The inversion of linear systems is a fundamental step in many inverse problems. Computational challenges exist when trying to invert large linear systems, where limited computing resources mean that only part of the s...
详细信息
Automatic extraction of crop organ from images is a crucial step for quantitatively acquiring crop growth information in precision agriculture. There has been some attempt on this task, but the performance is not sati...
详细信息
ISBN:
(纸本)9781509041527
Automatic extraction of crop organ from images is a crucial step for quantitatively acquiring crop growth information in precision agriculture. There has been some attempt on this task, but the performance is not satisfactory. In this paper, we proposed an image-based method based on low-rank matrix recovery to extract organ accurately. In our method, a crop image is considered to be compose of two factors: background and organ. In a certain feature space, the image is represented as a low-rank matrix plus sparse noises. The organ is then extracted by identifying the sparse noises when using low-rank matrix recovery algorithm. In order to ensure the rank of background is low, a linear transform for the feature space is introduced and needs to be learned from historical data. Dynamic threshold segmentation followed by vegetation removing techniques are ultimately adopted in the final step. The experimental results on the benchmark farmland dataset show that our method achieve competitive performance, compared with the other well-established methods, yielding the highest performance of 93.9% with the lowest standard deviation of 2.86%, which means our method is more robust and not sensitive to the complex environmental elements and different cultivars.
Sputum smear conventional microscopy (CM) is used as primary bacteriological test for detection of TB. This technique is the most preferred technique in low and middle income countries due to its availability as well ...
详细信息
ISBN:
(纸本)9781509036691
Sputum smear conventional microscopy (CM) is used as primary bacteriological test for detection of TB. This technique is the most preferred technique in low and middle income countries due to its availability as well as accessibility. Manual screening of bacilli using CM is time consuming and labor intensive. As a result, the sensitivity of TB detection is compromised leading to misdiagnosis 33-50% of active cases. Automated methods can increase the sensitivity and specificity of TB detection. Currently, the remote areas of TB-endemic developing countries have easy accessibility to portable and camera-enabled Smartphone microscope for capturing images from ZN-stained smear slide. In this paper, the performance of watershed segmentation method for detection and classification of bacilli from camera-enable Smartphone microscopic images is presented. Several preprocessing techniques have been implemented prior to watershed segmentation. Current method has achieved the sensitivity and specificity of 93.3% and 87% respectively for classifying an image as TB positive or negative.
The summed-area table ( SAT), also known as integral image, is a data structure extensively used in computer graphics and vision for fast image filtering. The parallelization of its construction has been thoroughly in...
详细信息
ISBN:
(纸本)9783319436593;9783319436586
The summed-area table ( SAT), also known as integral image, is a data structure extensively used in computer graphics and vision for fast image filtering. The parallelization of its construction has been thoroughly investigated and many algorithms have been proposed for GPUs. Generally speaking, state-of-the-art methods cannot efficiently solve this problem in multi-core and many-core (Xeon Phi) systems due to cache misses, strided and/or remote memory accesses. This work proposes three novel cache-aware parallel SAT algorithms, which generalize parallel block-based prefix-sums algorithms. In addition, we discuss 2D matrix partitioning policies which play an important role in the efficient operation of the cache subsystem. The combination of a SAT algorithm and a partition is manually tuned according to the matrix layout and the number of threads. Experimental evaluation of our algorithms on two NUMA systems and Intel's Xeon Phi, and for three datatypes (int, float, double) by utilizing all system cores, shows, in all experimental settings, better performance compared to the best known CPU and GPU approaches (up to 4.55x on NUMA and 2.8x on Xeon Phi).
Bayesian methods and their implementations by means of sophisticated Monte Carlo techniques have become very popular in signal processing over the last years. Importance Sampling (IS) is a well-known Monte Carlo techn...
详细信息
High-dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumptio...
详细信息
High-dimensional data arising from diverse scientific research fields and industrial development have led to increased interest in sparse learning due to model parsimony and computational advantage. With the assumption of sparsity, many computational problems can be handled efficiently in practice. Structured sparse learning encodes the structural information of the variables and has been quite successful in numerous research fields. With various types of structures discovered, sorts of structured regularizations have been proposed. These regularizations have greatly improved the efficacy of sparse learning algorithms through the use of specific structural information. In this article, we present a systematic review of structured sparse learning including ideas, formulations, algorithms, and applications. We present these algorithms in the unified framework of minimizing the sum of loss and penalty functions, summarize publicly accessible software implementations, and compare the computational complexity of typical optimization methods to solve structured sparse learning problems. In experiments, we present applications in unsupervised learning, for structured signal recovery and hierarchical image reconstruction, and in supervised learning in the context of a novel graph-guided logistic regression.
Steganography is a hiding information technique heavily used nowadays. Though initially it was used to establish hidden communication channels, modern steganography has been found useful to hide code inside multimedia...
详细信息
Single image super-resolution reconstruction is a challenging ill-posed inverse problem currently. In this paper, we propose a method based on image classification and sparse representation for single image super-reso...
详细信息
The scale of functional magnetic resonance image data is rapidly increasing as large multi-subject datasets are becoming widely available and high-resolution scanners are adopted. The inherent low-dimensionality of th...
详细信息
ISBN:
(纸本)9781467390057
The scale of functional magnetic resonance image data is rapidly increasing as large multi-subject datasets are becoming widely available and high-resolution scanners are adopted. The inherent low-dimensionality of the information in this data has led neuroscientists to consider factor analysis methods to extract and analyze the underlying brain activity. In this work, we consider two recent multi-subject factor analysis methods: the Shared Response Model and the Hierarchical Topographic Factor Analysis. We perform analytical, algorithmic, and code optimization to enable multi-node parallel implementations to scale. Single-node improvements result in 99x and 2062x speedups on the two methods, and enables the processing of larger datasets. Our distributed implementations show strong scaling of 3.3x and 5.5x respectively with 20 nodes on real datasets. We demonstrate weak scaling on a synthetic dataset with 1024 subjects, equivalent in size to the biggest fMRI dataset collected until now, on up to 1024 nodes and 32,768 cores.
暂无评论