobile robot can avoid obstcles safely. The DPH (distance profile historgram) represents geometrical arrangement of obstacles around the robot in the local polar coordinate system which is assumed to be atached to the robot. To control robot's navigation, a three-layered control structure is adopted. The proposed local path planning algorithm is placed on the top level. And a point-to-point translation controller takes the middle level. The bottom level consists of a velcoity servo and sonar driver modules which take charge of driving physical hardwares. The validity of the propsoed method is demonstated through several experiments.