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.
Aiming at the computational complexity and accuracy of the global motion estimation algorithm, a fast algorithm for global motion estimation is proposed. the algorithm eliminates the adverse effect of foreground object in global estimation and only fully search the particular regions in image to get initial optimal motion vector, then through the improved three-level pyramid multi-resolution model,...
This article describes the optimization real-time implementation of Viola & Jones face detection algorithm, based adaboost, on RISC processor combined with a genetic approach (called AdaBoost/GA). This algorithm detects the faces in image or video sequences, with rate detection about 97% on the basis of image CMU & MIT. In this work we present a study of the algorithm in terms of complexity...
There is an improvement to the Bicubic interpolation enlargement algorithm based on the hardware parallel processing in this article. Search table method used in this paper has avoided massive cubic and the floating numbers multiply operation. It reduces the computation load greatly. Convolution operation in tow directions, level and vertical, of the 4x4 picture element matrix on FPGA has been realized...
Many consumer digital cameras support dual shooting mode of both low-resolution (LR) video and high-resolution (HR) image. By periodically switching between the video and image modes, this type of cameras make it possible to super-resolve the LR video with the assistance of neighboring HR still images. We propose a model-based video super-resolution (VSR) technique for the above dual-mode cameras...
We propose an image stitching method which can compose the images with similar overlapped regions seamlessly. Traditional minimal error boundary (MEB) based method can't produce correct stitching result when the input images exist photometric inconsistency. To cope with the problem, we adopt the weighted sum of gradient and curvature as the robust feature, which represent the primary content of the...
In this paper we propose a new approach for disocclusion removal in depth image-based rendering (DIBR) for 3D-TV. The new approach, Hierarchical Hole-Filling (HHF), eliminates the need for any preprocessing of the depth map. HHF uses a pyramid like approach to estimate the hole pixels from lower resolution estimates of the 3D wrapped image. The lower resolution estimates involves a pseudo zero canceling...
We envision a conference room of the future where depth sensing systems are able to capture the 3D position and pose of users, and enable users to interact with digital media and contents being shown on immersive displays. The key technical barrier is that current depth sensing systems are noisy, inaccurate, and unreliable. It is well understood that passive stereo fails in non-textured, featureless...
This paper describes a novel fast mean shift algorithm based on a resampling technique with marked regular pyramid structure. This new method focuses on solving the problem of high calculation complexity when high data dimension or large data sets are involved in mean shift. By resampling the original image with marked regular pyramid structure, improved method reduces the number of pixels requiring...
This paper proposes a novel face detection method that finds tiny faces located at a long range even with low-resolution input images captured by a moving robot. The proposed approach can locate extremely small-sized face regions of 12x12 pixels by combining the results from mean-shift color tracking, short- and long-range face detection, and omega shape detection. According to the experimental results...
Fractal image compression is a relatively recent image compression method. Its basic idea is to represent images as a fixed point of a contractive Iterated Function System. Spiral Architecture is a novel image structure on which images are displayed as a collection of hexagonal pixels. But till date there are no available image capture or display devices to support this structure. Hence in order to...
Based on the binary image, the thesis proposes a suit of algorithm for the license plate intelligent recognition system serving the expressway toll collection system. Firstly, the algorithm of first difference combined with the method of determining the threshold of binarization via accumulating pixel spots is used in pre-processing. Secondly, taking advantage of the horizontal texture characteristic...
For improving accuracy and robust property of human detection, fusion of image sequences captured from visible-thermal sensors is lucrative. Instead of performing it in pixel-level directly, we try to fuse object features by a novel image sequence fusion algorithm based on gradient feature (GFIF). The GFIF algorithm calculate gradients of input images to form a joint histograms of Oriented Gradient...
This paper proposes an edge-adaptive interpolation algorithm for Super-resolution reconstruction. The objective is to recover high-resolution image from low-resolution image. At first, from a low-resolution image, a high-resolution image is formed by bilinear interpolation and its edges are detected. Then, the edge of the original high-resolution image is refined by two approaches: the first is based...
On the basis of the Bayesian inference using the maximizer of the posterior marginal (MPM) estimate, we formulate the problem of inverse halftoning via the framework of super resolution for the organized dither method. Then, the Monte Carlo simulation for a set of the snapshots of the Q-Ising model clarifies that this method achieves optimal performance under the Bayes-optimal condition and that the...
In this paper, we propose an algorithm for video signature using music videos and news video for our study. The algorithm was developed based on our earlier work with an improvement (reducing the steps) on the process of generating video signature. Thus, revised process reduces the amount of processing time needed tremendously. In addition, besides color as a feature, we introduce the addition of...
Image inpainting is one of the challenging problems in image restoration. To recover the missing region, we can only rely on the information in the uncorrupted region of the input image and some prior knowledge. The latter can be learned from suitable training data or implemented through some smoothness constraints. In this paper, a new approach for image inpainting is proposed. Here, we iteratively...
This paper presents a sequential image stitching approach for creating high-quality panoramic images on mobile devices. In this approach, each source image in the image sequence is stitched onto the panoramic image sequentially using two operations: optimal seam finding and transition smoothing. In the seam finding process, graph cut optimization finds an optimal seam and creates labeling in the overlapping...
A content-based video acquisition system was proposed recently for the power optimization of portable digital devices in. In this scheme, extra computation is required in the pre-analyzing for detecting the spatially and temporally active regions. Moreover, given full-resolution frames (FR) at certain frequency for reference, the adaptive sampling at the high active regions is redundant once proper...
India is a multi-lingual multi-script country, where eighteen official scripts are accepted and there are over hundred regional languages. In this paper we propose a zone-based hybrid feature extraction algorithm scheme towards the recognition of off-line handwritten numerals of two popular south-Indian scripts. The character centroid is computed and the character/numeral image (50 ?? 50) is further...
This paper presents a directional anisotropic correlation model for super resolution reconstruction. A local adaptive correlation model is formed by exploiting local edge direction and anisotropic characteristic. For a local region with presence of edge or texture, a directional anisotropic correlation model is suitable to describe the local correlation while the correlation model tends to be more...
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.