Current Issue : July - September Volume : 2019 Issue Number : 3 Articles : 5 Articles
The task of facial landmark extraction is fundamental in several applications which\ninvolve facial analysis, such as facial expression analysis, identity and face recognition, facial\nanimation, and 3D face reconstruction. Taking into account the most recent advances resulting\nfrom deep-learning techniques, the performance of methods for facial landmark extraction have\nbeen substantially improved, even on in-the-wild datasets. Thus, this article presents an updated\nsurvey on facial landmark extraction on 2D images and video, focusing on methods that make use of\ndeep-learning techniques. An analysis of many approaches comparing the performances is provided.\nIn summary, an analysis of common datasets, challenges, and future research directions are provided....
Quality is a very important parameter for all objects and their functionalities.\nIn image-based object recognition, image quality is a prime criterion. For authentic\nimage quality evaluation, ground truth is required. But in practice, it\nis very difficult to find the ground truth. Usually, image quality is being assessed\nby full reference metrics, like MSE (Mean Square Error) and PSNR\n(Peak Signal to Noise Ratio). In contrast to MSE and PSNR, recently, two\nmore full reference metrics SSIM (Structured Similarity Indexing Method)\nand FSIM (Feature Similarity Indexing Method) are developed with a view to\ncompare the structural and feature similarity measures between restored and\noriginal objects on the basis of perception. This paper is mainly stressed on\ncomparing different image quality metrics to give a comprehensive view. Experimentation\nwith these metrics using benchmark images is performed\nthrough denoising for different noise concentrations. All metrics have given\nconsistent results. However, from representation perspective, SSIM and FSIM\nare normalized, but MSE and PSNR are not; and from semantic perspective,\nMSE and PSNR are giving only absolute error; on the other hand, SSIM and\nPSNR are giving perception and saliency-based error. So, SSIM and FSIM can\nbe treated more understandable than the MSE and PSNR....
Video background modeling is an important preprocessing stage for various applications, and principal component pursuit (PCP) is\namong the state-of-the-art algorithms for this task. One of the main drawbacks of PCP is its sensitivity to jitter and camera\nmovement. This problem has only been partially solved by a few methods devised for jitter or small transformations. However, such\nmethods cannot handle the case of moving or panning cameras in an incremental fashion. In this paper, we greatly expand the results\nof our earlier work, in which we presented a novel, fully incremental PCP algorithm, named incPCP-PTI, which was able to cope with\npanning scenarios and jitter by continuously aligning the low-rank component to the current reference frame of the camera. To the\nbest of our knowledge, incPCP-PTI is the first low-rank plus additive incremental matrix method capable of handling these scenarios\nin an incremental way. The results on synthetic videos and Moseg, DAVIS, and CDnet2014 datasets show that incPCP-PTI is able to\nmaintain a good performance in the detection of moving objects even when panning and jitter are present in a video. Additionally, in\nmost videos, incPCP-PTI obtains competitive or superior results compared to state-of-the-art batch methods....
Haze hampers the performance of vision systems. So, removal of haze appearance\nin a scene should be the first-priority for clear vision. It finds wide\nspectrum of practical applications. A good number of dehazing techniques\nhave already been developed. However, validation with the help of ground\ntruth i.e. simulated haze on a clear image is an ultimate necessity. To address\nthis issue, in this work synthetic haze images with various haze concentrations\nare simulated and then used to confirm the validation task of dark-channel\ndehazing mechanism, as it is a very promising single image dehazing technique.\nThe simulated hazy image is developed using atmospheric model with\nand without Perlin noise. The effectiveness of dark-channel dehazing method\nis confirmed using the simulated haze images through average gradient metric,\nas haze reduces the gradient score....
Whereas modern digital cameras use a pixelated detector array to capture images,\nsingle-pixel imaging reconstructs images by sampling a scene with a series of masks and associating\nthe knowledge of these masks with the corresponding intensity measured with a single-pixel\ndetector. Though not performing as well as digital cameras in conventional visible imaging,\nsingle-pixel imaging has been demonstrated to be advantageous in unconventional applications,\nsuch as multi-wavelength imaging, terahertz imaging, X-ray imaging, and three-dimensional imaging.\nThe developments and working principles of single-pixel imaging are reviewed, a mathematical\ninterpretation is given, and the key elements are analyzed. The research works of three-dimensional\nsingle-pixel imaging and their potential applications are further reviewed and discussed....
Loading....