Recently, more and more intelligent algorithms are applied to biomedical, which have improved the biomedical data analysis and classification greatly. In this paper, a new method of automatic identification of heart s...
详细信息
Recently, more and more intelligent algorithms are applied to biomedical, which have improved the biomedical data analysis and classification greatly. In this paper, a new method of automatic identification of heart sound by using DTW (dynamic time warping) and MFCC (Mel-frequency cepstral coefficients) of heart is introduced. MFCC of heart sound are extracted, and then DTW is used to identify heart sound. The experimental results show that the methods have good performance in heart sound recognition.
By high speed photography, scanning electron microscope and x-ray energy dispersive spectroscopy on the diesel engine fueled with bio-diesel and No.0 diesel, the combustion processing in cylinder and the characteristi...
详细信息
By high speed photography, scanning electron microscope and x-ray energy dispersive spectroscopy on the diesel engine fueled with bio-diesel and No.0 diesel, the combustion processing in cylinder and the characteristics of particulate matter (PM) from engine exhaust are researched. The findings show that there are some fine differences between bio-diesel and diesel, such as the transport performance of fuel under high pressure, the ignition flammability of the mixtures of air and fuel, and the granularity characteristics of particle matter from engine exhausts. This research is enormously significant to the development and utilization of bio-diesel.
Human vision contrast resolution (HVCR) is lower and varies exponentially with background gray in scotopic condition. HVCR compensation implies that a small gray difference of two adjacent pixels in an image is made J...
详细信息
Human vision contrast resolution (HVCR) is lower and varies exponentially with background gray in scotopic condition. HVCR compensation implies that a small gray difference of two adjacent pixels in an image is made JND (just noticeable difference). To obtain the optimal compensation, the optimal compensation factor is determined by a subjective assessment result of the compensated image. To obtain the optimal quality of a compensated image, we proposed a prediction method of optimal compensation factor and obtained the compensated images with visually optimal effect for a set of the test images.
In this paper Iris and Retina features are combined for recognition in biometric system. This hybrid biometric system two biometrics can be taken from the same acquisition process and image. Gabor transform to extract...
详细信息
In this paper Iris and Retina features are combined for recognition in biometric system. This hybrid biometric system two biometrics can be taken from the same acquisition process and image. Gabor transform to extract the features from Iris and Retina is used and also geometrical features extraction steps of retina image is processed. Feature fusion is performed.
Based on wavelet transform, an image fusion algorithm was developed to increase the volume of hidden information. The algorithm was able to fuse 16 or 64 watermark images into one cover image. Taking advantage of Haar...
详细信息
Based on wavelet transform, an image fusion algorithm was developed to increase the volume of hidden information. The algorithm was able to fuse 16 or 64 watermark images into one cover image. Taking advantage of Haar wavelet transform, the algorithm could recover all hidden images. Simulation tests showed that the proposed algorithm was capable of hiding a large volume of information effectively and securely. It could be used to transmit encrypted military information over the network.
The images taken from low-light level condition can not be resolved by human vision. We called the method, that these images are transformed into the visible images by human vision, lower level image mining (LLIM). We...
详细信息
The images taken from low-light level condition can not be resolved by human vision. We called the method, that these images are transformed into the visible images by human vision, lower level image mining (LLIM). We proposed a method called as the gradually flattening gray spectrum to mine a gray distribution information, proposed a method called as Zadeh-X transformation to implement a gray transformation to acquire a new image, and proposed a method which can predict transformation parameter by means of the subjective assessment results of the optimal quality images to adaptively, automatically and fast acquire the optimal quality images.
Digital radiographs play very important role in medical imaging. However, the image quality has weakness with lower contrast and some noises owing to various reasons. So it is necessary to enhance these images to faci...
详细信息
Digital radiographs play very important role in medical imaging. However, the image quality has weakness with lower contrast and some noises owing to various reasons. So it is necessary to enhance these images to facilitate the postprocessing or diagnosis. In this paper, our method utilized wavelet transform to decompose the image, removed the noise using wavelet threshold method, and modified the high coefficients using nonlinear method and the low coefficient using the unsharp masking method. At last, the enhanced image got through inverse wavelet transform. At the same time, we also analyzed the characteristics of several common wavelet bases. Experiments were carried out on a digital radiograph with some different wavelet bases and some other traditional approaches. The results showed that this method had better enhancing effect than traditional approaches.
In this paper, an improved variational level set method for the Chan-Vese model is proposed to drive level set function to become fast and stably close to signed distance function. A restriction item that is a nonline...
详细信息
In this paper, an improved variational level set method for the Chan-Vese model is proposed to drive level set function to become fast and stably close to signed distance function. A restriction item that is a nonlinear heat equation with balanced diffusion rate is added to the traditional Chan-Vese model, and therefore the costly re-initialization procedure is completely eliminated. The proposed variational level set formulation is implemented by numerical scheme with spatial rotation-invariance gradient and divergence operator. Consequently it computes more efficiently. The proposed algorithm has been applied to medical images with desired results.
Tongue diagnosis is widely used in the Traditional Chinese Medicine (TCM) and tongue image classification based on pattern recognition plays an important role in the development of the modernization of TCM. However, d...
详细信息
Tongue diagnosis is widely used in the Traditional Chinese Medicine (TCM) and tongue image classification based on pattern recognition plays an important role in the development of the modernization of TCM. However, due to labeled tongue samples are rare and costly or time consuming to obtain, most of the existing methods such as SVM utilize labeled training samples merely. Therefore the classifiers usually have poor performance. In contrast, Universum SVM is a promising method which incorporates a priori knowledge into the learning process with labeled data and irrelevant data (also called universum data). In tongue image classification, the number of irrelevant instances could be very large since there are many irrelevant categories for a certain tongue's type. But not all the irrelevant instances joined in training can improve the classifier's performance. So an algorithm of selecting the universum samples is also introduced in this paper. Experimental results show that the Universum SVM classifier is improved and the algorithm of selecting universum samples is effective.
Bilateral filtering has been a popular denoising technique that smooths images while preserving edges by means of a nonlinear combination of adjacent pixel values. We propose an entropy-based trilateral (EnTri) filter...
详细信息
Bilateral filtering has been a popular denoising technique that smooths images while preserving edges by means of a nonlinear combination of adjacent pixel values. We propose an entropy-based trilateral (EnTri) filter that extends the classical bilateral filter for noise removal in digital images. A new median-metric weighting function is incorporated into the geometric and radiometric components, followed by an entropy function to balance the contribution between the weights. The entropy function is used to adaptively detect the local intensity variations on each pixel. Our EnTri framework replaces the intensity value on each pixel with an average value weighted by the three components between neighboring pixels. A variety of images contaminated with various levels of noise were used to assess the performance of this new filtering method. Experimental results indicate that the EnTri filter outperformed several existing methods in both visual image quality and restored signal quantity.
暂无评论