Abstract:Information retrieval based on multi-modal data is a challenging research topic. In this paper, we propose a novel approach to associate images and text keywords, which enables automatic image annotation and keyword-based image retrieval. First, the two independent spaces, containing images and text keywords respectively, are related to each other by the parallel projection. Second, the heterogeneous link between multi-modal data is defined as the form of dot product. Consequently, the link between a new data instance and the known data in the other modality can be deduced from the two homogeneous kernels. Finally, an iterative model is proposed to optimize the link and achieve the probability association matrix between the two-modal data. According to the link from images to text keywords, the annotations for images can be achieved; according to the link from text keywords to images, images can be retrieved based on text keywords. Moreover, the proposed approach explores the relationship between multi-modal data in an unsupervised manner. We provide experimental results on the tasks of automatic image annotation and keyword-based image retrieval to show the efficacy of our approach.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. Iterative Association Model for Image Annotation
	Xu Feng,Zhang YuJin
	Electrics, Communication and Autocontrol Technology 10 August 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Information retrieval based on multi-modal data is a challenging research topic. In this paper, we propose a novel approach to associate images and text keywords, which enables automatic image annotation and keyword-based image retrieval. First, the two independent spaces, containing images and text keywords respectively, are related to each other by the parallel projection. Second, the heterogeneous link between multi-modal data is defined as the form of dot product. Consequently, the link between a new data instance and the known data in the other modality can be deduced from the two homogeneous kernels. Finally, an iterative model is proposed to optimize the link and achieve the probability association matrix between the two-modal data. According to the link from images to text keywords, the annotations for images can be achieved; according to the link from text keywords to images, images can be retrieved based on text keywords. Moreover, the proposed approach explores the relationship between multi-modal data in an unsupervised manner. We provide experimental results on the tasks of automatic image annotation and keyword-based image retrieval to show the efficacy of our approach.
	TO cite this article:Xu Feng,Zhang YuJin. Iterative Association Model for Image Annotation[OL].[10 August 2007] http://en.paper.edu.cn/en_releasepaper/content/14513


	2. Scene Categorization Based on Atmosphere Semantics
	Feng Xu,Yu-Jin Zhang
	Electrics, Communication and Autocontrol Technology 10 August 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Image categorization and annotation with abstract semantics beyond cognitive semantic level is a difficult problem in image understanding. On the other hand, atmospheres semantics of film frames is important to convey the message behind the story. For this abstract attribute, contextual information and domain knowledge besides the traditional content features are more helpful. The domain knowledge is included by the semantic ontology and network structures learnt from data. The contextual information includes film topic, recording time, and audience response. Based on all the metadata, Bayesian networks are employed to fuse metadata and a causal strength is proposed to account for the causation. Finally, we provide extensive experimental results to demonstrate the efficacy of the proposed approach.
	TO cite this article:Feng Xu,Yu-Jin Zhang. Scene Categorization Based on Atmosphere Semantics[OL].[10 August 2007] http://en.paper.edu.cn/en_releasepaper/content/14507

Saved Papers

Saved Papers


	3. Performance Analysis of Angular-Smoothing Based Root-MUSIC for an L-Shaped Acoustic Vector-Sensor Array
	Yougen Xu,Zhiwen Liu
	Electrics, Communication and Autocontrol Technology 20 July 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Eigenstructure-based direction-of-arrival (DOA) estimation algorithms such as Multiple Signal Classification (MUSIC), Root-MUSIC, Estimation of Signal Parameters via Rotational Invariance Techniques (ESPRIT), encounter great difficulty in the presence of perfectly correlated incident signals. For an array composed of a number of translational invariant subarrays such as a uniform linear scalar-sensor array, this problem can be solved by spatial smoothing. An array of identically oriented acoustic vector-sensors can be grouped into four coupled subarrays of identical grid geometry, respectively corresponding to the pressure sensors and differently oriented velocity-sensors. These four subarrays are angular invariant dependent only on signals’ direction cosines and an angular smoothing can be exploited for source decorrelation. In this paper, the performance of root-MUSIC incorporated with angular smoothing for correlated source direction finding with an L-shaped acoustic vector-sensor array is analyzed in terms of the overall root mean-square errors (RMSE) of DOA estimates. We derive the analytical expression of the RMSE and compare it with simulation results and that of spatial smoothing for a rectangular pressure-sensor array instead.
	TO cite this article:Yougen Xu,Zhiwen Liu. Performance Analysis of Angular-Smoothing Based Root-MUSIC for an L-Shaped Acoustic Vector-Sensor Array[OL].[20 July 2007] http://en.paper.edu.cn/en_releasepaper/content/14177


	4. Study Of Adaptive Lane Detection algorithm
	Huang Tao,Liao Li
	Electrics, Communication and Autocontrol Technology 18 May 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:This paper presents a Adaptive Lane Detection algorithm .The algorithm based on geometrical transform and Hough transfer and use the least squares analysis to enhance the quality of lane detection. The algorithm have the advantages of high speed and robust. The experience proved that the algorithm is efficient and feasible.
	TO cite this article:Huang Tao,Liao Li. Study Of Adaptive Lane Detection algorithm[OL].[18 May 2007] http://en.paper.edu.cn/en_releasepaper/content/12905


	5. Measurement for Water Content in Oil-Water Two Phase Flow Using Novel Hybrid Intelligent Prediction Model
	Zhang Dongzhi,Xia Bokai,Fu Tao
	Electrics, Communication and Autocontrol Technology 11 April 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Some parameters affecting the measurement of water content in oil/water two-phase flow are detected using multi-sensor technology, and a novel hybrid intelligent prediction model is proposed to improve measuring precision of water content. Some advanced information processing technologies, such as neural networks optimized by hybrid genetic algorithm, combined meathod for decisions of multiple modules, are introduced in this intelligent prediction model, which guarantee a good prediction effect with global and fast convergence, strong generalization capability and high precision. The research result in this paper is shown that prediction precision is improved to a great extent in the all-round measuring range for water content, while the development cost is at a low valuation. It is a new and effective method for measuring water content in oil/water two-phase flow.
	TO cite this article:Zhang Dongzhi,Xia Bokai,Fu Tao. Measurement for Water Content in Oil-Water Two Phase Flow Using Novel Hybrid Intelligent Prediction Model[OL].[11 April 2007] http://en.paper.edu.cn/en_releasepaper/content/12138


	6. Method of Signal denoising Based on Wavelet
	Zitian Song,Yue Pan
	Electrics, Communication and Autocontrol Technology 26 March 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:The method of signal denoising based on wavelet thresholding is proposed in this paper. At first, it introduced principle of wavelet multiresoludion analysis. Secondly, three methods of selecting threshold are described. Then, the method of choosing threshold was introduced. At last, according to the computer simulation results, the performance of signal denoising based on wavelet thresholding were shown and the best method of choosing threshold has been found.
	TO cite this article:Zitian Song,Yue Pan. Method of Signal denoising Based on Wavelet [OL].[26 March 2007] http://en.paper.edu.cn/en_releasepaper/content/11669


	7. Modified Method of Line Solution to Arbitrary 2-D Dielectric Coated Conducting Cylinders
	Bin Yan
	Electrics, Communication and Autocontrol Technology 26 March 2007
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper, a modified MoL (method of line) is applied to solve Electromagnetic wave scattering from arbitrary 2-D dielectric coated conducting cylinders. In the process, the 2-D Laplacian equation is reduced to a series of 1-D differential equation which can be solved analytically in radial direction, by discretizing the angular direction with radial lines. Numerical results are also presented by MATLAB simulation.
	TO cite this article:Bin Yan. Modified Method of Line Solution to Arbitrary 2-D Dielectric Coated Conducting Cylinders[OL].[26 March 2007] http://en.paper.edu.cn/en_releasepaper/content/11650


	8. The Registration of INSAR Complex Images
	Peng Shurong ,Wang Yaonan ,Liu Guocai ,Wenzhong Yang
	Electrics, Communication and Autocontrol Technology 30 November 2006
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Registration accuracy of InSAR is a key index in the procedure of the processing InSAR data. To obtain better measuring results, A multi-steps matching method is proposed to improve registration accuracy progressively for InSAR complex image. Firstly calculate the approximate offsets by using software EnView. Then perform pixel level’s primary matching and sub-pixel level’s precise registration. The primary matching algorithm based on texture structure information. Considering that the presented algorithms are based on the amplitude map and ignore the integration, the algorithm by using global relaxation matching on account of the phase is proposed in the last matching step to reduce the matching errors and improve matching precision. The experiment verified the nicer validity of this algorithm.
	TO cite this article:Peng Shurong ,Wang Yaonan ,Liu Guocai , et al. The Registration of INSAR Complex Images[OL].[30 November 2006] http://en.paper.edu.cn/en_releasepaper/content/10091


	9. Uncoupled Fuzzy-based Geodesic Active Regions Models for Image Segmentation
	Li Canfei,Wang Yaonan
	Electrics, Communication and Autocontrol Technology 30 November 2006
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:In this paper we present a novel Uncoupled Fuzzy-based Geodesic Active Regions (UFGAR) framework for dealing with frame partition problems in image segmentation. Like the usually Geodesic Active Regions (GAR) framework presented by N. Paragios and R. Derichhave, our framework unifies boundary and region-based information. The boundary information of the mixture model is determined using a edge detector based on the fuzzy membership functions, and the region information indicates the region intensity properties is estimated by a measure based on the fuzzy membership functions too. The defined objective function is minimized using a gradient descent method where a level set approach is used to implement the resulting PDE system. But unlike GAR, which is based on the Maximum Likelihood Principle for the observed density function image histogram using a mixture of Gaussian elements, our model is based on FCM and fuzzy membership functions. We define a novel region measure based on fuzzy membership functions to measure the property of regions. According to the motion equation, the initial curve is propagated toward the segmentation result under the influence of boundary and region-based segmentation forces, and being constrained by a regularity force. The performance of this method is demonstrated by a synthetic image, and the results of its application to brain images are presented.
	TO cite this article:Li Canfei,Wang Yaonan. Uncoupled Fuzzy-based Geodesic Active Regions Models for Image Segmentation[OL].[30 November 2006] http://en.paper.edu.cn/en_releasepaper/content/10066


	10. 2-D Hybrid DFT-DWT Application to Two-dimensional Signal Processing*
	Xiao Tan,Xiao Yang,Hh Shaohai
	Electrics, Communication and Autocontrol Technology 29 November 2006
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Some two-dimensional signals may have different probability distribution of noise and frequency interference in different directions (horizontal and vertical, or space and time). It poses the question of how to extract desired signals from such complicated environment of noise and interference. It is difficult to extract by using classical DFT and DWT algorithms alone. To solve the problem, a hybrid 2-D transform, discrete Fourier transform-discrete wavelet transform (2-D DFT-DWT), with definitions, properties and algorithms, is developed for the hybrid 2-D signal processing. The hybrid transform can be used to remove the noise or interference in 2-D signals from different directions. Under the transform, desired results can be obtained to take advantage of merits of both DFT and DWT. Also, simulation illustrates the application.
	TO cite this article:Xiao Tan,Xiao Yang,Hh Shaohai. 2-D Hybrid DFT-DWT Application to Two-dimensional Signal Processing*[OL].[29 November 2006] http://en.paper.edu.cn/en_releasepaper/content/10035

	Check out RSS, or use RSS reader to subscribe this item