Earticle

To manipulate large video contents, effective video indexing and retrieval are required. A large number of video indexing and retrieval algorithms have been presented for frame-wise user query or video content query whereas a relatively few video sequence matching algorithms have been proposed for video sequence query. In this paper, we propose an efficient algorithm that extracts key frames using color histograms and matches the video sequences using edge features. To effectively match video sequences with a low computational load, we make use of the key frames extracted by the cumulative measure and the distance between key frames, and compare two sets of key frames using the modified Hausdorff distance. Experimental results with real sequence show that the proposed video sequence matching algorithm using edge features yields the higher accuracy and performance than conventional methods such as histogram difference, Euclidean metric, Battachaya distance, and directed divergence methods.

This paper describes the upgrade of an existing wave information retrieval algorithm by employing noise reduction in the pixel domain. Several algorithms for collecting wave information parameters from X-band radar image sequences including the wind field and current velocity have been developed over the past three decades. Using these algorithms, a band-pass filter (BPF) is applied to remove the non-wave contribution from the image spectra after the sea surface current velocity has been computed. However, such BPF designs have been both complex and insufficient in removing undesired components in X-band radar images. For this study, to improve the performance of wave information retrieval, an efficient noise reduction algorithm is incorporated into a regular wave information retrieval process. That is, the proposed algorithm was designed for operation in a more proper manner by effectively removing the undesired components in the pixel domain. Experiment results demonstrate that the proposed algorithm produces very close estimates to the buoy data records under undesirable noise conditions.

In order to improve the low accuracy of traditional wireless network health information retrieval methods, a wireless network health information retrieval method is designed based on data mining algorithm. The invalid health information stored in wireless network is filtered by data mapping, and the health information is clustered by data mining algorithm. On this basis, the high-frequency words of health information are classified to realize wireless network health information retrieval. The experimental results show that exactitude of design way is significantly higher than that of the traditional method, which can solve the problem of low accuracy of the traditional wireless network health information retrieval method.

A fast text retrieval algorithm using the idea of random blocking for massive‐content text based on Latent Semantic Analysis is proposed in this paper. Firstly, by fully considering the correlation between terms, retrieve and massive‐content text are represented in lower‐dimensional space and the model is improved using the way of singular value decomposition. Secondly, a random blocking query method is used for the retrieval of paragraphs which take the cosine similarity as the fitness function between the retrieve and massive‐content text and then the candidate paragraphs are output when there similarity value are higher than threshold. Experiments show that the proposed method has high performance in text retrieval by considering the semantic information fully and can achieve text retrieval quickly.

本文基于潜在语义分析技术提出了一种对大容量文本进行随机分块的快速文本检索算法。首先，充分考虑了词项之间的相关性，在低维空间中表示待检索文本的各个段落与检索文本，利用奇异值分解方法模型对其进行了改进；其次，利用随机分块检索算法，以检索文本和待检索文本各段落之间的余弦相似度作为适应度函数进行检索，将相似度超过阈值的候选段落输出；通过对实验结果分析，本文算法充分考虑文本语义信息，检索效果较好，能够实现快速文本检索。

논문은 영상의 주요한 색채들을 기반으로 하는 histogram-based 영상 검색을 위한 변형된 히스토그램 방법(SHM)을 제안한다. 히스토그램을 기초로 하는 방법은 이행이나 로테이션과 같은 이미지의 기하학적 변화에 영향을 받지 않기 때문에 컬러 영상 검색에 있어 매우 적합하다. 동일하고 비주얼한 정보를 지녔지만 컬러 강도가 변화된 영상의 경우, 전통적인 히스토그램 인터섹션(HIM)을 이용할 경우에는 현저히 성능이 떨어질 수도 있다. 이 문제를 해결하기 위해 변형된 히스토그램 방법(SHM)을 사용하였다. 실험 결과 변형된 히스토그램 방법(SHM)은 기존의 히스토그램 방식에 비해 더 높은 영상 검색 성능을 보였다

This paper proposes the shifted histogram method (SHM), for histogram-based image retrieval based on the dominant colors in images. The histogram-based method is very suitable for color image retrieval because retrievals are unaffected by geometrical changes in images, such as tran-slation and rotation. Images with the same visual information, but with shifted color intensity, may significantly degrade if the conventional histogram intersection method (HIM) is used. To solve this problem, we use the shifted histogram method (SHM). Our experimental results show that the shifted histogram method has significant higher retrieval performance than the standard histogram method.

본 연구의 목적은 이용자의 탐색 행태, 시스템의 정보 구축 행태를 기반으로 초기 질의어의 범주에 해당하는 연관 용어들(해당 용어의 지식구조와 관련된 연관 용어들)을 학습기능을 통해 자동으로 제시해 줄 수 있는 지능형 검색 시스템을 구현하는 것이다. 이를 위해 학습을 통해 전문가 수준의 색인어를 추출할 수 있는 지능형자동색인 알고리즘, 자동분류에 관련한 클러스터링 알고리즘과 문서 범주화 알고리즘 그리고 범주 표현 알고리즘에 대한 이론적 연구를 수행하였으며, 이들 이론적 연구를 근거로 비용과 시간적인 측면에서 그리고 재현율과 정도율이란 측면에서 우수한 성능을 발휘할 수 있는 지능형검색시스템을 구현하였다.

This is to develop Intelligent Retrieval System which can automatically present early query's category terms(association terms connected with knowledge structure of relevant terminology) through learning function and it changes searching form automatically and runs it with association terms. For the reason, this theoretical study of Intelligent Automatic Indexing System abstracts expert's index term through learning and clustering algorism about automatic classification, text mining(categorization), and document category representation. It also demonstrates a good capacity in the aspects of expense, time, recall ratio, and precision ratio.

본 연구에서는 GCOM-W1 위성에 탑재된 Advanced Microwave Scanning Radiometer 2 (AMSR2) 센서의 토양수분 자료를 Land Parameter Retrieval Model (LPRM) 알고리즘을 통해 전처리하여 2014년도 한반도 지점관측 자료와의 비교 분석을 수행, 위성 토양수분 자료의 적합성을 평가하였다. 통계 분석 결과 AMSR2 X-band의 토양수분 자료는 38개의 지점관측 자료와 비교해 0.03의 평균 bias, 0.16의 평균 RMSE의 낮은 오차 수준을 보였으며, 최대상관계수는 0.67로 나타났다. 또한 AMSR2 센서의 ascending, descending 시간대별 위성 토양수분자료 분석과 X, C1, C2-band의 주파수 영역별 위성 토양수분 자료 분석 결과, ascending overpass time 시간대와, X-band 주파수의 토양수분자료가 지점 관측 자료와 더 좋은 상관관계를 보였다. 본 연구의 분석 결과는 한반도에서 최근 문제가 되고 있는 가뭄을 비롯한 각종 재해 분석 시 토양수분의 공간적 분포를 연구하는데 활용 될 수 있을 것으로 기대된다.

This study aims at assessing the quality of the Advanced Microwave Scanning Radiometer 2 (AMSR2) soil moisture products onboard GCOM-W1 satellite based on Land Parameter Retrieval Model (LPRM) soil moisture retrieval algorithm with field measurements in South Korea from March to September, 2014. Results of mean bias and root mean square error between AMSR2 LPRM soil moisture products (X-band) and ground measurements showed reasonable value of 0.03 and 0.16. Also, the maximum of the Pearson correlation coefficients was 0.67, which showed good agreement in terms of temporal variability with ground measurements. By comparing AMSR2 soil moisture with in-situ measurement according to the overpass time and band frequency, X-band products on the ascending time outperformed than those of C1-band and C2-band. Furthermore, this study offers an insight into the applicability of the AMSR2 soil moisture products for monitoring various natural disasters at a large scale such as drought and flood.

The remote sensing images are massively stored, so it is difficult for the traditional single-node mode to meet the real-time requirement for remote sensing image retrieval. In order to improve remote sensing image retrieval efficiency and accuracy, a kind of feature information MapReduce based remote sensing image retrieval algorithm is proposed in this article. Specifically, the color features and the texture features of the remote sensing image are firstly extracted, and then Map function is adopted to calculate the similarity between the remote sensing image to be retrieved and the image in the feature library according to the color features and the texture features, and finally Reduce function is adopted to collect the intermediate results of various node tasks and the remote sensing images are ranked by a descending order according to the similarity in order to obtain the remote sensing image retrieval result. The test result shows that the proposed algorithm can rapidly and accurately retrieve the remote sensing image, thus not only improving the remote sensing image retrieval efficiency, but also improving the remote sensing image retrieval accuracy.

Due to the mass track data accumulated day by day, new challenges are raised for traditional information retrieval. This paper studies the issue of k-nearest neighbor track retrieval facing moving object, and converts this issue into aggregate Top-k query issue of information retrieval field. A parallel TA algorithm in random access database is proposed, and it has effectively solved the issue of k-nearest neighbor track retrieval. Performance of this algorithm is verified through a large number of experiments.

Because of the feature points can describe the local characteristics of the image in a reasonable manner, effective use of feature point of content based image retrieval become the current hot issues in the field of computer vision. Aiming at this problem, we put forward a kind of combination clustering based on feature points, a new method of image retrieval. The method includes the combination of feature point clustering algorithm and based on the algorithm of local color histogram construction strategy. With the existing and local color histogram retrieval method based on feature points, compared to the method can effectively solve the current method of feature point location information and feature point center relying too much on the problem. Subjectivity and as a result of the manual annotation image accuracy, the traditional image retrieval methods cannot meet the needs of the user. Multidimensional indexing technology is only from the perspective of how to improve the indexing algorithm to adapt to the large-scale database to consider a problem, in content-based image retrieval. Our research combines the advantages of the semantic analysis and kernel clustering which will enhance the performance of the traditional image retrieval methods and strengthen the feasibility of the algorithm.

The feature description of image and the index mechanism of the feature are the keys to realize the content-based image retrieval, aiming at the problem of massive image data and “dimension curse”, this paper proposes the BOF-based image retrieval improved algorithm, and combines with VLAD and soft assignment it generates the soft assignment local aggregation descriptor (SA-VLAD) which has a better ability to resist the dimension reduction and a higher recognition rate. When the index mechanism IVFADC is at query time, to ensure the recall ratio and precision rate of the result, the candidates inverted index chain are increased, which leads to the problems of distance calculation and the query time’s increasing. For this point, in the index phase, the scattered distribution is carried out aiming at the database vector, which reduces the burden of distance calculation, and improves the quality of the query results at the same time. The experimental results show that the algorithm in this paper obtains a good effect in the content-based massive image database retrieval.

Ant colony algorithm since it has a better convergence and parallelism, widely used in the data retrieval, however, is not high, due to the characteristics of retrieval object use seriously affect the accuracy of retrieval, and according to this problem, this paper proposed an improved ant colony algorithm, this algorithm will retrieve objects comprehensive characteristics into the ant colony algorithm, and solve the convergence speed and computational complexity of the algorithm, obtained good results in image retrieval.

With the fast development of data analysis and computer science technology, the design and implementation of image retrieval system has been a hot topic. The prior research focus more on image-size based approaches which are not intelligent or convenient. In this paper, we present a novel modified evolutionary algorithm based image retrieval framework theoretically with applications. To achieve more accuracy in less number of iteration, this paper, proposed a new approach to enhance the performance of content guided retrieval methodology by improving the performance of RF through Particle Swarm Optimization, Genetic Algorithm and Support Vector Machine. The objective of using Genetic Algorithm and Particle Swarm Optimization is to increase the number of images in relevant set where SVM is used to classify the relevant and irrelevant images. The experimental and numerical simulation indicate the efficiency of our method which means the presented technique is helpful in the fields where high accuracy rate of image retrieval is required. Further work of interest is also discussed in the final section.

Feature extraction is a key issue for 3d model retrieval. A novel architecture to extract the curve-skeleton of 3d model is introduced. The algorithm firstly calculates the 3D vector fields of models represented by discrete unit, and then extracts the hierarchical curve-skeleton based on topological features of the critical curve and critical points of the vector fields. The similarity among 3D curve-skeletons is measured by using an improved Earth Mover's Distance (EMD) algorithm. The curve-skeleton extracted with this novel algorithm can be used to categorize models and implement global matching and partial matching.

Nowadays the content based image retrieval (CBIR) is becoming a source of exact and fast retrieval. CBIR presents challenges in indexing, accessing of image data and how end systems are evaluated. Data clustering is an unsupervised method for extraction hidden pattern from huge data sets. Many clustering and segmentation algorithms both suffer from the limitation of the number of clusters specified by a human user. It is often impractical to expect a human with sufficient domain knowledge to be available to select the number of clusters (NC) to return. This paper discusses the image retrieval based on NC which is evaluated using hierarchical agglomerative clustering algorithm (HAC). In this paper, we determine the optimal number of clusters using HAC applied on RGB images and validate them using some validity indices. Based on number of clusters, we retrieve set of images. These cluster values can be further used for divide and conquer technology and indexing for large image dataset. An experimental study is presented on real data sets.

Radio occultation (RO) has been used in the planetary science since Microlab-1 was launched in 1995. With the RO technique, the profiles of atmosphere and the global atmospheric data can be obtained. In 2006, Taiwan launched six low Earth orbit (LEO) satellites as the RO constellation mission, known as FORMOSAT-3. In order to retrieve the RO data from original data, a retrieval algorithm, NCURO, is developed. The input of NCURO algorithm is mainly the excess phase of GPS signal, and the output is the dry pressure and dry temperature. Using temperature profiles retrieved by NCURO algorithm, temperature perturbation and potential energy of gravity wave have been evaluated. In this paper, the retrieval algorithm and the global distribution of energy of gravity waves are described and demonstrated.

This paper applies the Scan-Angle Method (SAM) to the Total Ozone Mapping Spectrometer (TOMS) aboard Earth Probe (EP) satellite for determining tropospheric ozone based on TOMS scan geometry. In the northern tropical Africa burning season, the distribution of the SAM-derived tropospheric ozone presents a tropospheric ozone enhancement related to biomass burning. This distribution is consistent with that of fire counts observed from Along Track Scanning Radiometer (ATSR) and that of carbon monoxide, the tropospheric ozone precursor, observed from Measurements of Pollution In The Troposphere (MOPITI). However, this feature is not shown in the distribution of tropospheric ozone derived from other TOMS-based algorithms for the northern burning season. In the high latitudes, the influence of pollution in the SAM results is seen over the northern continents in agreement with carbon monoxide for northern summer when the dynamical activity is weak in the northern hemisphere.