Frequency: Quarterly E- ISSN: 2277-2332 P- ISSN: Awaited Abstracted/ Indexed in: Ulrich's International Periodical Directory, Google Scholar, SCIRUS, Genamics JournalSeek, EBSCO Information Services
Quarterly published "Inventi Impact: Image & Video Processing" publishes high quality unpublished, as well as high impact pre-published research and reviews related to graphical tools to visualize, manipulate and process images and videos. The journal includes medical imaging besides many other application areas.
Face landmarking, defined as the detection and localization of certain characteristic points on the face, is an important\r\nintermediary step for many subsequent face processing operations that range from biometric recognition to the\r\nunderstanding of mental states. Despite its conceptual simplicity, this computer vision problem has proven extremely\r\nchallenging due to inherent face variability as well as the multitude of confounding factors such as pose, expression,\r\nillumination and occlusions. The purpose of this survey is to give an overview of landmarking algorithms and their\r\nprogress over the last decade, categorize them and show comparative performance statistics of the state of the art.\r\nWe discuss the main trends and indicate current shortcomings with the expectation that this survey will provide\r\nfurther impetus for the much needed high-performance, real-life face landmarking operating at video rates....
Accurate 3D measuring systems thrive in the past few years. Most of them are based on laser scanners because\nthese laser scanners are able to acquire 3D information directly and precisely in real time. However, comparing to\nthe conventional cameras, these kinds of equipment are usually expensive and they are not commonly available to\ncustomers. Moreover, laser scanners interfere easily with each other sensors of the same type. On the other hand,\ncomputer vision-based 3D measuring techniques use stereo matching to acquire the cameras� relative position and\nthen estimate the 3D location of points on the image. Because this kind of systems needs additional estimation of\nthe 3D information, systems with real time capability often relies on heavy parallelism that prevents implementation\non mobile devices.\nInspired by the structure from motion systems, we propose a system that reconstructs sparse feature points to a 3D\npoint cloud using a mono video sequence so as to achieve higher computation efficiency. The system keeps tracking\nall detected feature points and calculates both the amount of these feature points and their moving distances. We\nonly use the key frames to estimate the current position of the camera in order to reduce the computation load and\nthe noise interference on the system. Furthermore, for the sake of avoiding duplicate 3D points, the system\nreconstructs the 2D point only when the point shifts out of the boundary of a camera. In our experiments, we show\nthat our system is able to be implemented on tablets and can achieve state-of-the-art accuracy with a denser point\ncloud with high speed....
Visual quality and algorithm efficiency are two main interests in video frame\ninterpolation. We propose a hybrid task-based convolutional neural network for fast and accurate\nframe interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then\nreconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to\npreserve high-frequency information and make the synthesized frames look sharper. Experimental\nresults show that the proposed method achieves state-of-the-art performance and performs 2.69x\nfaster than the existing methods that are operable for 4K videos, while maintaining comparable\nvisual and quantitative quality....
RGB-D cameras offer both color and depth images of the surrounding environment, making\nthem an attractive option for robotic and vision applications. This work introduces the BRISK_D\nalgorithm, which efficiently combines Features from Accelerated Segment Test (FAST) and Binary\nRobust Invariant Scalable Keypoints (BRISK) methods. In the BRISK_D algorithm, the keypoints are\ndetected by the FAST algorithm and the location of the keypoint is refined in the scale and the space.\nThe scale factor of the keypoint is directly computed with the depth information of the image. In\nthe experiment, we have made a detailed comparative analysis of the three algorithms SURF, BRISK\nand BRISK_D from the aspects of scaling, rotation, perspective and blur. The BRISK_D algorithm\ncombines depth information and has good algorithm performance....
In this paper, we present a forward collision warning application for smartphones that\nuses license plate recognition and vehicular communication to generate warnings for notifying the\ndrivers of the vehicle behind and the one ahead, of a probable collision when the vehicle behind does\nnot maintain an established safe distance between itself and the vehicle ahead. The application was\ntested in both static and mobile scenarios, from which we confirmed the working of our application,\neven though its performance is affected by the hardware limitations of the smartphones....
Image quality is a vital criterion that guides the technical development of digital cameras. Traditionally, the image\r\nquality of digital cameras has been measured using test-targets and/or subjective tests. Subjective tests should be\r\nperformed using natural images. It is difficult to establish the relationship between the results of artificial test\r\ntargets and subjective data, however, because of the different test image types. We propose a framework for\r\nobjective image quality metrics applied to natural images captured by digital cameras. The framework uses\r\nreference images captured by a high-quality reference camera to find image areas with appropriate structural\r\nenergy for the quality attribute. In this study, the framework was set to measure sharpness. Based on the results,\r\nthe mean performance for predicting subjective sharpness was clearly higher than that of the state-of-the-art\r\nalgorithm and test-target sharpness metrics....
For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs\r\nto be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such\r\nconditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each\r\nblock location a representative set is maintained which contains distinct blocks obtained along its temporal line. The background\r\nestimation is carried out in a Markov Random Field framework, where the optimal labelling solution is computed using iterated\r\nconditional modes. The clique potentials are computed based on the combined frequency response of the candidate block and its\r\nneighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial\r\ncontinuity of structures within a scene. Experiments on real-life surveillance videos demonstrate that the proposedmethod obtains\r\nconsiderably better background estimates (both qualitatively and quantitatively) than median filtering and the recently proposed\r\nââ?¬Å?intervals of stable intensityââ?¬Â method. Further experiments on theWallflower dataset suggest that the combination of the proposed\r\nmethod with a foreground segmentation algorithm results in improved foreground segmentation....
This paper proposes an object-tracking algorithm with multiple randomlygenerated\nfeatures. We mainly improve the tracking performance which is\nsometimes good and sometimes bad in compressive tracking. In compressive\ntracking, the image features are generated by random projection. The resulting\nimage features are affected by the random numbers so that the results of\neach execution are different. If the obvious features of the target are not captured,\nthe tracker is likely to fail. Therefore the tracking results are inconsistent\nfor each execution. The proposed algorithm uses a number of different\nimage features to track, and chooses the best tracking result by measuring the\nsimilarity with the target model. It reduces the chances to determine the target\nlocation by the poor image features. In this paper, we use the Bhattacharyya\ncoefficient to choose the best tracking result. The experimental results show\nthat the proposed tracking algorithm can greatly reduce the tracking errors.\nThe best performance improvements in terms of center location error,\nbounding box overlap ratio and success rate are from 63.62 pixels to 15.45\npixels, from 31.75% to 64.48% and from 38.51% to 82.58%, respectively....
Image denoising is an important first step to provide cleaned images for follow-up tasks such as image segmentation\nand object recognition. Many image denoising filters have been proposed, with most of the filters focusing on one\nparticular type of additive or multiplicative noise. In this article, we propose a novel neighborhood regression\napproach. Using the neighboring pixels as predictors, our approach has superb performance over multiple types of\nnoises, including Gaussian, Poisson, Gaussian and Poisson, salt & pepper, and stripped noise. Our L2 regression filter\ncan be parallelized to significantly speed up the denoising process to process a large number of noisy images.\nMeanwhile, our regression approach does not need tuning parameters or any training images, and it does not need\nany prior knowledge of the variance of the noise. Instead, our regression filter can accurately estimate the variance of\nthe added Gaussian noise. We have performed extensive experiments, comparing our regression filter with the\npopular denoising filters, including BM3D, median filter, and wavelet filter, to demonstrate the superb performance of\nour proposed regression filter....
In this paper, we propose a new variational model for image restoration by incorporating a nonlocal TV regularizer\nand a nonlocal Laplacian regularizer on the image. The two regularizing terms make use of nonlocal comparisons\nbetween pairs of patches in the image. The new model can be seen as a nonlocal version of the CEP-L2 model.\nSubsequently, an algorithm combining the alternating directional minimization and the split Bregman iteration is\npresented to solve the new model. Numerical results verified that the proposed method has better performance for\nimage restoration than CEP-L2 model, especially for low noised images....
Loading....