Content-Based Image Retrieval Improved by Incorporating Semantic Annotation via Query Expansion

Guoqing Xu,Jian Li,Chunyu Xu,Qi Wang 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.12

Automatic image annotation (AIA) is expected to be a promising way to improve the performance of content-based image retrieval (CBIR). However, current image annotation results are always incomplete and noisy, and far from practical usage. In this paper, we incorporate semantic annotations into CBIR via query expansion scheme to improve retrieval accuracy. In the proposed method, semantic annotations of test images are obtained using a visual nearest-neighbor-based annotation model. And both visual features and annotation keywords are used to represent images. The similarity between two images is determined by their visual similarity and semantic similarity. The method is evaluated on the well-known Pascal VOC 2007 dataset using standard performance evaluation metric. The experimental results indicate that the performance of CBIR can be improved by incorporating semantic annotation via query expansion.

Shape Description and Retrieval Using Included-Angular Ternary Pattern

Guoqing Xu,Ke Xiao,Chen Li 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.4

Shape description is an important and fundamental issue in content-based image retrieval (CBIR), and anumber of shape description methods have been reported in the literature. For shape description, both globalinformation and local contour variations play important roles. In this paper a new included-angular ternarypattern (IATP) based shape descriptor is proposed for shape image retrieval. For each point on the shapecontour, IATP is derived from its neighbor points, and IATP has good properties for shape description. IATPis intrinsically invariant to rotation, translation and scaling. To enhance the description capability, multiscaleIATP histogram is presented to describe both local and global information of shape. Then multiscale IATPhistogram 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 thestandard MPEG-7 shape database and Swedish leaf database. And the shape image retrieval performance of theproposed method is compared with other shape descriptors using the standard evaluation method. Theexperimental results of shape retrieval indicate that the proposed method reaches higher precision at the samerecall value compared with other description method.

Fast Leaf Recognition and Retrieval Using Multi-Scale Angular Description Method

Guoqing Xu,Shouxiang Zhang 한국정보처리학회 2020 Journal of information processing systems Vol.16 No.5

Recognizing plant species based on leaf images is challenging because of the large inter-class variation andinter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes themost important problem in plant leaf recognition. In this paper, a multi-scale angular description method isproposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scalegenerationrule to develop an angular description of leaf contours. It is parameter-free and can capture leaffeatures from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compactand is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classifyleaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namelySwedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standardmetrics and compared with several state-of-the-art methods. The results and comparisons show that theproposed method not only requires a low computational time, but also achieves good recognition and retrievalaccuracies on challenging datasets.

Multi-granular Angle Description for Plant Leaf Classification and Retrieval Based on Quotient Space

Guoqing Xu,Ran Wu,Qi Wang 한국정보처리학회 2020 Journal of information processing systems Vol.16 No.3

Plant leaf classification is a significant application of image processing techniques in modern agriculture. Inthis paper, a multi-granular angle description method is proposed for plant leaf classification and retrieval. Theproposed method can describe leaf information from coarse to fine using multi-granular angle features. In theproposed method, each leaf contour is partitioned first with equal arc length under different granularities. Andthen three kinds of angle features are derived under each granular partition of leaf contour: angle value, anglehistogram, and angular ternary pattern. These multi-granular angle features can capture both local and globeinformation of the leaf contour, and make a comprehensive description. In leaf matching stage, the simple cityblock metric is used to compute the dissimilarity of each pair of leaf under different granularities. And thematching scores at different granularities are fused based on quotient space theory to obtain the final leafsimilarity measurement. Plant leaf classification and retrieval experiments are conducted on two challengingleaf image databases: Swedish leaf database and Flavia leaf database. The experimental results and thecomparison with state-of-the-art methods indicate that proposed method has promising classification andretrieval performance.

Shape Description and Retrieval Using Included-Angular Ternary Pattern

Xu, Guoqing,Xiao, Ke,Li, Chen Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.4

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.

A Study on the Present Situation and Problems of Mentoring Relationship in Modern Apprenticeship - Based on the Perspective of Students

Dr. Guoqing XU,Xu CHEN,Yingwen ZHOU 한국직업자격학회 2017 한국직업자격학회 학술대회 Vol.2017 No.10

In the new era, the development and transformation of economy and society in China need more high-quality technicians. However, the traditional and conservative talent training model is far from satisfying the demand of the new development. Therefore, Modern Apprenticeship has gradually become the optimal model for cultivating new talents in China. Because the harmony of mentoring relationship directly affects the effective implementation of Modern Apprenticeship, this article is committed to exploring the present situation and problems of this relationship based on the perspective of students, and attempting to explain the underlying reasons, which are important evidence for improving this relationship. Only by establishing a stable and harmonious mentoring relationship can we really promote the development of Modern Apprenticeship and vocational education for better.

Novel Determination of Wheel-Rail Adhesion Stability for Electric Locomotives

Kun Xu,Guoqing Xu,Chunhua Zheng 한국정밀공학회 2015 International Journal of Precision Engineering and Vol. No.

Monitoring the wheel-rail adhesion state and maintaining the stability are the key issues to ensure the safety of locomotives withincreasing running speed nowadays. In this paper, a novel methodology is proposed to determine the wheel-rail adhesion stability. It is proved that when the adhesion state is in the unstable region, the transmitting factor which is defined as the ratio of the adhesionforce in the wheel drive force is negative. Based on this principle, we propose a novel adhesion stability detector via measuring thewheel drive torque and the wheel rotational speed. It is free from measuring or determining the chassis speed, creep ratio, and optimalcreep ratio, which are usually difficult to obtain in practical applications. In addition, the proposed methodology can evaluate theadhesion state dynamically regardless of the specific wheel-rail conditions. Numerical simulations are carried out to validate itseffectiveness.

Effect of Temperature and Strain Rate on the Hot Deformation Behaviour of Ferritic Stainless Steel

Guoqing Zu,Yukuan Lu,Yi Yan,Xiaoming Zhang,Jingwei Zhao,Wei Du,Xu Ran,Zhengyi Jiang 대한금속·재료학회 2020 METALS AND MATERIALS International Vol.26 No.2

The fow behaviour and microstructure characteristics of a ferritic stainless steel were investigated using plain strain compression test on a Gleeble 3500 thermo-mechanical test simulator with a hydrawedge system in the temperature range of850–1100 °C and strain rate range of 0.1–50 s−1. The phenomenological constitutive model and the relationship betweenthe Zener–Hollomon (Z) parameter and fow stress were established. The results reveal that the fow softening phenomenonoccurs at high strain rate, which is caused by the coupling efect of the adiabatic heating and dynamic recrystallisation (DRX). New grains nucleate preferentially at the original grain boundaries by strain-induced grain boundary migration. With anincrease of temperature or strain rate, a part of new grains form in the interior of deformed grains. The DRX grain size andfraction increase with the increase of temperature, however, exhibit a non-linear relationship with strain rate.

Analysis of Dike Natural Subsidence Caused by Mining under River

Gong Xu,Xiaoqing Su,Guoqing Qu 한국토양비료학회 2014 한국토양비료학회 학술발표회 초록집 Vol.2014 No.6

The Grain-Based Model Numerical Simulation of Unconfined Compressive Strength Experiment Under Thermal-Mechanical Coupling Effect

Zhongyuan Xu,Tianbin Li,Guoqing Chen,Chunchi Ma,Shili Qiu,Zhi Li 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.8

PFC-GBM (Particle Flow Code-Grain Based Model) is the major and fundamental method to simulate rock behaviors in thispaper. Geo-materials are composed of micro-grains, the behavior of these grains and the interface between them influencemacroscopic behavior of materials. Traditional PFC simulation method could simulate the integral micro-behavior of material, andPFC-GBM simulation focuses on every different grains and interfaces to simulate micro-heterogeneity of material. In this paper, anattempt is made to investigate the strength of rock masses and the development of micro-cracks under thermal-mechanical couplingeffect. For this purpose, a numerical model is established based on mineral analysis and pre-existing mechanical experiments ofGranite from one of complex tunnels in Yunnan Province. After establishing the model, the specimen were first heated and thencompressed according to test sequence of laboratory experiments. The simulation results are calibrated to match the laboratory testresults including thermal behaviors and fracture development. The conclusion of simulations show that both of thermal behaviorsand fracture development are depended on the micro-heterogeneity of granite in UCS (Unconfined Compressive Strength)experiment, the characteristics of minerals influence the macroscopic fracture mechanism. The simulation reveals that in a certainrange of temperature (40oC ~ 90oC), temperature increasing enhance the brittle damage of granite. The situation of 130oC had theobvious thermal-crack before loading and then exhibited a much lower peak strength and failure strain. This numerical observationmay guide the underground construction in complex geo-environment.