The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper introduces region of interest (ROI) as a functionality to local tone mappings of high dynamic range (HDR) radiance maps. In the proposed scheme, a new quadratic regularization method is provided to decompose the luminance of an HDR radiance map into a base layer with large gradients and a detail layer with small gradients. An ROI based global tone mapping is designed to compress the base...
The 3D reconstruction for freehand 3D ultrasound remains a hard problem because that the recorded B-scans are not only sparse, but also non-parallel (actually they may intersect each other). Conventional volume reconstruction methods can't reconstruct sparse data efficiently while not introducing geometrical artifacts, and conventional surface reconstruction methods can't reconstruct surfaces from...
The complexity of hand function is such that most existing upper limb rehabilitation robotic devices use only simplified hand interfaces. This is in contrast to the importance of the hand in regaining function after neurological injury. Computer vision technology has been used to identify hand posture in the field of Human Computer Interaction, but this approach has not been translated to the rehabilitation...
With the development of flow visualizations and measuring techniques, the particle image velocimetry(PIV) is applied in experiments and researches of fluid gradually. But, the background noise is unavoidable in acquiring partical images. The experimental researches showed: the background noise, which will lead to errors or deviations in gray value of partical images, introduces errors in velocity...
Forest type identification is one of most important contents of forest inventory. K nearest-neighbour algorithm has already proven their use in forest mapping. However, as the remote sensing data was large scale, the efficiency of processing based on KNN decreased seriously. Therefore, the study implemented a tool which could have the feature of fast processing multi-spectral data based on KNN. For...
This paper proposes a novel scheme to save the usage of ink or toner by an approximate-K algorithm for color printers. Existing printers use the mixtures of three color toners(C, M and Y) to print all the pixels for color images, and it makes color printing cost 4-4.5 times more expensive than monochromic printing. Since human eyes are not sensitive to distinguish neighboring colors in the color space,...
In this work, a sample rate estimator is proposed for selective graphics rendering so that the samples are allocated such that the best perceived image quality can be achieved under a given sample budget. In the proposed estimator, the sample rate of a pixel is decided by not only the visual attention (VA) level of the region to which the pixel belongs but also the required rendering complexity (RC)...
In applications where shape is used as metadata to describe image and video content, image dependent techniques exhibit superior error concealment performance compared to the traditional MPEG-4 like image-independent techniques. The image corresponding to a particular shape may not be readily known at the decoder and rather needs to be retrieved from of a set of images. This paper presents a novel...
Identifying events in sports video offers great potential for advancing visual sports coaching applications. In this paper, we present our results for detecting key events in a tennis match. Our overall goal is to automatically index a complete tennis match into all the main tennis events, so that a match can be recorded using affordable visual sensing equipment and then be automatically indexed into...
Traditional window-based color indexing techniques have been widely used in image analysis and retrieval systems. In the existing approaches, all the image regions are treated with equal importance. However, some image areas carry more information about their content (e.g. the scene foreground). The human visual system bases indeed the categorization process on such set of perceptually salient region...
Content-Based Copy Detection (CBCD) is an emergent research topic and has been extensively studied recently. Color is one of the most important and easily recognizable features of visual content. To address efficiency and effectiveness issues of CBCD systems, in this article a compact and computationally inexpensive CBCD scheme using MPEG-7 Dominant Color Descriptor is proposed. This paper proposes...
In this paper, a new medical image segmentation algorithm based on Skew Gaussian distribution is proposed. In brain images, it is necessary to classify the brain voxels into one of the 3 main tissues mainly Gray matter (GM), White matter (WM) and Cerebro Spiral fluid (CSF). Quantization of Gray & White matter is a topic of concern in neuro-degenerative disorders. Viz., Alzheimer disease and Parkinson's...
In this paper, we have proposed an accurate and an efficient text detection model for document images and video frames. The proposed model is based on the Moravec operator to localize text in a document image and horizontal and vertical mask convolution is performed to identify the actual text blocks. In order to exhibit the performance of the proposed model, we have conducted experimentation on the...
Texture analysis plays a vital role in remotely sensed image classification as every pixel is going to be classified based on the collective pixel values of neighborhood. The result thus obtained gives increased classification accuracy. In this paper, a modified texture model obtained by modifying Multivariate Local Binary Pattern (MLBP) texture model is used for classification in remotely sensed...
Image retrieval is an active research area in numerous applications. Color and Texture is an important Low Level features for content based image retrieval and this paper proposes a method for extracting color feature using Discrete Wavelet transform and Auto-Correlogram. The Weighted Wavelet Auto-Correlogram is applied on the High frequency sub bands such as LH, HL and HH of the Y, Cb, and Cr channel...
Cryptography is the art of securing information by making sure that the secret can be understood only by the right person. Steganography is the process of sharing information in an undetectable way by making sure that nobody else can even detect the presence of a secret. If these two methods could be combined, it would provide a fool-proof security to information being communicated over a network...
SSAO(Screen Space Ambient Occlusion) is a global illumination algorithm, it samples the depth information of pixels around each pixel in the screen space to calculate the ambient occlusion caused by the surrounding geometry. It can enhance the sense of space and layering and increase the level of realism. This paper proposes a fast implementation of SSAO, the experimental results demonstrate that...
The fingerprint image preprocessing is the premise and basis for fingerprint identification. It will directly influence the final outcome of fingerprint identification. In order to maintain and restore fingerprint ridge structures, and improve the noise immunity of fingerprint image preprocessing algorithm. In the paper, a method for getting direction image based on gradient is given. Using direction...
This paper deals with a novel steganographic technique which demonstrates the colour image authentication technique in frequency domain based on the Discrete Fourier Transform (DFT). The DFT is applied on sub-image block called mask of size 2 × 2 for frequency components of corresponding spatial component. This transforms process done from beginning to end mask in row major order of the carrier image...
Image super-resolution is the process by which additional information is incorporated to enhance a low resolution image thereby producing a high resolution image. In the simplest case super-resolution of a single image is a process of obtaining high-resolution image with more number of pixels with more resolving power. Therefore the super-resolved image should demonstrate an improvement in the perceived...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.