Search

The first step in a scale invariant image matching system is scale space generation. Nonlinear scale space generation algorithms such as AKAZE, reduce noise and distortion in different scales while retaining the borders and key-points of the image. An FPGA-based hardware architecture for AKAZE nonlinear scale space generation is proposed to speed up this algorithm for real-time applications. The three contributions of this work are (1) mapping the two passes of the AKAZE algorithm onto a hardware architecture that realizes parallel processing of multiple sections, (2) multi-scale line buffers which can be used for different scales, and (3) a time-sharing mechanism in the memory management unit to process multiple sections of the image in parallel. We propose a time-sharing mechanism for memory management to prevent artifacts as a result of separating the process of image partitioning. We also use approximations in the algorithm to make hardware implementation more efficient while maintaining the repeatability of the detection. A frame rate of 304 frames per second for a 1280 × 768 image resolution is achieved which is favorably faster in comparison with other work. [ABSTRACT FROM AUTHOR]

Retina images acquired by an adaptive optics confocal scanning laser ophthalmoscope (AOSLO) usually need to remove image warp to improve image quality. The most significant task of AOSLO image dewarping is image registration. Most traditional feature-based registration algorithms used for AOSLO images are based on Gaussian scale space. However, the homogeneous Gaussian blurring reduces the localization accuracy of feature points and the distinctiveness of feature descriptors. In this paper, the accelerated KAZE (AKAZE) feature based on nonlinear scale space was utilized to register AOSLO retinal images for the first time, and an efficient strategy based on matched feature points for frame selection was proposed to automatically accomplish AOSLO retinal image dewarping. Moreover, a flexible method based on power spectra analysis is proposed to study the minimum number of frames needed to accomplish image dewarping. The extensive experiments demonstrated that the AKAZE method is more suitable for AOSLO image dewarping, benefitted with better accuracy, robustness, and rapidity compared with several traditional registration methods based on Gaussian scale space.

The recently proposed, KAZE image feature detection and description algorithm (Alcantarilla et al. in Proceedings of the British machine vision conference. LNCS, vol 7577, no 6, pp 13.1–13.11, 2013) offers significantly improved robustness in comparison to conventional algorithms like SIFT (scale-invariant feature transform) and SURF (speeded-up robust features). The improved robustness comes at a significant computational cost, however, limiting its use for many applications. We report a GPU acceleration of the KAZE algorithm that is significantly faster than its CPU counterpart. Unlike previous reports, our acceleration does not resort to binary descriptors and can serve as a drop-in replacement for CPU-KAZE, SIFT, SURF etc. By achieving nearly tenfold speedup (for a 1920 by 1200 sized image, our Compute Unified Device Architecture (CUDA)-C implementation took around 245 ms on a single GPU in comparison to nearly 2400 ms for a 16-threaded CPU version) without degradation in feature extraction performance, our work expands the applicability of the KAZE algorithm. Additionally, the strategies described here could also prove useful for the GPU implementation of other nonlinear scale-space-based image processing algorithms. [ABSTRACT FROM AUTHOR]

Aiming at the inaccuracy of embedding watermarking location and random selection of embedding intensity parameters, this paper proposed a nonlinear scale space adaptive equalization watermarking algorithm. It used KAZE algorithm to extract and filter the feature points with strong stability in nonlinear scale space for constructing the watermark region. Then it used singular value decomposition on watermarking image, it constructed a new matrix as the watermarking carrier to be embedded and calculated the embedding intensity by adjusting the fitness function of the fruit fly optimization algorithm. And with the DWT-SVD algorithm, it adaptively completed the watermark embedding process. Extracting the feature points from the under attack watermark image to synthesize the feature region matrix, it used inverse process to extract watermark image. The experimental results show that the PSNR values are above 44 dB and the average NC value is as high as 0.99, which effectively equalizes the invisibility and robustness of the watermarking algorithm [ABSTRACT FROM AUTHOR]

Abstract: A novel nonlinear scale space framework is proposed for the purpose of multi-scale image representation. The scale space decomposition problem is formulated as a general Bayesian least-squares estimation problem. A quasi-random density estimation approach is introduced for estimating the posterior distribution between consecutive scale space realizations. In addition, the application of the proposed nonlinear scale space framework for edge detection is proposed. Experimental results demonstrate the effectiveness of the proposed scale space framework for constructing scale space representations with significantly better structural localization across all scales when compared to state-of-the-art scale space frameworks such as anisotropic diffusion, regularized nonlinear diffusion, complex nonlinear diffusion, and iterative bilateral scale space methods, especially under scenarios with high noise levels. [ABSTRACT FROM AUTHOR]

Abstract: In this work, we analyse a series of approaches to evolve images. It is motivated by combining Gaussian blurring, the Mean Curvature Motion, used for denoising and edge-preserving, and maximal blurring, used for inpainting. We investigate the generalised method using the combination of second-order derivatives in terms of gauge coordinates. For the qualitative behaviour, we derive a solution of the series and mention its properties briefly. Relations with anisotropy and general diffusion equations are discussed. Quantitative results are obtained by a novel implementation whose stability is analysed. The practical results are visualised on a real-life image, showing the expected qualitative behaviour. When a constraint is added that penalises the distance of the results to the input image, one can vary the desired amount of blurring and denoising. [Copyright &y& Elsevier]

In this paper we consider the problem of unsupervised boundary localization in textured images reporting a parallel texture separation algorithm which extracts textural density gradients by a nonlinear multiple scale-space analysis of the image. The scale-space analysis is modeled by a differential morphological filter, and texture boundaries are extracted by segmenting the images resulting from a multiscale fuzzy gradient operation applied to the detail images, which are the differences between images at successive scales. Experiments and comparisons on Brodatz real textures are reported. [Copyright &y& Elsevier]

Segmentation of MR brain images using intensity values is severely limited owing to field inhomogeneities, susceptibility artifacts and partial volume effects. Edge based segmentation methods suffer from spurious edges and gaps in boundaries. A multiscale method to MRI brain segmentation is presented which uses both edge and intensity information. First a multiscale representation of an image is created, which can be made edge dependent to favor intra-tissue diffusion over inter-tissue diffusion. Subsequently a multiscale linking model (the hyperstack) is used to group voxels into a number of objects based on intensity. It is shown that both an improvement in accuracy and a reduction in image post-processing can be achieved if edge dependent diffusion is used instead of linear diffusion. The combination of edge dependent diffusion and intensity based linking facilitates segmentation of grey matter, white matter and cerebrospinal fluid with minimal user interaction. To segment the total brain (white matter plus grey matter) morphological operations are applied to remove small bridges between the brain and cranium. If the total brain is segmented, grey matter, white matter and cerebrospinal fluid can be segmented by joining a small number of segments. Using a supervised segmentation technique and MRI simulations of a brain phantom for validation it is shown that the errors are in the order of or smaller than reported in literature. [ABSTRACT FROM AUTHOR]