Grayscale Gradient Research Articles

A Biometric Features-Based Watermarking Encryption Approach for Secure Authentication of Visual Images

Due to the uniqueness of biometric features, it remains practical in generating cryptographic keys. In this study, a region-based encryption method is proposed, which can avoid the attacks on the whole encryption such as block attack and frame insertion attack. This method can protect important areas while encrypting images so that the image can maintain recognition and credibility even when attacked. It has certain universality and scalability, and can be applied to a variety of scenarios and systems. First, biometric features are introduced to extract keys from fingerprint key images through grayscale segmentation and gradient segmentation. Then, a watermarking addition algorithm is completed based on single encryption and reversible exchange encryption using hybrid vectors, and the image is encrypted using encryption algorithms. Next, the generated biometric key is embedded into the encrypted image, and a complete watermark encryption model named BKE is established by adjusting the singular value decomposition algorithm. Finally, invisibility, decoding accuracy, and stability analysis are completed based on publicly available data. The experimental results show that this method has high effectiveness and feasibility in image security authentication, and this method improves the security and authentication accuracy of images. This method has broad application prospects and can be used for image security authentication in various fields.

Correction of thermal airflow distortion in warpage measurements of microelectronic packaging structures via deep learning-based digital image correlation

The projected speckle-based three-dimensional digital image correlation method (3D-DIC) is being increasingly used in the reliability measurement of microelectronic packaging structures because of its noninvasive nature, high precision, and low cost. However, during the measurement of the thermal reliability of packaging structures, the thermal airflow generated by heating introduces distortions in the images captured by the DIC measurement system, impacting the accuracy and reliability of noncontact measurements. To address this challenge, a thermal airflow distortion correction model based on the transformer attention mechanism is proposed specifically for the measurement of thermal warpage in microelectronic packaging structures. This model avoids the oversmoothing issue associated with convolutional neural networks and the lack of physical constraints in generative adversarial networks, ensuring the precision of grayscale gradient changes in speckle patterns and minimizing adverse effects on DIC calculation accuracy. By inputting the distorted images captured by the DIC measurement system into the network, corrected images are obtained for 3D-DIC calculations, thus allowing the thermal warpage measurement results of the sample to be acquired. Through experiments measuring topography with customized step block specimens, the effectiveness of the proposed method in improving warpage measurement accuracy is confirmed; this is particularly true when captured images are affected by thermal airflow at 140 °C and 160 °C, temperatures commonly encountered in thermal reliability testing of packaging structures. The method successfully reduces the standard deviation from 9.829 to 5.943 µm and from 12.318 to 6.418 µm, respectively. The results demonstrate the substantial practical value of this method for measuring thermal warpage in microelectronic packaging structures.

A novel phase measuring deflectometry based on polar coordinate

Phase measuring deflectometry (PMD) is a method measure the surface of a mirror. However, when measuring convex mirrors, Cartesian coordinate fringes experience extreme compression. To address this issue, this paper proposes a novel PMD based on polar coordinate. This new method defines two linearly independent phase modulation directions, using the orthogonal basis of polar coordinate. It establishes polar coordinate fringes with rotational symmetry and radial pre-modulation, effectively reducing the impact of extreme compression at the edges. To correct the phase errors in polar coordinate fringes, a phase error compensation algorithm based on greyscale gradient is introduced. The algorithm calculates the influence factor of the eight connected domains around the error points to be compensated, utilising the phase grey gradient. The wavefront gradient data obtained through polar coordinate fringes are radial and tangential. Hence, a surface reconstruction method is proposed based on the Zernike partial derivative polynomial based on polar coordinate. In this method, the tangential partial derivatives and radial partial derivatives of the first 36 terms of Zernike in polar coordinate to construct Gram matrix equations. As a result, linearly independent Zernike recovery coefficients are obtained from coupled aliasing gradient data. Compared to the Cartesian coordinate system, the proposed method significantly reduces the fitting coefficient errors. Experimental measurements of convex mirrors with radii of curvature of 200 mm and 100 mm were conducted. The results demonstrate that compared to traditional PMD, this technique not only effectively suppresses extreme compression and increases the measurement area but also improves measurement accuracy by six times.

Point Spread Function And Spatial Resolution Analysis Of Multi-Focus Plenoptic Cameras

With the recent development of plenoptic cameras, light field imaging has become a reliable solution for 3D metrology. Plenoptic cameras allow recovering the 3D information of a scene with a single acquisition and only one camera. These advantages make light field imaging particularly interesting for the metrology of two-phase flows. The measurement depth of a back-light imaging setup can be determined by the calibration of the Point Spread function (PSF) of the optical system. This study provides a method adapted to multi-focus plenoptic cameras to measure the PSF width from reconstructed images. We used a calibration target composed of multiple calibrated opaque disks and a diffuse backlight illumination set-up. The PSF width is estimated by measuring the grayscale gradient at the interface of the images of the disks. Coupled with the depth information provided by the plenoptic camera, we obtained the evolution of the PSF at different depth planes. The information on the PSF enables us to obtain the focus criterion, which sets the limits of the measurement volume. The spatial resolution of the reconstructed images is obtained from the PSF. The results obtained for the resolution as a function of virtual depth are consistent with results from previous studies.

APW: An ensemble model for efficient wheat spike counting in unmanned aerial vehicle images

The accurate estimation of wheat ear is of great significance to gain high yield for ensuring food security. The use of computer vision for wheat ear counting to improve the estimation efficiency and accuracy has been explored by many scholars. However, existing single-computer vision recognition methods have insufficient robustness and recognition of adherent wheat ears. This study mainly focused on to solve the problem of adherent wheat ears, and proposed a combined algorithm called “APW” that ensemble with alternating direction methods of multipliers (ADMM), Potts algorithm and Watershed to achieve fast recognition and counting of wheat ears. The images of wheat ears were collected under three different scenarios including growth stages, planting densities, and flight heights by using unmanned aerial vehicle (UAV), and the Potts model was used to recognise the images. The masked images of the wheat ear were converted into a greyscale image, and were layered using a greyscale gradient. Finally, the watershed algorithm was used to segment adherent wheat ears in the layered image, and the centroids were labelled and counted. The results shows that the best accuracy was obtained under low planting density scenario, with an R2 of 0.89 and a root mean square error (RMSE) of 3.72, suggesting that APW can handle scenarios with large background differences and low target adherence. These findings provides a new approach for efficient counting of wheat ears in UAV acquired images.

Automatic Particle Recognition Based on Digital lmage Processing

The purpose of the research is to develop and compare various methods and algorithms for effective particle analysis based on their visual characteristics. Тhe purpose of this article is to develop and compare various methods and algorithms for effective particle analysis based on their visual characteristics. Тhe paper considers two fundamentally different approaches: the analysis of grayscale gradients and the machine learning method.Methods.Тhe research methodology includes the analysis of particle images obtained by precipitation from colloidal solutions after laser ablation and images of powder particles for selective laser melting. Тhe materials were obtained using a Quanta 200 3D electron microscope (FЕ/). For the analysis, threshold brightness binarization, contour recognition methods by the Kenny operator and the Hough algorithm are used to combine boundary points into connected contours. For comparison, the U-Net neural network solution was used, and a dataset generator was created to train the neural network. Hand-cut images of aluminum alloy powder particles and micro and nanoparticles of various metals are used as data for generation.Results.Тhe results of the study show that the Hough method provides recognition of the number of particles at the level of 80%, and the machine learning method achieves 95% accuracy in recognizing the shape of particles. Both methods can be used to analyze microand nanoparticles, including irregularly shaped particles.Conclusion.Тhe findings of the work confirm that neural networks are the optimal solution for automatic particle recognition in digital images. However, in order to create a dataset of sufficient volume, it is necessary to develop a generator of labeled images, which requires a detailed study of the subject area.

Multiscale method for identifying and marking the multiform fractures from visible-light rock-mass images

Multiform fractures have a direct impact on the mechanical performance of rock masses. To accurately identify multiform fractures, the distribution patterns of grayscale and the differential features of fractures in their neighborhoods are summarized. Based on this, a multiscale processing algorithm is proposed. The multiscale process is as follows. On the neighborhood of pixels, a grayscale continuous function is constructed using bilinear interpolation, the smoothing of the grayscale function is realized by Gaussian local filtering, and the grayscale gradient and Hessian matrix are calculated with high accuracy. On small-scale blocks, the pixels are classified by adaptively setting the grayscale threshold to identify potential line segments and mini-fillings. On the global image, potential line segments and mini-fillings are spliced together by progressing the block frontier layer-by-layer to identify and mark multiform fractures. The accuracy of identifying multiform fractures is improved by constructing a grayscale continuous function and adaptively setting the grayscale thresholds on small-scale blocks. And the layer-by-layer splicing algorithm is performed only on the domain of the 2-layer small-scale blocks, reducing the complexity. By using rock mass images with different fracture types as examples, the identification results show that the proposed algorithm can accurately identify the multiform fractures, which lays the foundation for calculating the mechanical parameters of rock masses.

Otsu Image Segmentation Algorithm Based on Hybrid Fractional-Order Butterfly Optimization

To solve the drawbacks of the Otsu image segmentation algorithm based on traditional butterfly optimization, such as slow convergence speed and poor segmentation accuracy, this paper proposes hybrid fractional-order butterfly optimization with the Otsu image segmentation algorithm. G-L-type fractional-order differentiation is combined with the algorithm’s global search to improve the position-updating method, which enhances the algorithm’s convergence speed and prevents it from falling into local optima. The sine-cosine algorithm is introduced in the local search step, and Caputo-type fractional-order differentiation is used to avoid the disadvantages of the sine-cosine algorithm and to improve the optimization accuracy of the algorithm. By dynamically converting the probability, the ratio of global search to local search is changed to attain high-efficiency and high-accuracy optimization. Based on the 2-D grayscale gradient distribution histogram, the trace of discrete matrices between classes is chosen as the fitness function, the best segmentation threshold is searched for, image segmentation is processed, and three categories of images are chosen to proceed with the segmentation test. The experimental results show that, compared with traditional butterfly optimization, the convergence rate of hybrid fractional-order butterfly optimization with the Otsu image segmentation algorithm is improved by about 73.38%; meanwhile, it has better segmentation accuracy than traditional butterfly optimization.

Identification method of raindrops and hailstones based on digital holographic interference.

The identification of raindrops and hailstones is of great significance to the study of precipitation characteristics from the aspect of microphysics and can provide important data support for weather modification. In this paper, an identification method of raindrops and hailstones based on digital holographic interference is proposed. The grayscale gradient variance method is used to obtain the focus position of the particles. By means of binarization and morphological processing, digital holograms are processed to obtain clear profiles of the particles. Then the contour parameters of the particles are used to obtain the equivalent volume diameter and roundness. Finally, according to the equivalent volume diameter, roundness and lens-like effect of the particles, the phase states of the raindrop and hailstone are identified by the algorithm. Experiments show that the method proposed in this paper has a good identification effect on raindrops and hailstones. The research results can provide reference for the research of the identification method of raindrops and hailstones and the acquisition of accurate characteristic parameters.

A saturation channel detection method for surface defects of silicon nitride bearing rollers based on adaptive gamma correction-edge threshold segmentation coupling algorithm

For the problem that the surface defects in Si3N4 ceramic bearing rollers are fuzzy, it is difficult for traditional single algorithms to achieve accurate localization and detection of surface defects. An adaptive gamma correction and edge threshold segmentation coupling algorithm is designed to accurately detect surface defects in the intensity channel of Si3N4 ceramic bearing rollers. To preserve the surface defects information to the greatest extent, the HSI intensity channel image characteristics of a single surface defects in Si3N4 ceramic bearing roller is analyzed. To obtain the best γ value of a single image, an adaptive gamma correction function equation is constructed. Analyze the frequency-domain characteristics of the three-dimensional grayscale curve of surface defects, and the grayscale gradient of surface defects is extended. Use the non-maximum value suppression model to suppress noise and background information, and perform sharpening enhancement and threshold segmentation on defect edge information. The mean PSNR of the surface defects images of the Si3N4 ceramic bearing roller is 28.9161 dB. The mean information entropy is 3.7572 bit. The accuracy of the detection result is 96.3%. The surface defects intensity channel detection method effectively improves the accuracy and efficiency of locating and detecting surface defects of Si3N4 ceramic bearing rollers.

Wave force measurement on a large-scale vertical cylinder using a visual technique

Visual techniques were used to identify the wave force on a large-scale vertical cylinder for the first time in this study by tracking the dynamic waterlines around the cylinder. Experimental validation of the proposed method with two types of waves, regular and irregular, was conducted in a wave flume. Four cameras were used to capture images synchronously, and the dynamic waterlines around the cylinder were identified using a grayscale gradient of pixels. Based on the potential theory, the wave force, including the linear and part of the second- and higher-order force components, was identified using recursive least squares (RLS) in real-time. The identified wave force agreed well with the wave force measured by the load cells, particularly the linear wave forces. The identified results could be significantly improved by considering the nonlinear wave forces. The proposed method has broad applications for laboratory measurements of wave loads on cylindrical structures.

Identification Research of Trichagalma Glabrosa Insect Gall Pests Based on YOLOv5s

In order to solve the problem of low image identification accuracy of Trichagalma glabrosa insect gall pests in a complex natural environment, an image identification method of Trichagalma glabrosa insect gall pests based on YOLOv5s was designed and introduced in this study. The original images were preprocessed with the grayscale maximum method and different gradients of noise, which reduced the color difference interference with complex backgrounds and improved the image identification rate. A total of 6090 images of insect gall pests under opposite light, back light, and complex backgrounds were constructed, which were divided into a training set and a test set with a ratio of 7 : 3. The results showed that the precision, recall, and mean average precision of YOLOv5s were 94.35%, 95.42%, and 95.8%, respectively. YOLOv5s, YOLOv4, and Faster-RCNN were compared and analyzed under the same test conditions. The identification accuracy of YOLOv5s was higher than that of YOLOv4 and Faster-RCNN, and its model size was only 13.8 MB. It was considered that the designed YOLOv5s method could help accurately and quickly identify Trichagalma glabrosa insect gall pests with high identification accuracy and a small model capacity, which was more conducive to the migration application of the model, and provide a new method for the rapid identification of Trichagalma glabrosa insect gall pests in a complex natural environment.

Early apple bruise recognition based on near-infrared imaging and grayscale gradient images

Early apple bruises, especially those occurring within half an hour, usually have no external symptoms and are difficult to recognize. This study developed a fast and nondestructive detection method for early bruises based on near-infrared camera imaging and image recognition. A total of 31 apple samples were photographed on both sides of each apple. Grayscale images of the sound apples were captured using a near-infrared camera with a wavelength region between 900 and 2350 nm. Images (n = 62) of apples without bruises were collected. The identical apples were artificially damaged and photographed at two stages (0 h, 0.5 h) by the near-infrared camera, and a total of 186 grayscale images were collected. As the light spot on the surface of apples limits the accuracy in detecting defects, a compound image pre-processing method was proposed consisting of nonlinear grayscale transformation and frequency-domain image filtering techniques. Finally, the gradient image is obtained by taking the first-order derivative of the preprocessed image. Since bruise had distinct edges, the gradient grayscale images of apples are more favorable for bruise identification. The compound method obtained a 97.62% classification accuracy for nonbruised apples and apples with fresh bruises. The experimental results show that it is feasible to identify early bruises in apples based on near-infrared camera imaging and gradient grayscale images. In the subsequent study, the method will be further improved, especially the parameters involved in the algorithm could be adjusted to adaptive variables. In addition, the system will be explored to be suitable for online apple bruise detection.

Robust descriptor for key-point detection and matching in color images with radial distortion

Constructing descriptors for key points in image matching is a crucial task in computer vision, visual tracking, and pattern recognition. Highly rated descriptors such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF) utilize the grayscale gradient information of the square regions around the key points. Nevertheless, these famous descriptors fail to take advantage of the image color information. Furthermore, their performances will be severely degraded for distorted images and the error due to rotation of their square windows. To address the problems, we proposed Circular Coordinate Combining Shape–Color Descriptor Under Distortion Based SURF (CSCD-SURF) that achieves competitive performance for colorful images with distortion contamination and numerical similar structures. The proposed approach can generate scale-space by adaptive filter to rectify distortion and integrate the SURF descriptor and shape–color information into our own custom concentric circular coordinate with flying colors. Experiments with Institut National de Recherche en Infomatique et Automatique dataset and spherical radial distortion-SIFT distorted image datasets prove that the ability of distortion rectification as well as matching performance against rotation, scaling, viewpoints, and blurring is more competitive than the state-of-the-art methods and its computation cost is acceptable.

Evaluation of microenvironment cleanliness for computer assisted sperm analysis system based on fusion of neutrosophic feasures

Background and ObjectiveComputer assisted sperm analysis (CASA) provides a quantitative assessment of the quality of male fertility. But sometimes there are difficulties in comparing among diagnoses of different laboratories due to the deficiency of quality control indicators, especially for microenvironment cleanliness. An unclean microenvironment may seriously degrade the quality of microscopic images, resulting in diagnosis inaccuracy. The primary reason for the scarcity of microenvironment cleanliness indicators is non-sperm objects can't be recognized from microscopic images accurately. In this paper, to overcome the issues mentioned above and lay a foundation for CASA's quality control from the perspective of digital image processing, an algorithm for non-sperm objects extraction was designed and then an approach for evaluating of microenvironment cleanliness proposed. MethodFirst, two features neutrosophic grayscale and neutrosophic gradient were designed. Then based on them, a neutrosophic similarity measurement was developed. Combined with Otsu method, the measurement was applied to extract non-sperm objects by adjusting the value of noise factor. Finally, the indicator ratio of non-sperm objects (RNSO) was formed for evaluating the degree of microenvironment cleanliness. ConclusionThe experiments demonstrated non-sperm targets can be extracted efficiently and effectively by adjusting the noise factor of the proposed algorithm. The RNSO indicator can reflect microenvironment cleanliness degree properly and indicate whether the operations of sample production or video acquiring meet standards. So, it can provide convictive and quantitative information for CASA's quality control.

Impact of order of catalytic ethylene and propylene polymerization on nanometer scale isotactic polypropylene‐polyethylene blend morphology in nascent heterophasic granules revealed by low voltage scanning electron microscopy and scanning transmission electron microscopy

AbstractNew heterophasic granules comprised of two high molecular weight semi‐crystalline components ‐ polyethylene (PE) and isotactic polypropylene (iPP) ‐ are prepared from a MgCl2 supported Zeigler‐Natta catalyst. The impact of order of monomer addition on granule morphology and extent of mixing of PE and iPP in these monomer‐to‐polymer scenarios are examined. In one polymerization propylene is followed by ethylene (iPP‐PE; 1), and in the second ethylene is followed by propylene (PE‐iPP; 2). Detailed morphological assessments were carried out on RuO4 stained sections of the nascent granules of these heterophasic products using low voltage scanning electron microscopy (LVSEM) and scanning transmission electron microscopy (STEM). In these side‐by‐side granule morphology comparisons, LVSEM, which has not been used for granule examinations, has proved to be invaluable, typically providing insights into phase morphology that STEM does not. Both polymerizations 1 and 2 result in intimate mixing of PE and iPP on the tens to hundreds of nanometer scale. However, morphological outcomes for 1 and 2 are markedly different. In the case of 1, comprising 31 wt% iPP and 69 wt% of PE (the second‐grown phase), a reticulated mesh network of PE is readily observed coursing through much of the first produced iPP globular and sub‐globular matrix. The PE fibrils that comprise this network are remarkably uniform in diameter; approximately 100–150 nm. This aspect of the morphology is consistent with a PE sheath encapsulating both iPP globules and sub‐globules commonly found in iPP homopolymer granules made with MgCl2 catalysts. This morphology is similar to that of the most extensively studied heterophasic granules, classic iPP‐ethylene‐propylene rubber (EPR) impact copolymer (ICP), where the second grown EPR fills in space between and around the iPP globules and sub‐globules. Thus, the dominant morphology of 1 is consistent with the often‐called pore‐filling model. Using the same catalyst and arriving at a similar global composition (65 wt% PE and 35 wt% iPP), sample 2 is produced through the reverse order of monomer addition. The dominant morphology for 2 cannot be explained by the pore‐filling model. Instead, LVSEM most clearly shows that the second grown iPP phase, is finely dispersed throughout the PE matrix (not outside it) as irregularly shaped inclusions that are nominally 100 to 400 nm in diameter, so the dominant morphology in 2 is consistent with the proposed but not previously observed core‐shell model. The STEM results for 2 also reveal the presence of primitive PE spherulites and organized PE lamellae in the granules; structures not found in 1 and apparently not reported before in polyethylene homopolymer granules. These structures form likely from heat released during ethylene polymerization in the first step in 2. In LVSEM, the PE and iPP phases provide different amplitude contrast (grayscale) that is useful for calibration. In the LVSEM images of both samples 1 and 2, non‐binary strong grayscale gradients are observed in many regions in the micrographs. These suggest, but do not yet prove, fine dispersion of some PE in the first formed iPP (1) as well as a fine dispersion, perhaps on the ~10 nm scale, of some iPP in the first formed PE (2). So even granules of 1 appear to have some hybrid quality; primarily pore‐filling, with some core‐shell result as well. Finally, in STEM images of both 1 and 2 well‐formed, long PE lamella provide occasional marked contrast (especially at boundaries) with nascent iPP, which exists in a microparacrystalline state (short, poorly formed crystals). Regardless of the morphological complexity, the exceedingly fine mixing of the two semi‐crystalline phases accomplished during dilation of the granules to accommodate each second produced crystallizable polymer offers the potential for utility of these heterophasic granules in materials design (grafting and cross‐coupling, for example).

Image segmentation and analysis for densification mapping of nanoporous gold after nanoindentation

Segmentation of scanning electron microscopy (SEM) images of focused ion beam (FIB) cross-sections through indented regions in nanoporous gold (np-Au) is carried out. A key challenge for image analysis of open porous materials is the appropriate binarization of the pore and gold ligament regions while excluding material lying below the cross-sectional plane. Here, a manual approach to thresholding is compared to global and local approaches. The global thresholding resulted in excessive deviations from the nominal solid fraction, due to a strong gray-scale gradient caused by the tilt angle during imaging and material shadowing. In contrast, the local thresholding approach delivered local solid fractions that were free of global gradients, and delivered a quality comparable to the manual segmentation. The extracted densification profiles vertically below the indenter as well as parallel to the surface showed an exponential-type decay from the indenter tip towards the nominal value of 1 far from the indenter.Graphic abstract

Mask Wearing Detection Method Based on the Skin Color and Eyes Detection

During the period of fighting against COVID-19, wearing masks is the main measure of protection in public places. In order to obey relevant regulations, railway stations, airports, shopping malls and other public places are equipped with staff to supervise citizens to wear masks. This method not only wastes human resources, but also has the disadvantage of significantly reducing the efficiency when the flow increases. In order to improve work efficiency, save human resources, and ensure the health and safety of staff, computer vision technology can be used to develop embedded device to deal with the task of automatic mask wearing detection. This paper proposes a mask wearing detection method based on the skin color and eyes detection. This method uses the ellipse skin model, the grayscale gradient features of eyes and the geometric relationship between eyes and other parts of face to locate the face region. And by calculating the coverage of skin color in nose and mouth area, this method gives a judgement of whether a man is wearing a mask properly. This method can basically deal with the task of mask wearing detection under the specific application scenario. It also has the advantages of small volume and strong interpretability.

Partial Discharge Pattern Recognition Based on 3D Graphs of Phase Resolved Pulse Sequence

Partial discharge (PD) is an important phenomenon that reflects the insulation condition of electrical equipment. In order to protect the safety of power grids, it is of significance to diagnose the type of insulation defects inside the equipment accurately and early through PD pattern recognition. In this article, phase resolved pulse sequence (PRPS) graphs in 3D were constructed by the PD pulse data of the gas-insulated switchgear (GIS) acquired, then the histogram of oriented gradient (HOG) features were extracted directly from the 3D PRPS graphs, and finally the attribute selective Naïve Bayes classifier was used to recognize the discharge pattern. In addition, this method was compared with two traditional methods, i.e., the statistical method and the grayscale gradient co-occurrence matrix method, from three aspects. The result shows that 3D PRPS graphs have different morphology characteristics in vision under different defects, and the similarity among different voltages applied is higher than among different defects, so it is reasonable to use them as the basis for PD pattern recognition. The contrast indicates that the HOG method not only has the highest accuracy with the least requirement for pretreatment and training, but it also has robustness when the voltage applied changes. Consequently, this method has the universality for PD pattern recognition that is based on 3D PRPS graphs.

A study of hepatic fibrosis staging methods using diffraction enhanced imaging

The early hepatic fibrosis staging is very important for timely diagnosis, prognosis, and treatment of all chronic liver diseases. Diffraction-enhanced imaging, which can provide much more information on soft tissue morphology than conventional absorption radiography, might be a potential noninvasive technique to diagnose and stage hepatic fibrosis. This paper presents different feature extraction strategies and classification methods to automatically classify hepatic fibrosis using diffraction-enhanced imaging images. Texture features are obtained using a total of three methods including first order feature, gray level co-occurrence matrix, and grayscale gradient co-occurrence matrix. The fusion of these texture features is also studied. The principal component analysis is used to reduce the dimension of the features and redundant information among data. The features are classified using two popular classification techniques, namely, K-nearest neighbors and support vector machines. On the basis of the comparison of different feature strategies and classification methods, we can identify the suitable methods for grading hepatic fibrosis. The proposed approach efficiently classifies the hepatic fibrosis DEI images into four classes with the highest classification accuracy of 99.99%. We further demonstrate the potential of the DEI images in staging hepatic fibrosis.