Automatic Target Generation Process Research Articles

A Novel Dictionary Learning Algorithm Based on Prior Knowledge for fMRI Data Analysis

ABSTRACTTask‐based functional magnetic resonance imaging (fMRI) has been widely utilized for brain activation detection and functional network analysis. In recent years, the K‐singular value decomposition (K‐SVD) algorithm has gained increasing attention in the research of fMRI data analysis methods. In this study, we propose a novel temporal feature region‐growing constrained K‐SVD algorithm that incorporates task‐based fMRI temporal prior knowledge and utilizes a region‐growing algorithm to infer potential activation locations. The algorithm incorporates temporal and spatial constraints to enhance the detection of brain activation. Specifically, this paper improves the three stages of the traditional K‐SVD algorithm. First, in the dictionary initialization stage, the automatic target generation process with an independent component analysis algorithm is utilized in conjunction with prior knowledge to enhance the accuracy of initialization. Second, in the sparse coding stage, the region‐growing algorithm is employed to infer potential activation locations based on temporal prior knowledge, thereby imposing spatial constraints to limit the extent of activation regions. Finally, in the dictionary learning stage, soft constraints and low correlation constraints are applied to reinforce the consistency with prior knowledge and enhance the robustness of learning for task‐related atoms. The proposed method was validated on simulated and real fMRI data, showing superior performance in detecting brain activation compared with traditional methods. The results indicate that the algorithm accurately identifies activated brain regions, providing an effective approach for studying brain function in clinical applications.

Hyperspectral endmember extraction using convexity based purity index

The endmember extraction is a challenging problem in spectral unmixing (SU) of a mixed pixel in hyperspectral imagery. There are plenty of attempts to solve the endmember extraction problem. Still, the pure pixel assumption-based algorithms have probably been used most in solving the endmember extraction of SU due to the light computational burden. These pure pixel assumption-based algorithms usually follow one of the criteria: (1) Maximum simplex volume or (2) Extreme projection on a subspace. We propose a novel integrated framework that uses both the criteria mentioned above and the proposed one is referred to as the Convexity-based Pure Index (CPI) algorithm. The CPI generates a fixed number of convex sets based on the number of available bands in the hyperspectral image. The algorithm defines the purity score based on the availability of pixels in the convex sets for the two-band data. The CPI has been compared with contemporary algorithms such as Automatic Target Generation Process (ATGP), Vertex Component Analysis (VCA), Pixel Purity Index (PPI), Successive Volume MAXimization (SVMAX), Alternating Volume MAXimization (AVMAX), TRIple-P: P-norm based Pure Pixel identification (TRIP), Successive Decoupled Volume Max–Min (SDVMM), Negative ABundance-Oriented (NABO), and Entropy-based Convex Set Optimization (ECSO). The metrics, Spectral Angle Distance (SAD) and Spectral Information Divergence (SID) used in the comparison were improved up to 5.9% and 9%, respectively. The CPI outperforms prevailing algorithms on real benchmark data and new AVIRIS-NG data. The robustness of the CPI is also tested for various noisy synthetic data. The efficacy of the proposed algorithm is also tested by using qualitative analysis by visualizing the spectra comparison, and abundance maps for all real data.

An initially robust minimum simplex volume-based method for linear hyperspectral unmixing

ABSTRACT Initialization plays an important role in the accuracy of endmember extraction algorithms (EEAs) in linear hyperspectral unmixing (LHU). Random initialization can lead to varying endmembers generated by EEAs. To address this challenge, an initialization strategy has been introduced, encompassing vertex component analysis (VCA), automatic target generation process (ATGP), among others. These techniques significantly contribute to enhancing the accuracy of EEAs. However, complex initialization is sometimes less preferable, prompting the unexplored question of whether there exists an EEA robust to initialization. This paper focuses on analyzing this issue within the context of minimum simplex volume-based (MV) methods, which have received considerable attention in the past two decades due to their robustness against the absence of pure pixels. MV methods typically formulate LHU as an optimization problem, most of which includes a non-convex volume term. Additionally, many MV methods use VCA as an initialization strategy. Firstly, this paper demonstrates that the variable splitting augmented Lagrangian approach (SISAL), as a representative non-convex MV method, heavily depends on initialization. To our knowledge, the impact of initialization for MV methods has not been thoroughly analyzed before. Furthermore, this paper proposes an initially robust MV method by introducing a new convex MV term. Numerical experiments conducted on simulated and real datasets demonstrate its outstanding performance in accuracy and robustness to initialization. Throughout the experiments the proposed method proves to be the most stable, which is crucial in real scene where the ground truth is unknown beforehand.

The Automated Detection of Fusarium Wilt on Phalaenopsis Using VIS-NIR and SWIR Hyperspectral Imaging

Phalaenopsis, an essential flower for export, is significantly affected by fusarium wilt, which impacts its export quality. Hyperspectral imaging technology offers the potential to detect fusarium wilt on Phalaenopsis. The goal of this study was to establish an automated platform for the rapid detection of fusarium wilt on Phalaenopsis. In this research, the automatic target generation process (ATGP) method was employed to identify outliers in the hyperspectral spectrum. Subsequently, the Spectral Angle Mapper (SAM) method was utilized to detect signals similar to the outliers. To suppress background noise and extract the region of interest (ROI), the Constrained Energy Minimization (CEM) method was implemented. For ROI classification and detection, a deep neural network (DNN), a support vector machine (SVM), and a Random Forest Classifier (RFC) were employed. Model performance was evaluated using three-dimensional receiver operating characteristics (3D ROC), and the automated identification system was integrated into hyperspectrometers. The proposed system achieved an accuracy of 95.77% with a total detection time of 3380 ms ± 86.36 ms, proving to be a practical and effective tool for detecting fusarium wilt on Phalaenopsis in the industry.

SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION

Abstract. Written information on the surface of cultural relics can record important historical events. Due to the influence of natural and human factors, the surface of cultural relics fades and the words are difficult to identify. Take advantage of the hyperspectral data image and spectral unity and wide spectral range, a cultural relics surface handwriting enhancement method based on manifold learning and mixed pixel decomposition was proposed. First, the minimum noise fraction (MNF) transformation was carried out on the hyperspectral image, and then the top 10 bands were selected for inverse MNF transformation to reduce noise of the hyperspectral image. Then, the reconstructed image was dimensionally reduced by locally linear embedding (LLE) to obtain a gray image with the maximum amount of information. At the same time, the spectral features of the handwriting and background area in the reconstructed image were analysed. The automatic target generation process (ATGP) was adopted for endmember extraction on the reconstructed image to identify the endmember of handwriting. The abundance map of handwriting area was obtained by the fully constrained least squares (FCLS). Finally, the gray image and the abundance map of the handwriting region were weighted together to obtain the handwriting enhanced image. The true color image was synthesized from the reconstructed image, Then the true color image and the handwriting enhancement image were fused to obtain the handwritting fusion image. The hyperspectral image of a faded text in Shuozhou City, Shanxi Province, China, was used as an example for verification, and the results showed that the method can effectively enhance the text on the surface of the artifacts.

A New Endmember Extraction Method Based on Least Squares

Endmember extraction is frequently adopted to detect spectrally unique signatures of pure ground materials in hyperspectral imagery. These endmembers are the purest pixels in the HSI data cubes. Every pixel in a HSI data cube can be expressed as a linear combination of a finite number of endmembers. In this paper, we propose a novel method for endmember extraction by means of least squares. We perform minimum noise fraction to reduce the dimensionality of the data cube, initialize the endmembers by using automatic target generation process, compute the abundance map from the dimensionality reduced data cube and the initial endmembers, and calculate the final endmembers by using least squares. Our proposed method is comparable to and sometimes outperforms existing methods in term of spectral angle distance for all four testing data cubes for endmember extraction. In addition, our method is relatively fast as well because it only performs quite simple operations to find endmembers in the testing hyperspectral data cubes.

Interference-Suppressed and Cluster-Optimized Hyperspectral Target Extraction Based on Density Peak Clustering

Target extraction can provide a prior knowledge for spectral unmixing, unsupervised hyperspectral image classification, and unsupervised target detection tasks, which is of great practice. Considering that the traditional endmember extraction algorithms such as automatic target generation process (ATGP) and simplex growing algorithm (SGA) are sensitive to the burst noise caused by hyperspectral sensor imaging and cannot extract the appropriate target set to simultaneously guide the various tasks, a weighted target extraction algorithm based on the density peak clustering (DPC) is proposed in this article. First, DPC is extended to hyperspectral images, and the decision graph is generated according to the density and distance of each pixel to effectively classify the regions with different attributes such as burst noise, cluster center, cluster boundary, and cluster core. On the basis, three DPC-based weighted vectors are designed, and the weighted target extraction algorithms W-ATGP and W-SGA are put forward which allocates a lower weight than the core pixel to the interference so as to reduce its impact on ATGP and SGA while obtaining the high-quality targets for various tasks. The experimental results on three datasets show that the accuracies of the target sets extracted by W-ATGP and W-SGA are higher than that of ATGP and SGA, no matter as the prior knowledge of spectral unmixing, unsupervised hyperspectral image classification, or unsupervised target detection, which verifies the effectiveness of the proposed methods.

Orthogonal Subspace Projection Target Detector for Hyperspectral Anomaly Detection

Orthogonal subspace projection (OSP) is a versatile hyperspectral imaging technique which has shown great potential in dimensionality reduction, target detection, spectral unmixing, etc. However, due to its inherent requirement of prior target knowledge, OSP has not been explored in anomaly detection. This article takes advantage of an unsupervised OSP-based algorithm, automatic target generation process (ATGP), and a recently developed OSP-go decomposition (OSP-GoDec) along with data sphering (DS) to make OSP applicable to anomaly detection. Its idea is to implement ATGP on the background (BKG) and target subspaces constructed from the low-rank matrix L and sparse matrix S generated by OSP-GoDec to derive an OSP-based anomaly detector (OSP-AD). In particular, OSP-AD also includes DS to remove BKG interference from the target subspace so as to enhance anomaly detection. Surprisingly, operating data samples on different constructions of the BKG subspace and the target subspace yields various versions of OSP-AD. Experiments show that given an appropriate construction of the BKG subspace and the target subspace, OSP-AD can be shown to outperform existing anomaly detectors including Reed-Xiaoli anomaly detector and collaborative representation-based anomaly detector (CRD).

Hyperspectral Target Detection Using Gram-Schmidt Orthogonal Projections

The automatic detection of targets in the hyperspectral images is highly used in defense and security applications. Hyperspectral images are rich in information due to its high spectral and spatial resolution. In this paper, we use Automatic Target Generation Process (ATGP) to extract the endmembers from the hyperspectral image. We compared the performance of Gram-Schmidt orthogonal vector projection (GSOVP) with the classical Orthogonal Subspace Projection (OSP). In our experiments, we used HYDICE and ROSIS urban datasets for evaluating the performance of the optimized algorithm.

Breast Tumor Detection and Classification Using Intravoxel Incoherent Motion Hyperspectral Imaging Techniques.

Breast cancer is a main cause of disease and death for women globally. Because of the limitations of traditional mammography and ultrasonography, magnetic resonance imaging (MRI) has gradually become an important radiological method for breast cancer assessment over the past decades. MRI is free of the problems related to radiation exposure and provides excellent image resolution and contrast. However, a disadvantage is the injection of contrast agent, which is toxic for some patients (such as patients with chronic renal disease or pregnant and lactating women). Recent findings of gadolinium deposits in the brain are also a concern. To address these issues, this paper develops an intravoxel incoherent motion- (IVIM-) MRI-based histogram analysis approach, which takes advantage of several hyperspectral techniques, such as the band expansion process (BEP), to expand a multispectral image to hyperspectral images and create an automatic target generation process (ATGP). After automatically finding suspected targets, further detection was attained by using kernel constrained energy minimization (KCEM). A decision tree and histogram analysis were applied to classify breast tissue via quantitative analysis for detected lesions, which were used to distinguish between three categories of breast tissue: malignant tumors (i.e., central and peripheral zone), cysts, and normal breast tissues. The experimental results demonstrated that the proposed IVIM-MRI-based histogram analysis approach can effectively differentiate between these three breast tissue types.

A Novel FPGA-Based Architecture for Fast Automatic Target Detection in Hyperspectral Images

Onboard target detection of hyperspectral imagery (HSI), considered as a significant remote sensing application, has gained increasing attention in the latest years. It usually requires processing huge volumes of HSI data in real-time under constraints of low computational complexity and high detection accuracy. Automatic target generation process based on an orthogonal subspace projector (ATGP-OSP) is a well-known automatic target detection algorithm, which is widely used owing to its competitive performance. However, ATGP-OSP has an issue to be deployed onboard in real-time target detection due to its iteratively calculating the inversion of growing matrices and increasing matrix multiplications. To resolve this dilemma, we propose a novel fast implementation of ATGP (Fast-ATGP) while maintaining target detection accuracy of ATGP-OSP. Fast-ATGP takes advantage of simple regular matrix add/multiply operations instead of increasingly complicated matrix inversions to update growing orthogonal projection operator matrices. Furthermore, the updated orthogonal projection operator matrix is replaced by a normalized vector to perform the inner-product operations with each pixel for finding a target per iteration. With these two major optimizations, the computational complexity of ATGP-OSP is substantially reduced. What is more, an FPGA-based implementation of the proposed Fast-ATGP using high-level synthesis (HLS) is developed. Specifically, an efficient architecture containing a bunch of pipelines being executed in parallel is further designed and evaluated on a Xilinx XC7VX690T FPGA. The experimental results demonstrate that our proposed FPGA-based Fast-ATGP is able to automatically detect multiple targets on a commonly used dataset (AVIRIS Cuprite Data) at a high-speed rate of 200 MHz with a significant speedup of nearly 34.3 times that of ATGP-OSP, while retaining nearly the same high detection accuracy.

An Endmember Initialization Scheme for Nonnegative Matrix Factorization and Its Application in Hyperspectral Unmixing

Nonnegative matrix factorization (NMF) is a blind source separation (BSS) method often used in hyperspectral unmixing. However, it tends to converge to a local optimum. To overcome this limitation, we present a simple, but effective endmember initialization scheme for NMF, which is realized by improving initial values through the application of the automatic target generation process (ATGP) algorithm. The initial spectra and abundances of target endmembers are first obtained using the ATGP algorithm and nonnegative least squares (NNLS) method, respectively. The preliminary results are then optimized through iterative application of NMF. To validate the applicability and effectiveness of the proposed method, we analyzed the improvement of NMF by the ATGP algorithm, using the synthetic hyperspectral data and real hyperspectral images. The results from the proposed method are compared with those of the vertex component analysis (VCA)-NMF algorithm, which uses the VCA algorithm to perform initialization for NMF, the minimum volume constrained NMF (MVC-NMF) algorithm, the traditional two-step VCA-fully-constrained least squares (FCLS) algorithm, which uses the VCA to extract the endmember matrix, and the FCLS algorithm to estimate the abundance matrix. The comparison results prove that proper endmember initialization can help the NMF algorithm yield better estimation results. Through the optimization of target endmembers’ initial values, the proposed ATGP-NMF algorithm can consistently produce good results at a lower computational cost, especially in the case of a real hyperspectral image for which pure pixels do not exist and there is little prior knowledge. With its high applicability and effectiveness, the ATGP-NMF algorithm has a great potential to solve hyperspectral unmixing problems.

Brain Functional Plasticity Driven by Career Experience: A Resting-State fMRI Study of the Seafarer.

The functional connectome derived from BOLD resting-state functional magnetic resonance imaging data represents meaningful functional organizations and a shift between distinct cognitive states. However, the body of knowledge on how the long-term career experience affects the brain’s functional plasticity is still very limited. In this study, we used a dynamic functional connectome characterization (DBFCC) model with the automatic target generation process K-Means clustering to explore the functional reorganization property of resting brain states, driven by long-term career experience. Taking sailors as an example, DBFCC generated seventeen reproducibly common atomic connectome patterns (ACP) and one reproducibly distinct ACP, i.e., ACP14. The common ACPs indicating the same functional topology of the resting brain state transitions were shared by two control groups, while the distinct ACP, which mainly represented functional plasticity and only existed in the sailors, showed close relationships with the long-term career experience of sailors. More specifically, the distinct ACP14 of the sailors was made up of four specific sub-networks, such as the auditory network, visual network, executive control network, and vestibular function-related network, which were most likely linked to sailing experience, i.e., continuously suffering auditory noise, maintaining balance, locating one’s position in three-dimensional space at sea, obeying orders, etc. Our results demonstrated DBFCC’s effectiveness in revealing the specifically functional alterations modulated by sailing experience and particularly provided the evidence that functional plasticity was beneficial in reorganizing brain’s functional topology, which could be driven by career experience.

Recursive Band Processing of Automatic Target Generation Process for Finding Unsupervised Targets in Hyperspectral Imagery

Automatic target generation process (ATGP) has been widely used for unsupervised target detection. However, as designed, it detects targets using full-band information. Unfortunately, on many occasions, various targets can be detected using varying bands, and ATGP can only provide one-shot target detection with all bands being used. This paper develops a new approach which can implement ATGP bandwise in a progressive manner, called progressive band processing of ATGP (PBP-ATGP) so that ATGP can be carried out band by band. Since PBP-ATGP must repeatedly implement orthogonal projections, recursive equations are further derived for PBP-ATGP, to be called recursive band processing of ATGP (RBP-ATGP) which can implement PBP-ATGP recursively. As a result, many advantages can be benefited from RBP-ATGP. Most importantly, RBP-ATGP can generate 3-D interband progressive profiles from band to band that can be used for progressive target detection, a task for which no target detection techniques using full-band information can provide.

FPGA Implementation of an Algorithm for Automatically Detecting Targets in Remotely Sensed Hyperspectral Images

Timely detection of targets continues to be a relevant challenge for hyperspectral remote sensing capability. The automatic target-generation process using an orthogonal projection operator (ATGP-OSP) has been widely used for this purpose. Hyperspectral target-detection applications require timely responses for swift decisions, which depend upon (near) real-time performance of algorithm analysis. Reconfigurable field-programmable gate arrays (FPGAs) are promising platforms that allow hardware/software codesign and the potential to provide powerful onboard computing capabilities and flexibility at the same time. In this paper, we present an FPGA implementation for the ATGP-OSP algorithm. Our system includes a direct memory access module and implements a prefetching technique to hide the latency of the input/output communications. The proposed method has been implemented on a Virtex-7 XC7VX690T FPGA and tested using real hyperspectral data collected by NASA’s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite mining district in Nevada and the World Trade Center in New York. Experimental results demonstrate that our hardware version of the ATGP-OSP algorithm can significantly outperform a software version, which makes our reconfigurable system appealing for onboard hyperspectral data processing.

Comparative Study and Analysis Among ATGP, VCA, and SGA for Finding Endmembers in Hyperspectral Imagery

Endmember finding has become increasingly important in hyperspectral data exploitation because endmembers can be used to specify unknown particular spectral classes. Pixel purity index (PPI) and N-finder algorithm (N-FINDR) are probably the two most widely used techniques for this purpose where many currently available endmember finding algorithms are indeed derived from these two algorithms and can be considered as their variants. Among them are three well-known algorithms derived from imposing different abundance constraints, that is, abundance-unconstrained automatic target generation process (ATGP), abundance nonnegativity constrained vertex component analysis (VCA), and fully abundance constrained simplex growing algorithm (SGA). This paper explores relationships among these three algorithms and further shows that theoretically they are essentially the same algorithms in the sense of design rationale. The reason that these three algorithms perform differently is not because they are different algorithms, but rather because they use different preprocessing steps, such as initial conditions and dimensionality reduction transforms.

Introduction to the Special Issue on High Performance Computing Solutions for Complex Problems

In the last decades, the complexity of the current and upcoming scientific/engineering problems has increased considerably. Computations involved in numerical simulations, molecular dynamics, computational fluid dynamics, bio-informatics, image processing, linear algebra, deep-learning, information retrieval, or big-data computing are just a few examples of such problems. At the same time, improvements in high performance computing (HPC) systems are mainly associated with an important increasing in the complexity of computer architectures, making difficult the code optimization. This results in a greater gap between the general scientific / engineering user community (in need of easy access to efficient high performance computations) and the HPC programmers community (who design codes for narrow sub-classes of problems). The development of user-friendly codes for non-HPC-trained user community becomes a big challenge. As consequence, effective use of HPC centers requires specialized / individual training for each user group. Today, programmers of HPC or/and scientific applications have to deal with numerous details regarding computer architectures at low level to take advantage of the last features of the current and upcoming computing systems. It makes difficult the efficient and optimized software development. Thus, strategies and tools that can help us to adapt our codes over different computing architectures is of vital importance. However, previously, we must know and identify what are most efficient programming strategies and architectonic features. This is a difficult task as both, strategies and features, depend on the particular problem to be dealt. Portability is other important issue today. Multiples kind of processors have arisen in the last years. Most of these current platforms use their own compilers, languages, etc., being a very complex task to implement portable codes. This special issue provides several studies, which involve different applications and strategies to improve performance and to achieve better usage of current computing systems. It is composed by three works. The work Performance Optimizations for an Automatic Target Generation Process in Hyperspectral Analysis by Fernando Sierra-Pajuelo, Abel Paz-Gallardo, and Antonio Plaza presents several optimizations for hyperspectral image processing algorithms intended to detect targets in hyperspectral images. The algorithm used is the automated target generation process (ATGP) and the optimizations comprise parallel versions of the algorithm developed using open multi-processing (OpenMP, including Intel Xeon Phi) and message passing interface (MPI). The study Using Computational Geometry to Improve Process Rescheduling on Round-Based Parallel Applications by R. da Rosa-Righi, V. Magalhaes-Guerreiro, G. Rostirolla, V. Facco-Rodrigues, C. Andre da Costa, and L. Dagnino-Chiwiacowsky, proposes two novel heuristics applied to process rescheduling, named MigCube and MigHull, to choose the candidate processes for migration and their destination. Both heuristics consider the use of computational geometry for plotting computation, communication and migration costs metrics in a 3D graph without any user intervention. Finally, the work Many-Task Computing on Many-Core Architectures by Pedro Valero-Lara, Poorima Nookala, Fernando L. Pelayo, Johan Jansoon, Serapheim Dimitropoulos, and Ioan Raicu, studies what are the Many-Task Computing (MTC) programming mechanisms to take advantages of the massively parallel features of current hardware accelerators for the particular target of MTC. Also, the hardware features of the two dominant many-core platforms (NVIDIA GPUs and Intel Xeon Phi) are also analyzed for our specific framework. This study consisted of comparing the time consumed for computing in parallel several tasks one by one (the whole computational resources are used just to compute one task at a time) with the time consumed for computing in parallel the same set of tasks simultaneously (the whole computational resources are used for computing the set of tasks at very same time). Finally, both software-hardware scenarios were compared to identify the most relevant computer features in each of our many-core architectures. We would like to thank the editorial board of SCPE and reviewers for their effort and time, which is very appreciated.

Performance Optimizations for an Automatic Target Generation Process in Hyperspectral Analysis

Hyperspectral sensors acquire images with hundreds of spectral channels. These images have a lot of information in both spectral and spatial domain, and with this kind of information different research studies can be accomplished. In this work, we present several optimizations for hyperspectral image processing algorithms intended to detect targets in hyperspectral images. The hyperspectral image selected for our study was collected by the NASAs Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the World Trade Center (WTC) in New York, five days after September 11th attack. The algorithm used in our experiments is the automated target generation process (ATGP) and our optimizations comprise parallel versions of the algorithm developed using open multi-processing (OpenMP) and message passing interface (MPI). Our experiments indicate that the ATGP can be successfully implemented in parallel in multicore and cluster computing architectures, including Intel Xeon Phi.

Recursive Automatic Target Generation Process in Subpixel Detection

Automatic target generation process (ATGP) has been used in a wide range of applications in hyperspectral image analysis. It performs a sequence of orthogonal subspace projections to extract potential targets of interest. This letter presents a recursive version of the ATGP, which is referred to as the recursive ATGP (RATGP) and has three advantages over the ATGP as follows: 1) there is no need of inverting a matrix as the ATGP does for finding each new target; 2) there is a significant reduction in the computational complexity in the hardware design due to its recursive structure; and 3) there is an automatic stopping rule that can be derived by the Neyman–Pearson detection theory to terminate the algorithm.

A two-step super-Gaussian independent component analysis approach for fMRI data

Independent component analysis (ICA) has been widely applied to functional magnetic resonance imaging (fMRI) data analysis. Although ICA assumes that the sources underlying data are statistically independent, it usually ignores sources’ additional properties, such as sparsity. In this study, we propose a two-step super-GaussianICA (2SGICA) method that incorporates the sparse prior of the sources into the ICA model. 2SGICA uses the super-Gaussian ICA (SGICA) algorithm that is based on a simplified Lewicki-Sejnowski’s model to obtain the initial source estimate in the first step. Using a kernel estimator technique, the source density is acquired and fitted to the Laplacian function based on the initial source estimates. The fitted Laplacian prior is used for each source at the second SGICA step. Moreover, the automatic target generation process for initial value generation is used in 2SGICA to guarantee the stability of the algorithm. An adaptive step size selection criterion is also implemented in the proposed algorithm. We performed experimental tests on both simulated data and real fMRI data to investigate the feasibility and robustness of 2SGICA and made a performance comparison between InfomaxICA, FastICA, mean field ICA (MFICA) with Laplacian prior, sparse online dictionary learning (ODL), SGICA and 2SGICA. Both simulated and real fMRI experiments showed that the 2SGICA was most robust to noises, and had the best spatial detection power and the time course estimation among the six methods.