In this paper, we present our solutions for the WikipediaMM task at ImageCLEF 2008. The aim of this task is to investigate effective retrieval approaches in the context of a large-scale and heterogeneous collection of...
详细信息
In this paper, we present our solutions for the WikipediaMM task at ImageCLEF 2008. The aim of this task is to investigate effective retrieval approaches in the context of a large-scale and heterogeneous collection of Wikipedia images that are searched by textual queries (and/or sample images and/or concepts) describing a user's information need. We first experimented with a text-based image retrieval approach with query extension, where the expansion terms are automatically selected from a knowledge base that is (semi-)automatically constructed from Wikipedia. We show how this open, constantly evolving encyclopedia can yield inexpensive knowledge structures that are specifically tailored to effectively enhance the semantics of queries. Encouragingly, the experimental results rank in the first place among all submitted runs. The second approach we experimented with is content-based image retrieval (CBIR), in which we first train 1-vs-all classifiers for all query concepts by using the training images obtained by Yahoo! search, and then treat the retrieval task as visual concept detection in the given Wikipedia image set. By comparison, this approach performs better than other submitted CBIR runs. Finally, we experimented with a cross-media image retrieval approach by combining and re-ranking text-based and content-based retrieval results. Despite the final experimental results were not formally submitted before the deadline, this approach performs remarkably better than the text-based retrieval or CBIR approaches.
Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bitext. The current dominant pract...
详细信息
In this paper, we describe a novel type of feature for fast and accurate face detection. The feature is called Locally Assembled Binary (lab. Haar feature. lab.feature is basically inspired by the success of Haar feat...
详细信息
In this paper, we describe a novel type of feature for fast and accurate face detection. The feature is called Locally Assembled Binary (lab. Haar feature. lab.feature is basically inspired by the success of Haar feature and Local Binary Pattern (LBP) for face detection, but it is far beyond a simple combination. In our method, Haar features are modified to keep only the ordinal relationship (named by binary Haar feature) rather than the difference between the accumulated intensities. Several neighboring binary Haar features are then assembled to capture their co-occurrence with similar idea to LBP. We show that the feature is more efficient than Haar feature and LBP both in discriminating power and computational cost. Furthermore, a novel efficient detection method called feature-centric cascade is proposed to build an efficient detector, which is developed from the feature-centric method. Experimental results on the CMU+MIT frontal face test set and CMU profile test set show that the proposed method can achieve very good results and amazing detection speed.
In this paper, we address the problem of classifying image sets, each of which contains images belonging to the same class but covering large variations in, for instance, viewpoint and illumination. We innovatively fo...
详细信息
In this paper, we address the problem of classifying image sets, each of which contains images belonging to the same class but covering large variations in, for instance, viewpoint and illumination. We innovatively formulate the problem as the computation of Manifold-Manifold Distance (MMD), i.e., calculating the distance between nonlinear manifolds each representing one image set. To compute MMD, we also propose a novel manifold learning approach, which expresses a manifold by a collection of local linear models, each depicted by a subspace. MMD is then converted to integrating the distances between pair of subspaces respectively from one of the involved manifolds. The proposed MMD method is evaluated on the task of Face Recognition based on Image Set (FRIS). In FRIS, each known subject is enrolled with a set of facial images and modeled as a gallery manifold, while a testing subject is modeled as a probe manifold, which is then matched against all the gallery manifolds by MMD. Identification is achieved by seeking the minimum MMD. Experimental results on two public face databases, Honda/UCSD and CMU MoBo, demonstrate that the proposed MMD method outperforms the competing methods.
Resource Space Model (RSM) is a semantic model to manage resources in the future interconnection environment. The query capability is an important aspect of RSM as a semantic resource management model. This paper repo...
详细信息
One of the major problems in continuous wave bistatic radar based on FM radio transmitter is direct path interference(DPI). This is the signal received directly from a transmitter by the receive channel antenna. The D...
详细信息
ISBN:
(纸本)9780863418488
One of the major problems in continuous wave bistatic radar based on FM radio transmitter is direct path interference(DPI). This is the signal received directly from a transmitter by the receive channel antenna. The DPI and the reflected signal are coherent, have similar structure except for the mutual delay and Doppler frequency shift. To detect targets it is necessary to suppress or remove the DPI signal. First of all, the DPI signal based on FM radio transmitter is analyzed. Secondly, the approach based on adaptive nulling array processing is introduced in detail to solve this problem. Finally, associated signal processing schemes of the FM-radio-based passive radar is discussed. Simulation results by applying real collected data show the proposed method is effective.
The novel adaptive filtering algorithm based on the analysis of the detail images obtained from the wavelet decomposition of the original noisy image is proposed in the paper. The base idea is to compute the wavelet d...
详细信息
Authorization mechanism is an effective technique of access control. In this paper, we construct a multidimensional authorization space for RSM with the guidance of the methodology of RSM design. This authorization sp...
详细信息
An iterative algorithm is presented for the frequency recovery of the band-limited seismic data based on the sparse spike train deconvolution (SSTD) method using the minimum entropy criterion. In this method, we explo...
详细信息
In this paper, a technique for the extraction of roads in a high resolution synthetic aperture radar (SAR) image is presented. And a three-step method is developed for the extraction of road network from space borne S...
详细信息
ISBN:
(纸本)9780819469540
In this paper, a technique for the extraction of roads in a high resolution synthetic aperture radar (SAR) image is presented. And a three-step method is developed for the extraction of road network from space borne SAR image: the process of the feature points, road candidate detection and connection. Roads in a high resolution SAR image can be modeled as a homogeneous dark area bounded by two parallel boundaries. Dark areas, which represent the candidate positions for roads, are extracted from the image by a Gaussian probability iteration segmentation. Possible road candidates are further processed using the morphological operators. And the roads are accurately detected by Hough Transform, and the extraction of lines is achieved by searching the peak values in Hough Space. In this process, to detect roads more accurately, post-processing, including noisy dark regions removal and false roads removal is performed. At last, Road candidate connection is carried out hierarchically according to road established models. Finally, the main road network is established from the SAR image successfully. As an example, using the ERS-2SAR image data, automatic detection of main road network in Shanghai Pudong area is presented.
暂无评论