Oriented edge-selective band-pass filtering

Park, Y.,Suh, I.H. Elsevier science 2014 Information Sciences Vol. No.

Edge orientations play an important role in recognition due to their function as a primitive visual feature for various kinds of recognition tasks. Filter-based schemes are the most well-known and widely used method for analyzing edge orientation. However, the classical filter-based approach passes not only edges inside the preferred orientation band, but also edges outside the band. This can cause ambiguity in the estimation of edge orientation and can subsequently lead to failure in recognition tasks where edge orientations are used as a primitive feature. In this paper, we propose a novel filtering scheme, referred to as oriented edge-selective band-pass filtering, which passes edges inside the preferred orientation band and prevents edges outside the band from passing through. We present a computational model based on the basic mechanisms of cortical processing, i.e., a recurrent framework integrating the feedforward, lateral, and feedback processes, with the aim of investigating a solution based on the psychophysical and neuro-physiological findings of several decades. In the feedforward stage, our model employs a classical filter-based method to allow as many edges as possible in the preferred orientation band to pass through, while also allowing some edges outside the band to pass. The responses of edges outside the band are then inhibited by recurrent processing, involving two steps: a lateral and a feedback stage. We evaluated the performance of our model against classical filter-based methods, such as Gabor and Neumann filtering, using several artificial and natural images. The results validated the effectiveness of our approach.

Super-Interpolation With Edge-Orientation-Based Mapping Kernels for Low Complex <tex> $2\times $</tex> Upscaling

Jae-Seok Choi,Munchurl Kim IEEE 2016 IEEE TRANSACTIONS ON IMAGE PROCESSING - Vol.25 No.1

<P>With the advent of ultrahigh-definition (UHD) video services, super-resolution (SR) techniques are often required to generate high-resolution (HR) images from low-resolution (LR) images, such as HD images. To generate such HR images and a video of UHD resolutions in limited computing devices with hardware and software, low complex but excellent SR methods are particularly required. In this paper, we present a novel and fast SR method, called super-interpolation (SI), by unifying an interpolation step and a quality-enhancement step. The proposed SI method utilizes edge-orientation (EO)-based pre-learned kernels, which inherits the simplicity of interpolation and the quality enhancement of SR. It performs SR directly from the initial resolution of an input image to the target resolution of an up-scaled output image without requiring any intermediate interpolated image. The proposed SI method involves offline training and online up-scaling phases. In the offline training phase, training LR image patches are clustered based on their edge orientations into different EO classes for which class-dependent linear mapping functions are learned between training LR and HR image patches. In up-scaling phase, an HR output image patch for each LR input image patch is generated by applying an appropriate linear mapping function selected based on the EO of LR input image patch. Our proposed SI method is intensively compared with the ten state-of-the-art SR methods for common image sets and many HD/UHD images. The experimental results show that the SI method yields the smallest running time and requires relatively small hardware resources. It outperforms the six state-of-the-art methods in average (peak signal-to-noise ratio) PSNR/(structural similarity) SSIM, and exhibits competitive or somewhat lower PSNR/SSIM performance compared with the others.</P>

Ship Detection Using Edge-Based Segmentation and Histogram of Oriented Gradient with Ship Size Ratio

Eum, Hyukmin,Bae, Jaeyun,Yoon, Changyong,Kim, Euntai Korean Institute of Intelligent Systems 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.4

In this paper, a ship detection method is proposed; this method uses edge-based segmentation and histogram of oriented gradient (HOG) with the ship size ratio. The proposed method can prevent a marine collision accident by detecting ships at close range. Furthermore, unlike radar, the method can detect ships that have small size and absorb radio waves because it involves the use of a vision-based system. This system performs three operations. First, the foreground is separated from the background and candidates are detected using Sobel edge detection and morphological operations in the edge-based segmentation part. Second, features are extracted by employing HOG descriptors with the ship size ratio from the detected candidate. Finally, a support vector machine (SVM) verifies whether the candidates are ships. The performance of these methods is demonstrated by comparing their results with the results of other segmentation methods using eight-fold cross validation for the experimental results.

Ship Detection Using Edge-Based Segmentation and Histogram of Oriented Gradient with Ship Size Ratio

Hyukmin Eum,Jaeyun Bae,Changyong Yoon,Euntai Kim 한국지능시스템학회 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.4

In this paper, a ship detection method is proposed; this method uses edge-based segmentation and histogram of oriented gradient (HOG) with the ship size ratio. The proposed method can prevent a marine collision accident by detecting ships at close range. Furthermore, unlike radar, the method can detect ships that have small size and absorb radio waves because it involves the use of a vision-based system. This system performs three operations. First, the foreground is separated from the background and candidates are detected using Sobel edge detection and morphological operations in the edge-based segmentation part. Second, features are extracted by employing HOG descriptors with the ship size ratio from the detected candidate. Finally, a support vector machine (SVM) verifies whether the candidates are ships. The performance of these methods is demonstrated by comparing their results with the results of other segmentation methods using eight-fold cross validation for the experimental results.

방향성 보간을 이용한 공간적 에러 은닉 기법

유현선,김원기,정제창,Yoo Hyun sun,Kim Won ki,Jeong Je chang 한국통신학회 2005 韓國通信學會論文誌 Vol.30 No.3C

본 논문에서는 블록 기반의 영상압축에 있어서 방향성 기반 공간적 에러 은닉 기법을 제안한다. 제안된 기법은 우선 공간적 경계 정합 기법을 이용하여 손실된 블록 내의 에지 방향성을 나타내는 공간 방향 벡터들을 찾아낸다. 이 벡터들을 이용한 방향성 보간을 통해 복원 블록들을 만들고, 그 중 방향성 경계정합 에러가 작은 복원 블록들을 이용하여 최종 복원 영상을 생성한다. 제안된 기법은 매크로블록이나 슬라이스 단위의 에러에 대해 적응적으로 대처할 수 있고, 복잡도가 낮을 뿐만 아니라 우수한 복원 화질을 얻게 해준다. This paper introduces a spatial error concealment technique using directional interpolation in block-based compression. The first step involves finding the spatial direction vectors represented an edge-direction in the lost block using spatial boundary matching algorithm. Then, the error blocks are recovered by directional interpolation through these vectors and concealed by using the recovered blocks which have lower directional boundary matching error out of them relatively. This proposed method is able to deal with errors on macroblock or slice level adaptively. And it has lower complexity and maintains better performance compared to the conventional methods.

적응적 방향성 보간을 이용한 효율적인 공간적 에러 은닉 기법

박선규,김원기,정제창,Park, Sun-Kyu,Kim, Won-Ki,Jeong, Je-Chang 한국통신학회 2007 韓國通信學會論文誌 Vol.32 No.5c

에러가 존재하는 전송 환경에서 압축된 영상을 전송하는 경우, 일정한 화질을 유지하기 위해서는 에러 은닉 기법이 필요하다. 본 논문에서는 블록 기반의 영상 압축에 있어서 공간적 에러 은닉 기법을 제안한다. 제안된 기법은 공간 영역에서 슬라이스 단위의 에러가 발생했을 경우, 에러가 발생한 블록에 이웃하는 상 하 블록의 경계 화소를 이용하여 손상된 블록의 상 하 외곽 영역의 세밀한 에지 방향성을 찾아 각각 부분 복원을 한다. 그리고 복원되지 않은 내부 영역은 이웃한 경계 화소를 이용하여 블록 내의 전체적인 에지 방향성을 찾아 적응적으로 최종 복원 영상을 만들어 내는 2단계의 경계 정합 기법이다. 이 기법은 기존의 에러 은닉 방식보다 복잡도가 낮을 뿐만 아니라 에지를 흐름을 잘 복원하여 객관적 주관적으로 우수한 복원 영상을 얻게 해준다. When error occurs during the network transmission of the image, the quality of the restored image is very serious. Therefore to maintain the received image quality, the error concealment technique is necessary. This paper presents an efficient spatial error concealment method using adaptive edge-oriented interpolation. It deals with errors on slice level. The proposed method uses boundary matching method having 2-step processes. We divide error block into external and internal region, adaptively restore each region. Because this method use overall as well as local edge characteristics, it preserves edge continuity and texture feature. The proposed technique reduces the complexity and provide better reconstruction quality for damaged images than the previous methods.

PEOPLE DETECTION USING FEATURE VECTOR MATCHING

Hwa-Young Kim,Rae-Hong Park 대한전자공학회 2008 ITC-CSCC :International Technical Conference on Ci Vol.2008 No.7

This paper presents a novel method to detect people in real time from a video sequence taken from a single fixed camera. Foreground images are obtained from a sequence of operations: background differencing, thresholding, and morphological operation. We make use of quantized edge orientation to represent shape of human because human has particular edge orientation distribution on each of body parts. Then, a feature vector derived from the edge orientation map is computed in each of body parts of foreground images. The dataset, composed of sets of feature vectors, is used for matching with feature vectors computed from the current image of the input sequence. We use the Knearest neighbors to match the feature vectors. The proposed people detection method uses a proper feature vector that represents human edge orientation distribution, and employs simple matching steps for real-time processing. Experimental results with a number of test sequences demonstrate the effectiveness of the proposed method.

Edge Map-Based Fingerprint Reference-Point Detection

宋映澈(Young-Chul Song) 대한전기학회 2007 전기학회논문지 Vol.56 No.7

A new reference point location method based on an edge map is proposed, where an orientation map is defined and used to find the edge map. Experimental results show that the proposed method can effectively detect the core point in poor quality and arch-type fingerprint images and produces better results in terms of the detection rate and accuracy than the sine map-based method.

Comparative Study of Tetrahydrothiophene and Thiophene Self Assembled Monolayers on Au(111): Structure and Molecular Orientation

Ito, Eisuke,Hara, Masahiko,Kanai, Kaname,Ouchi, Yukio,Seki, Kazuhiko,Noh, Jaegeun Korean Chemical Society 2009 Bulletin of the Korean Chemical Society Vol.30 No.8

Surface structure and molecular orientation of self-assembled monolayers (SAMs) formed by the spontaneous adsorption of tetrahydrothiophene (THT) and thiophene (TP) on Au(111) were investigated by means of scanning tunneling microscopy (STM) and carbon K-edge near edge X-ray absorption fine structure (NEXAFS) spectroscopy. STM imaging revealed that THT SAMs have a commensurate (3 ${\times}\;2\sqrt[]{3}$) structure containing structural defects in ordered domains, whereas TP SAMs are composed of randomly adsorbed domains and paired molecular row domains that can be described as an incommensurate packing structure. The NEXAFS spectroscopy study showed that the average tilt angle of the aliphatic THT ring and $\pi$-conjugated TP ring in the SAMs were calculated to be about $30^o\;and\;40^o$, respectively, from the surface normal. It was also observed that the $\pi$* transition peak in the NEXAFS spectrum of the TP SAMs is very weak, suggesting that a strong interaction between $\pi$-electrons and the Au surface arises during the self-assembly of TP molecules. In this study, we have clearly demonstrated that the surface structure and adsorption orientation of organic SAMs on Au(111) are strongly influenced by whether the cyclic ring is saturated or unsaturated.

Comparative Study of Tetrahydrothiophene and Thiophene Self-Assembled Monolayers on Au(111): Structure and Molecular Orientation

Eisuke Ito,Masahiko Hara,Kaname Kanai,Yukio Ouchi,Kazuhiko Seki,노재근 대한화학회 2009 Bulletin of the Korean Chemical Society Vol.30 No.8

Surface structure and molecular orientation of self-assembled monolayers (SAMs) formed by the spontaneous adsorption of tetrahydrothiophene (THT) and thiophene (TP) on Au(111) were investigated by means of scanning tunneling microscopy (STM) and carbon K-edge near edge X-ray absorption fine structure (NEXAFS) spectroscopy. STM imaging revealed that THT SAMs have a commensurate (3 × 2√3) structure containing structural defects in ordered domains, whereas TP SAMs are composed of randomly adsorbed domains and paired molecular row domains that can be described as an incommensurate packing structure. The NEXAFS spectroscopy study showed that the average tilt angle of the aliphatic THT ring and π-conjugated TP ring in the SAMs were calculated to be about 30o and 40o, respectively, from the surface normal. It was also observed that the π* transition peak in the NEXAFS spectrum of the TP SAMs is very weak, suggesting that a strong interaction between π-electrons and the Au surface arises during the self-assembly of TP molecules. In this study, we have clearly demonstrated that the surface structure and adsorption orientation of organic SAMs on Au(111) are strongly influenced by whether the cyclic ring is saturated or unsaturated.