A new model-based speech enhancement algorithm by variational Bayesian learning was proposed in this paper. Autoregressive process was used to model speech signal and its order was determined automatically. Clean spee...
详细信息
A new model-based speech enhancement algorithm by variational Bayesian learning was proposed in this paper. Autoregressive process was used to model speech signal and its order was determined automatically. Clean speech signal could be estimated using a variational Kalman smoother. Moreover, overfitting was avoided in the learning of model parameter and model structure. Experimental results compared with Kalman filter-based enhancement and spectral subtraction methods demonstrate the performance of our algorithm.
An additive discussion for the validity of using the weighted information entropy to evaluate the complex degree of infrared （IR） backgronnds is given, Since small targets can be temporarily lost in actual infrared ...
详细信息
An additive discussion for the validity of using the weighted information entropy to evaluate the complex degree of infrared （IR） backgronnds is given, Since small targets can be temporarily lost in actual infrared video sequences, an adaptive binarization threshold for small targets detection is presented. Experimental results show the robustness of our method,
In this paper, two new similarity measure methods based on set theory were proposed. Firstly, similarity measure of two sets based on set theory and set operation was discussed. This principle was used to spectral vec...
详细信息
In this paper, two new similarity measure methods based on set theory were proposed. Firstly, similarity measure of two sets based on set theory and set operation was discussed. This principle was used to spectral vectors, and two approaches were proposed. The first method was to create a spectral polygon corresponding to spectral curve, and similarity of two spectral vectors can be replaced by that of two polygons. Area of spectral polygon was used as quantification function and some effective indexes for similarity and dissimilarity were computed. The second method was to transform the original spectral vector to encoding vector according to absorption or reflectance feature bands, and similarity measure was conducted to encoding vectors. It proved that the spectral polygon-based approach was effective 'and can be used to hyperspectral RS image retrieval.
Neighborhood Preserving Embedding (NPE) is a subspace learning algorithm, which has the ability of preserving local neighborhood structure on the data manifold. Though NPE has been applied in many domains of pattern r...
详细信息
It is difficult but important to get clear information from the low illumination images. In recent years the research of the low illumination image enhancement has become a hot topic in imageprocessing and computer v...
详细信息
It is difficult but important to get clear information from the low illumination images. In recent years the research of the low illumination image enhancement has become a hot topic in imageprocessing and computer vision. The Retinex algorithm is one of the most popular methods in the field and uniform illumination is necessary to enhance low illumination image quality by using this algorithm. However, for the different areas of an image with contrast brightness differences, the illumination image is not smooth and causes halo artifacts so that it cannot retain the detail information of the original images. To solve the problem, we generalize the multi-scale Retinex algorithm and propose a new enhancement method for the low illumination images based on the microarray camera. The proposed method can well make up for the deficiency of imbalanced illumination and significantly inhibit the halo artifacts as well. Experimental results show that the proposed method can get better image enhancement effect compared to the multi-scale Retinex algorithm of a single image enhancement. Advantages of the method also include that it can significantly inhibit the halo artifacts and thus retain the details of the original images, it can improve the brightness and contrast of the image as well. The newly developed method in this paper has application potential to the images captured by pad and cell phone in the low illumination environment.
This paper illustrates the performance of a mobile positioning technique applicable to a GSM *** experimental system of a network-based GSM positioning for ITS has been proposed, and the hybrid TOA-TDOA method based o...
详细信息
This paper illustrates the performance of a mobile positioning technique applicable to a GSM *** experimental system of a network-based GSM positioning for ITS has been proposed, and the hybrid TOA-TDOA method based on GSM signaling has been analyzed and used. The performance of the proposed system is showed through simulations in urban and suburban environments. The accuracy for 67% mobile stations is 70 m in urban and 120 m in suburban. The accuracy, coverage and network load of positioning system are also analyzed.
In recent years, the subspace learning methods based on the bidirectional two-dimensional are widely used in extracting features of face image. However, the existing bidirectional two-dimensional subspace learning met...
详细信息
This paper addresses the application of hand gesture recognition in monocular image sequences using Active Appearance Model （AAM）, For this work, the proposed algorithm is composed of constricting AAMs and fitting t...
详细信息
This paper addresses the application of hand gesture recognition in monocular image sequences using Active Appearance Model （AAM）, For this work, the proposed algorithm is composed of constricting AAMs and fitting the models to the interest region. In training stage, according to the manual labeled feature points, the relative AAM is constructed and the corresponding average feature is obtained. In recognition stage, the interesting hand gesture region is firstly segmented by skin and movement cues. Secondly, the models are fitted to the image that includes the hand gesture, and the relative features are extracted. Thirdly, the classification is done by comparing the extracted features and average features. 30 different gestures of Chinese sign language are applied for testing the effectiveness of the method. The Experimental results are given indicating good performance of the algorithm.
An algorithm to refine and clean gait silhouette noises generated by imperfect motion detection techniques is developed,and a relatively complete and high quality silhouette is *** silhouettes are sequentially refined...
详细信息
An algorithm to refine and clean gait silhouette noises generated by imperfect motion detection techniques is developed,and a relatively complete and high quality silhouette is *** silhouettes are sequentially refined in two levels according to two different probabilistic *** first level is within-sequence *** silhouette in a particular sequence is refined by an individual model trained by the gait images from current *** second level is between-sequence *** the silhouettes that need further refinement are modified by a population model trained by the gait images chosen from a certain amount of *** intention is to preserve the within-class similarity and to decrease the interaction between one class and *** experimental results indicate that the proposed algorithm is simple and quite effective,and it helps the existing recognition methods achieve a higher recognition performance.
This paper proposed a novel model-based feature representation method to characterize human walking properties for individual recognition by gait. First, a new spatial point reconstruction approach is proposed to reco...
详细信息
This paper proposed a novel model-based feature representation method to characterize human walking properties for individual recognition by gait. First, a new spatial point reconstruction approach is proposed to recover the coordinates of 3D points from 2D images by the related coordinate conversion factor (CCF). The images are captured by a monocular camera. Second, the human body is represented by a connected three-stick model. Then the parameters of the body model are recovered by the method of projective geometry using the related CCF. Finally, the gait feature composed of those parameters is defined, and it is proved by experiments that those features can partially avoid the influence of viewing angles between the optical axis of the camera and walking direction of the subject.
暂无评论