Speckle Intensity Research Articles

Real-time co-localized OCT surveillance of laser therapy using motion corrected speckle decorrelation.

We present a system capable of real-time delivery and monitoring of laser therapy by imaging with optical coherence tomography (OCT) through a double-clad fiber (DCF). A double-clad fiber coupler is used to inject and collect OCT light into the core of a DCF and inject the therapy light into its larger inner cladding, allowing for both imaging and therapy to be perfectly coregistered. Monitoring of treatment depth is achieved by calculating the speckle intensity decorrelation occurring during tissue coagulation. Furthermore, an analytical noise correction was used on the correlation to extend the maximum monitoring depth. We also present a method for correcting motion-induced decorrelation using a lookup table. Using the value of the noise- and motion-corrected correlation coefficient in a novel approach, our system is capable of identifying the depth of thermal coagulation in real time and automatically shut the therapy laser off when the targeted depth is reached. The process is demonstrated ex vivo in rat tongue and abdominal muscles for depths ranging from 500 µm to 1000 µm with induced motion in real time.

Light field imaging through a single multimode fiber for OAM-multiplexed data transmission

Multimode fibers (MMFs) can support a large number of spatial modes, increasing the amount of transmitted information, a feature that benefits fields such as endoscopic imaging or optical communications. However, the transport of information encoded in the phase through a standard MMF has not been achieved due to strong mode coupling, hindering direct data transfer using light beams endowed with orbital angular momentum (OAM). Here, we present a computational light field imaging technique to achieve OAM-multiplexed transmission through a commercial MMF. Such a technique enables the retrieval of the incident field from the speckle intensity at the distant end of the fiber. Based on the recovered field, the extraction of the transferred data by addressing all the OAM channels can be achieved. Experimentally, light field imaging through a MMF is demonstrated by recovering a structured light field and a phase picture. For optical transmission, the crosstalk between OAM channels is tested first, and then we demonstrate high-fidelity image data transfer via 24 multiplexed OAM channels through a commercial MMF.

Tutorial on laser speckle rheology: technology, applications, and opportunities.

.Significance: The onset of several diseases is frequently marked with anomalous mechanical alteration of the affected tissue at the intersection of cells and their microenvironment. Therefore, mapping the micromechanical attributes of the tissues could enhance our understanding of the etiology of human disease, improve the diagnosis, and help stratify therapies that target these mechanical aberrations.Aim: We review the tremendous opportunities offered through using optics for imaging the micromechanical properties, at length scales inaccessible to other modalities, in both basic research and clinical medicine. We specifically focus on laser speckle rheology (LSR), a technology that quantifies the mechanical properties of tissues in a rapid, noncontact manner.Approach: In LSR, the shear viscoelastic modulus is measured from the time-variant speckle intensity fluctuations reflected off the tissue. The LSR technology is engineered and configured into several embodiments, including bench-top optical systems, endoscopes for minimally invasive procedures, portable point-of-care devices, and microscopes.Results: These technological nuances have primed the LSR for widespread applications in diagnosis and therapeutic monitoring, as demonstrated here, in cardiovascular disease, coagulation disorders, and tumor malignancies.Conclusion: The fast-paced technological advancements, elaborated here, position the LSR as a competent candidate for many more exciting opportunities in basic research and medicine.

Spatial Beam Self-Cleaning in Second-Harmonic Generation

We experimentally demonstrate the spatial self-cleaning of a highly multimode optical beam, in the process of second-harmonic generation in a quadratic nonlinear potassium titanyl phosphate crystal. As the beam energy grows larger, the output beam from the crystal evolves from a highly speckled intensity pattern into a single, bell-shaped spot, sitting on a low energy background. We demonstrate that quadratic beam cleanup is accompanied by significant self-focusing of the fundamental beam, for both positive and negative signs of the linear phase mismatch close to the phase-matching condition.

Dynamic speckle analysis with coarse quantization of the raw data.

Analysis of dynamic speckle formed on the surface of diffusely reflecting objects under laser illumination is a non-contact method for inspection of speed of processes. The paper deals with intensity-based implementation of the method that relies on statistical processing of correlated in time sequences of speckle images. A two-dimensional activity map is built for each sequence to visualize regions of different speed on the object surface at a given instant. A great number of images is required to track a process in time. We propose data compression by coarse quantization of the raw speckle data. Efficacy of quantization is analyzed by simulation and experiment for low- and high-contrast speckle patterns with bell-shaped and long-tailed distributions of intensity, respectively. Non-uniform quantization is proposed for long-tailed speckle intensity distributions. Decreasing the bit depth from 8 to 4 causes no change in the probability density function of the activity estimate.

Comparing focal plane wavefront control techniques: Numerical simulations and laboratory experiments

Context. Fewer than 1% of all exoplanets detected to date have been characterized on the basis of spectroscopic observations of their atmosphere. Unlike indirect methods, high-contrast imaging offers access to atmospheric signatures by separating the light of a faint off-axis source from that of its parent star. Forthcoming space facilities, such as WFIRST/LUVOIR/HabEX, are expected to use coronagraphic instruments capable of imaging and spectroscopy in order to understand the physical properties of remote worlds. The primary technological challenge that drives the design of these instruments involves the precision control of wavefront phase and amplitude errors. To suppress the stellar intensity to acceptable levels, it is necessary to reduce phase aberrations to less than several picometers across the pupil of the telescope. Aims. Several focal plane wavefront sensing and control techniques have been proposed and demonstrated in laboratory to achieve the required accuracy. However, these techniques have never been tested and compared under the same laboratory conditions. This paper compares two of these techniques in a closed loop in visible light: the pair-wise (PW) associated with electric field conjugation (EFC) and self-coherent camera (SCC). Methods. We first ran numerical simulations to optimize PW wavefront sensing and to predict the performance of a coronagraphic instrument with PW associated to EFC wavefront control, assuming modeling errors for both PW and EFC. Then we implemented the techniques on a laboratory testbed. We introduced known aberrations into the system and compared the wavefront sensing using both PW and SCC. The speckle intensity in the coronagraphic image was then minimized using PW+EFC and SCC independently. Results. We demonstrate that both techniques – SCC, based on spatial modulation of the speckle intensity using an empirical model of the instrument, and PW, based on temporal modulation using a synthetic model – can estimate the wavefront errors with the same precision. We also demonstrate that both SCC and PW+EFC can generate a dark hole in space-like conditions in a few iterations. Both techniques reach the current limitation of our laboratory bench and provide coronagraphic contrast levels of ∼5 × 10−9 in a narrow spectral band (< 0.25% bandwidth). Conclusions. Our results indicate that both techniques are mature enough to be implemented in future space telescopes equipped with deformable mirrors for high-contrast imaging of exoplanets.

Fully automated lesion segmentation and visualization in automated whole breast ultrasound (ABUS) images.

The number of breast cancer patients has increased each year, and the demand for breast cancer detection has become quite large. There are many common breast cancer diagnostic tools. The latest automated whole breast ultrasound (ABUS) technology can obtain a complete breast tissue structure, which improves breast cancer detection technology. However, due to the large amount of ABUS image data, manual interpretation is time-consuming and labor-intensive. If there are lesions in multiple images, there may be some omissions. In addition, if further volume information or the three-dimensional shape of the lesion is needed for therapy, it is necessary to manually segment each lesion, which is inefficient for diagnosis. Therefore, automatic lesion segmentation for ABUS is an important issue for guiding therapy. Due to the amount of speckle noise in an ultrasonic image and the low contrast of the lesion boundary, it is quite difficult to automatically segment the lesion. To address the above challenges, this study proposes an automated lesion segmentation algorithm. The architecture of the proposed algorithm can be divided into four parts: (I) volume of interest selection, (II) preprocessing, (III) segmentation, and (IV) visualization. A volume of interest (VOI) is automatically selected first via a three-dimensional level-set, and then the method uses anisotropic diffusion to address the speckled noise and intensity inhomogeneity correction to eliminate shadowing artifacts before the adaptive distance regularization level set method (DRLSE) conducts segmentation. Finally, the two-dimensional segmented images are reconstructed for visualization in the three-dimensional space. The ground truth is delineated by two radiologists with more than 10 years of experience in breast sonography. In this study, three performance assessments are carried out to evaluate the effectiveness of the proposed algorithm. The first assessment is the similarity measurement. The second assessment is the comparison of the results of the proposed algorithm and the Chan-Vese level set method. The third assessment is the volume estimation of phantom cases. In this study, in the 2D validation of the first assessment, the area Dice similarity coefficients of the real cases named cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.84±0.06 and 0.78±0.04, real case B are 0.91±0.04 and 0.82±0.05, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.02 and 0.92±0.03, respectively. In the 3D validation, the volume Dice similarity coefficients of the real cases A, real cases B and phantoms are 0.85±0.02, 0.89±0.04 and 0.94±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.82±0.06 and 0.79±0.04, real cases B are 0.92±0.04 and 0.85±0.07, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.01 and 0.93±0.04, respectively. Therefore, the proposed algorithm is highly reliable in most cases. In the second assessment, compared with Chan-Vese level set method, the Dice of the proposed algorithm in real cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The Dice of Chan-Vese level set in real cases A, real cases B and phantoms are 0.65±0.23, 0.69±0.14 and 0.76±0.14, respectively. The Dice performance of different methods on segmentation shows a highly significant impact (P<0.01). The results show that the proposed algorithm is more accurate than Chan-Vese level set method. In the third assessment, the Spearman's correlation coefficient between the segmented volumes and the corresponding ground truth volumes is ρ=0.929 (P=0.01). In summary, the proposed method can batch process ABUS images, segment lesions, calculate their volumes and visualize lesions to facilitate observation by radiologists and physicians.

Band-Limited Reference-Free Speckle Spectroscopy: Probing the Fluorescent Media in the Vicinity of the Noise-Defined Threshold

A method of reference-free speckle spectroscopy based on the statistical analysis of intensity spatial fluctuations of the spectrally-selected multiple-scattered fluorescence radiation is examined in the case of the finite-band spectral selection of fluorescence light emitted by the laser-pumped random medium, and detection conditions far from the ideal case. Intensity fluctuations are recorded during point-to-point scanning of the surface of a random multiple-scattering medium, which is characterized by the dependences of the second- and third-order statistical moments of intensity on the wavelength of detected spectrally selected light. In turn, the statistical moments of intensity fluctuations are determined by the average propagation path of fluorescent radiation in the medium. This makes it possible to analyze the features of the light-medium interactions at a scale of the order of the transport mean free path of radiation propagation in the medium. Depending on the spectral selection conditions, the method is applicable for characterizing micro- or nano-structured fluorescent layers with thicknesses from tens of micrometers to several millimeters. In the examined case, the finite-band spectral selection results in the values of coherence length of the detected fluorescence radiation compared with the ensemble-averaged absolute value of the path-length difference between the stochastically interfering and spectrally selected partial contributions to the fluorescence field. In addition, non-ideal detection conditions (usage of a multimode optical fiber in the light-collecting unit) cause additional strong damping of the detected speckle intensity fluctuations. These factors lead to a remarkable suppression of spatial fluctuations of the fluorescence intensity in the course of spatially- and spectrally-resolved surface scanning of the laser-pumped probed random medium. Nevertheless, with appropriate procedures of the intrinsic noise reduction and data correction, the obtained spectral dependencies of the normalized third-order statistical moment of the band-limited fluorescence intensity clearly indicate the fluorescence propagation features in the probed multiple-scattering random media (such as a strong influence of the scattering strength and multiple self-absorption–re-emission events on the average propagation path of light in the medium).The possibilities of noise reduction and data correction in the case of applying the band-limited reference-free spectroscopic instrumentation with low spectral and spatial resolution are illustrated by the experimental results obtained using the Rhodamine-6G-doped and continuous wave (CW)-laser-pumped layers of the densely packed titania and silica particles.

Protein Conformational Dynamics Probed Correlation Spectroscopy of Multiply Scattered Light

To assess the dynamics of proteins due to their external and internal degrees of freedom, we used a optical correlation spectroscopy method, that provides the spectrum of optical fluctuations due to protein dynamics in solution. In the case of acto-myosin forced out-of-equilibrium by its chemically driven motor activity, the difference spectrum between thermal and driven fluctuations reveals the frequency-amplitude properties of the conformational dynamics of myosin. This optical method is the so-called DWS (diffusive wave spectroscopy), first proposed by Maret and Wolf in 1987 (Z. Phys.). Practically, when illuminated by a highly monochromatic and coherent light beam in the strong scattering regime, the sample produces a diffusive light flux inside the sample. Outside of the sample, one obtains an intensity speckle field that is determined by the scattering properties and the spatial distribution of the scatterers, with fixed speckles if scatterers are immobile. By measuring the speckle intensity autocorrelation function, one obtains the fluctuation spectrum of the scaterrers. Using that method, we found that conformational changes of myosin occur at times-scales that are typically 2 to 3 orders of magnitude faster that the shortest time of the enzymatic activity cycle. To improve the sensitivity of that method, we introduce a new concept called Cavity Amplified Speckle Decorrelation Spectroscopy. The phase fluctuations of the light scattered by a given sample are amplified by placing it inside a closed Lambertian cavity with highly diffusively reflecting walls, which ergodically forces the light multiple times back into the sample. This new concept will be illustrated with a few biological and non-biological samples, showing that previously undetected fluctuations can be measured over 8-10 decades in the frequency domain, and resolved with unprecedented sensitivity.

Surface roughness estimation of wood boards using speckle interferometry

A problem present in the wood boards industry is the lack of knowledge of its roughness. The roughness causes the formation of voids between the board and the protective cover commonly used to give a special finish to the board. This leads to poor adhesion between the adhesive and the cover which affects the quality of the final product. Thus, a precise and fast way to measure the roughness that allows characterization in line and across the board is required.Speckle interferometry is a widely used technique to perform non-invasive measurements, mainly by illuminating objects under study with coherent light. In this study, laser speckle interferometry is used to determinate surface roughness in different wood boards. The proposed method uses an optical system and an image processor that correlates a series of successive images of intensity speckle pattern. These images are obtained varying the illumination angle.In order to obtain the roughness parameters of the boards, the measured correlations were adjusted to a theoretical function by using a numerical regression algorithm. The obtained values of roughness for different boards varied between 1.55 µm and 12.69 µm. Our results show a good agreement with the measurements obtained using conventional methods.Finally, we present a discussion of how laser speckle interferometry can be adapted to characterize roughness during production in real time and in wide area boards.

Two-way ANOVA gage R&amp;R working example applied to speckle intensity statistics due to different random vertical surface roughness characteristics using the Fresnel diffraction integral

Two-way ANOVA gage R&amp;R working example applied to speckle intensity statistics due to different random vertical surface roughness characteristics using the Fresnel diffraction integral

A Correction of Random Medium Motion Correlation Imaging Method

Abstract Imaging and communication are often disturbed in random medium due to random scattering. The correlation in a random scattering field provides a possible way to recover information. By using speckle intensity correlation, Newmann and Webb proposed a motion correlation imaging method to reconstruct the field incident on thick random medium. However, the size effect of a light intensity detector on the speckle intensity correlation is not fully understood. We investigate the size effect on the speckle intensity correlation. We find that if the size is too large or too small, the statistics of an electric field deviates from zero-mean circular complex Gaussian statistics, and the speckle intensity correlation deviates from magnitude square of the incident field autocorrelation. The deviation is due to the random fluctuation amplitude of the scattered electric field, which is different at spatial locations on an output plane. We propose a correction for the original motion correlation imaging method, and results from our modified method agree better with the theoretical prediction

Spatial Multiplexing Technique for Improving Dynamic Range of Speckle Correlation based Optical Lever

Speckle correlation based optical levers (SC-OptLev) possess attractive characteristics suitable for sensing small changes in the angular orientations of surfaces. In this study, we propose and demonstrate a spatial multiplexing technique for improving the dynamic range of SC-OptLev. When the surface is in its initial position, a synthetic speckle intensity pattern, larger than the area of the image sensor is created by transversely shifting the image sensor and recording different sections of a larger speckle pattern. Then, the acquired images are stitched together by a computer program into one relatively large synthetic speckle pattern. Following the calibration stage, the synthetic speckle intensity pattern is used to sense changes in the surface’s angular orientation. The surface is monitored in real-time by recording part of the speckle pattern which lies within the sensor area. Next, the recorded speckle pattern is cross-correlated with the synthetic speckle pattern in the computer. The resulting shift of the correlation peak indicates the angular orientations of the reflective surface under test. This spatial-multiplexing technique enables sensing changes in the angular orientation of the surface beyond the limit imposed by the physical size of the image sensor.

Minimization of non-common path aberrations at the Palomar telescope using a self-coherent camera

Context. The two main advantages of exoplanet imaging are the discovery of objects in the outer part of stellar systems, which constrains the models of planet formation, and its ability to spectrally characterize the planets to study their atmospheres. It is, however, challenging because exoplanets are up to 1010 times fainter than their stars and are separated by a fraction of an arcsecond. Current instruments like SPHERE-VLT or GPI-Gemini detect young and massive planets only because of non-common path aberrations (NCPA) that are not corrected by the adaptive optics system. To probe fainter exoplanets a new instruments capable of minimizing the NCPA is needed. One solution is the self-coherent camera (SCC) focal plane wavefront sensor which is able to attenuate the starlight by factors of up to several 108 in the laboratory in space-like conditions. Aims. In this paper, we demonstrate the SCC on the sky for the first time. Methods. We installed an SCC on the stellar double coronagraph instrument at the Hale telescope. We minimize the NCPA that limited the vortex coronagraph performance. We then compared this procedure to the standard procedure used at Palomar. Results. On internal sources, we demonstrated that the SCC improves the coronagraphic detection limit by a factor of 4–20 between 1.5 and 5 λ/D. Using this SCC calibration, the on-sky contrast is improved by a factor of 5 between 2 and 4 λ/D. These results prove the ability of the SCC to be implemented in an existing instrument. Conclusions. This paper highlights two interests of the self-coherent camera. First, the SCC can minimize the speckle intensity in the field of view, especially the ones that are very close to the star where many exoplanets are to be discovered. Then the SCC has a 100% efficiency with science time as each image can be used for both science and NCPA minimization.

Active minimization of non-common path aberrations in long-exposure imaging of exoplanetary systems

Context. Spectroscopy of exoplanets is very challenging because of the high star-planet contrast. A technical difficulty in the design of imaging instruments is the noncommon path aberrations (NCPAs) between the adaptive optics (AO) sensing and the science camera, which induce planet-resembling stellar speckles in the coronagraphic science images. In an observing sequence of several long exposures, quickly evolving NCPAs average out and leave behind an AO halo that adds photon noise to the planet detection. Static NCPA can be calibrated a posteriori using differential imaging techniques. However, NCPAs that evolve during the observing sequence do not average out and cannot be calibrated a posteriori. These quasi-static NCPAs are one of the main limitations of the current direct imaging instruments such as SPHERE, GPI, and SCExAO. Aims. Our aim is to actively minimize the quasi-static speckles induced in long-exposure images. To do so, we need to measure the quasi-static speckle field above the AO halo. Methods. The self-coherent camera (SCC) is a proven technique which measures the speckle complex field in the coronagraphic science images. It is routinely used on the THD2 bench to reach contrast levels of &lt; 10−8 in the range 5 − 12 λ/D in space-related conditions. To test the SCC in ground conditions on THD2, we optically simulated the residual aberrations measured behind the SPHERE/VLT AO system under good observing conditions. Results. We demonstrate in the laboratory that the SCC can minimize the quasi-static speckle intensity in the science images down to a limitation set by the AO halo residuals. The SCC reaches 1σ raw contrast levels below 10−6 in the region 5 − 12 λ/D at 783.25 nm in our experiments. Conclusions. The results presented in this article reveal an opportunity for the current and future high-contrast imaging systems to adapt the SCC for real-time measurement and correction of quasi-static speckles in long-exposure science observations from the ground.

Stochastic Speckle Discrimination with Time-tagged Photon Lists: Digging below the Speckle Noise Floor

We present an algorithm that uses the distribution of photon arrival times to distinguish speckles from incoherent sources, like planets and disks, in high-contrast images. Using simulated data, we show that our approach can overcome the noise limit from fluctuating speckle intensity. The algorithm is likely to be most advantageous when a coronagraph limits the coherent diffraction pattern in the image plane but the intensity is still strongly modulated by fast-timescale uncorrected stellar light, for example from atmospheric turbulence. These conditions are common at small inner working angles of highly corrected adaptive optics images and will allow probing of exoplanet populations at smaller angular separations. The technique requires a fast science camera that can temporally resolve the speckle fluctuations, and the detection of many photons per speckle decorrelation time. Because the algorithm directly extracts the incoherent light, standard differential imaging postprocessing techniques can be performed afterwards to further boost the signal.

Modeling of laser ponderomotive self-focusing in plasma within the paraxial complex geometrical optics approach

Laser ponderomotive self-focusing in an underdense homogeneous plasma is studied within the paraxial complex geometrical optics (PCGO) approach implemented in a hydrodynamic code in two-dimensional planar geometry. The self-focusing of a PCGO Gaussian beam is compared to simulations performed with a paraxial electromagnetic code. Good agreement has been found for beam powers less than three times the critical power and for plasma densities 5%–10% of the critical density. Besides Gaussian beams, PCGO allows to reproduce spatially modulated beams by superposition of Gaussian beams, mimicking a speckle pattern. Although the statistics of speckle patterns generated with PCGO reproduces well the speckle statistics of optically smoothed beams, a PCGO speckle is larger than optical speckles, carrying thus higher power such that they overestimate self-focusing effects. To overcome this issue, an algorithm is proposed within PCGO framework: it consists of superposing several Gaussian beams forming a speckle such that self-focusing effects are eventually well controlled. It is found that the superposition of three Gaussian beams with appropriate initial conditions leads to a reduction of the PCGO speckle intensity enhancement.

Unsupervised Local Spatial Mixture Segmentation of Underwater Objects in Sonar Images

In this paper, we focus on the segmentation of sonar images to achieve underwater object detection and classification. Our goal is to achieve accurate segmentation of the object's highlight and shadow regions. We target a robust solution that can manage different seabed backgrounds. Segmentation of sonar images is a challenging task. Speckle noise and intensity inhomogeneity may cause false detections and complex seabed textures, such as sand ripples and seagrass, often leading to false segmentation. In this paper, we propose our local spatial mixture (LSM) method for image segmentation of sidescan deployed sonar systems of any type. This new method estimates pixel labels in sonar images by incorporating the possible spatial correlation between neighboring pixels for improved segmentation. LSM modifies the expectation–maximization algorithm by adding an intermediate step (I-step) between the expectation (E-step) and maximization (M-step) steps. To combat intensity inhomogeneity, we employ a new initialization algorithm, one whose thresholds are set automatically to achieve and maintain robustness in various underwater environments. Using multiple evaluation indexes that measure the geometrical features of the segmented objects, we tested LSM using synthetic and real sonar images, one of which is obtained from our own sea experiment. Our results show that LSM achieves improved segmentation performance over the state-of-the-art methods of four different approaches; LSM is also robust to different seabed textures and intensity inhomogeneity. We share the sonar images from our sea experiments.

Segmentation of sonar images with intensity inhomogeneity based on improved MRF

Sonar is one of the most important tools for underwater object detection and submarine topography reconstruction. To classify sonar images automatically and accurately is essential for the navigation and path planning of autonomous underwater vehicles (AUV). However, for the intensity inhomogeneity and speckle noise in sonar images, it is difficult to obtain segmentation results of high accurate rate. To address these issues, in this paper, we advocate a segmentation method incorporating simple linear iterative clustering (SLIC) and adaptive intensity constraint into Markov random field (MRF), to segment sonar images with intensity inhomogeneity into the object highlight, the object shadow and the background areas. The main procedures of the proposed work are as follows: first, SLIC is used to separate sonar images into homogeneous super pixels, and second the homogeneity patches, with a novel intensity constraint strategy, is utilized to optimize the segmentation result of MRF at each iteration. Experimental results reveal that the proposed method performs well and fast on real sonar images which have intensity inhomogeneity problem.

Autoencoder-aided measurement of concentration from a single line of speckle

We demonstrate that a single 6mm line sample of simulated near-field speckle intensity suffices for accurate estimation of the concentration of dielectric micro-particles over a range from 104 to 6⋅106 particles per ml. For this estimation, we analyze the speckle using both standard methods (linear principal component analysis, support vector machine (SVM)) and a neural network, in the form of a sparse stacked autoencoder (SSAE) with a softmax classifier or with an SVM. Using an SSAE with SVM, we classify line speckle samples according to particle concentration with an average accuracy of over 78%, with other methods close behind.