Gray Histogram Research Articles

Comparative Study of Different Classifiers Based on Extracted Facial Features for Supervised Age Estimation

Estimating a person age is a major concern for many researchers due to his importance in many applications, whereas finding a person age is crucial in making specific decision. This paper conducts a comparative study between two classification-algorithms for age estimation which applied on extracted Local Binary Patterns (LBP). It was also divided dataset into 3 classes in order to improve results and increasing accuracy of system, Root Mean Squared Error, Mean Absolute Error and other parameters are used to measure the precision of the system. The proposed methodology of this work is divided into three phases. First phase consists pre-processing methods in which selected image is handled using color to gray scale image conversion and histogram equalization. Result image of which is manipulated by standard Viola-Jones algorithm to detect and crop face area from the whole image. While to ensure same size for all images, detected face image is resized to 256 × 256. Second phase tends to extract LBP features to be fed in the next classification phase. In third phase, two classifiers Logistic Model Tree (LMT) as well as Sequential Minimal Optimization (SMO) have been applied on the extracted features for age estimation.

Research on Dynamic Measurement Method of Electromagnetic Environment Based on Image Similarity

In this paper, by discretizing the battlefield region, using the power, frequency and direction of the wave to quantitatively characterize the electromagnetic environment, the image similarity measure, the gray histogram comparison and the signal arrival direction histogram method are introduced to analyze the histogram. The degree of change of the graph is proposed, and a calculation method for calculating the degree of change of electromagnetic environment is proposed. The method is simulated. The comparison of the histograms at different time points proves that the method has certain effectiveness in dealing with various electromagnetic environments.

Whole-tumor histogram analysis of apparent diffusion coefficient maps in grading diagnosis of ependymoma

ObjectiveTo study the value of whole-tumor histogram analysis which is based on apparent diffusion coefficient maps in grading diagnosis of ependymoma.Methods71 patients with ependymal tumors were retrospectively analyzed, including 13 cases of WHO grade I, 28 cases of WHO grade II, and 30 cases of WHO grade III. Mazda software was used to draw the region of interest (ROI) in the apparent diffusion coefficient maps of three groups on every layer of tumor level. The whole-tumor gray histogram analysis was carried to obtained nine characteristic parameters, including mean, variance, kurtosis, skewness, Perc.01%, Perc.10%, Perc.50%, Perc.90%, and Perc.99%. When the parameters satisfy the test of normal distribution and homogeneity of variance, single factor analysis of variance (ANOVA) was carried to compare the three groups and LSD t test was performed to compare the two groups. Besides, the ROC curve was used to analyze the diagnostic efficacy of the parameters.ResultsVariance, Perc.01%, and Perc.10% had significant differences among the three groups (all P < 0.05). The remaining six parameters had no significant difference among the three groups (all P > 0.05). And, between WHO I and WHO II, the sensitivity and specificity of the Perc.10% were 85.7% and 100.0%, the AUC was 0.872, and the cut-off was 126.5. Between WHO I and WHO III, the sensitivity and specificity of the Perc.10% were 85.7% and 87.7%, the AUC was 0.835, and the optimum critical value was 131.33. Besides, the sensitivity, specificity, and AUC of variance between WHO II and WHO III are 68.4%, 76.9%, 0.794, and 2645.7, respectively. They had higher identification efficiency.ConclusionWhole-tumor histogram analysis of apparent diffusion coefficient (ADC) maps could provide ancillary diagnostic value in grading diagnosis of ependymoma. Perc.10% had a high diagnostic efficiency.

Image recognition method of building wall cracks based on feature distribution

In order to solve the building damage caused by cracks in the wall surface, based on feature distribution and SAR image segmentation technology, the cracks in the building wall were identified by extracting feature data images, de-noising and enhancing image edges, and segmenting target images. The validity and feasibility of the method are verified by the actual concrete wall image. The results show that the recognition accuracy of cracks in non-cracked walls is 100%, and that of longitudinal cracks is 78.2%. Compared with the color feature discrimination, this method has a good processing effect on the image, clear crack line, good coincidence degree with the original image, and crack width is close to the width of the original image. After processing the image with rough set, the recognition rate of the image is 98.1%, the false reject rate is 1.9%, the recognition time is 12 min, and the execution time of the algorithm is 126 s. After the processing of gray histogram, the feature distribution of image set has a certain distribution transfer, but the transfer effect is not particularly obvious. It can be found that this method has advantages of high recognition accuracy, short time, and practical application value, significantly enhancing pretreatment effect.

Unsupervised Specific Emitter Identification Method Using Radio-Frequency Fingerprint Embedded InfoGAN

Machine learning approaches are becoming increasingly popular to improve the efficiency of specific emitter identification (SEI). However, in most non-cooperative SEI scenarios, supervised and semi-supervised learning approaches are often incompatible due to the lack of labeled datasets. To solve this challenge, an unsupervised SEI framework is proposed based on information maximized generative adversarial networks (InfoGANs) and radio frequency fingerprint embedding (RFFE). To enhance individual discriminability, a gray histogram is first constructed according to the bispectrum extracted from the received signal before being embedded into the proposed framework. In addition to the latent class input and the RFFE, the proposed InfoGAN incorporates a priori statistical characteristics of the wireless propagation channels in the form of a structured multimodal latent vector to further improve the GAN quality. The probabilistic distribution of the bispectrum is derived in closed-form and the convergence of the InfoGAN is analyzed to demonstrate the influence of the RFFE. Numerical results indicate that the proposed framework consistently outperforms state-of-the-art algorithms for unsupervised SEI applications, both in terms of evaluation score and classification accuracy.

Three-Dimensional Reconstruction of Fuzzy Medical Images Using Quantum Algorithm

In order to deal with the problems of poor anti-interference, low reconstruction clarity and large errors in the traditional medical image reconstruction methods, we proposed a fuzzy medical images three-dimensional (3D) reconstruction method using quantum algorithm. First of all, a feature matching model of fuzzy medical image was built. Secondly, this study decomposed the edge contour features by using the Gaussian mixture feature matching method, extracted the edge contour vectors of fuzzy medical image, and enhanced the information of fuzzy medical images by adopting the region edge sharpening. Thirdly, this study reorganized the 3D texture structure of images and reconstructed the sparse scattered points according to its texture and detail regions. Finally, we combined with the gray histogram of fuzzy medical images to achieve the adaptive pixel reconstruction of fuzzy medical images, and completed the 3D reconstruction of fuzzy medical images by employing the quantum algorithm. The results show that the proposed method is characterized by high matching degree of image features and balanced distribution of point clouds, and the self-similarity coefficient of the reconstructed texture can reach 0.994; in addition, the SINR value of the reconstruction result can be maintained around 100dB, and it has lower error rate than the traditional method, thereby improving the detection and recognition capability of medical images, and the algorithm has certain practical application.

Application of chlorophyll fluorescence imaging technique in analysis and detection of chilling injury of tomato seedlings

Low temperature is one of the main environmental factors limiting plant geographical distribution and crop production. Chilling injury is a stress caused by low, nonfreezing temperatures (0–12 °C). Since chilling injury is an important facility agriculture problem in northeast China regions, we aimed to study a suitable method for evaluate the potential of chlorophyll fluorescence imaging for the detection of chilling injury in tomato Seedlings. Here, four types of chlorophyll fluorescence image features were used to study and analyze chilling injury classes: chlorophyll fluorescence parameter values, histograms, textures and color descriptions. The Pearson correlations of the features in each type were calculated, and eligible features were input into BPNN model to identify chilling injury classes of leaf. Our results reveal six fluorescence parameter values of Y (II), qP, qL, Y (NPQ), Y (NO) and Fv/Fm can be used to evaluate the chilling injury classes of tomato seedlings. The identification accuracy rate of training set was 90.3%, and that of the validation set was 90%. The Skewness of the gray histogram features and standard deviation of entropy of the texture can be used to evaluate the chilling injury classes of tomato seedlings. The identification accuracy rates of training sets were 88.1% and 72.6%, respectively, and that of the validation set were 82.5% and 61.7%, respectively. The B, b and L/b of the color descriptor features can also be used to evaluate the chilling injury classes of tomato seedlings. The identification accuracy rates of the training sets were 89.8%, 91.9% and 90.1%, respectively, and that of the validation sets were 87.5%, 90.8% and 90.0%, respectively. Our research showed that the best recognition accuracy was b and L/b of the color descriptor features, as well as fluorescence parameter values, and the recognition accuracy are all more than 90%. Therefore, chlorophyll fluorescence imaging was recommended for the detection of chilling injury classes of tomato seedlings under low temperature stress, and had a good evaluation effect. The data reported in this manuscript should foster new research method for the detection of the chilling injury classes and have considerable prospects for non-destructive diagnosis of plant chilling injury.

A new chaotic circuit with multiple memristors and its application in image encryption

In this paper, a new seventh-order mixed memristive chaotic circuit was designed, and the new mathematical model of the system was established. The origin as the only equilibrium point was calculated. Based on the chaotic secret key generated by the memristive chaotic circuit system, the new algorithm of the image encryption was designed. In particular, by using the security analysis methods of gray histogram, correlation and robustness, the security feature of the new encryption algorithm was analyzed. And the results show that the encryption algorithm based on this mixed memristive chaotic system has higher security and better anti-decoding ability. In comparison with the simple model of the memristive chaotic circuit, this new memristive chaotic circuit model has complete RLC structure and multiple memristors. It is closer to the actual memristive chaotic circuit. Thus, it is of great significance to the commercial realization of the memristive circuit. In particular, the memristive chaotic system also provides a valuable model of the system for the research of the related fields.

B-mode ultrasonography and gray scale histogram for evaluation of the nuchal ligament in Quarter horse

ABSTRACT: The gray scale histogram (GSH) makes it possible to measure the amount and distribution of gray shade frequencies, providing quantitative information on both echogenicity and echotexture of tissues. There is a need to diminish the subjectivity of the ultrasound images of the nuchal ligament (NL). This work proposes to evaluate the NL by ultrasound B-mode GSH images in different ages of Quarter horses. It used 15 healthy Quarter horses, which were classified by age into three different groups: “baby” (1), “sobreano” (2) and “adult” (3). The animals were submitted to chemical restraint for the ultrasound examination. Subsequently, the GSH tool was used in each image for statistical analysis. There was a significant difference between Mean and Mode between groups. Group 1 differed significantly when compared to Group 2 and 3. Group 2 presented superior echogenicity to Group 1 and 3. The height of the NL did not vary considerably between groups. GSH indicated that the echogenicity of NL in Quarter horses varies with age.

Analysis and detection of decayed blueberry by low field nuclear magnetic resonance and imaging

Decay is a major cause of quality loss and food safety concerns for blueberry fruit. Low-field nuclear magnetic resonance (LF-NMR) has been used to analyze and detect decayed blueberry fruit. According to NMR relaxation analysis, transverse relaxation time (T21, T22, T23) of decayed fruit increased to different degrees, while signal amplitude (A21, A22, A23) decreased to different degrees. Six relaxation features were input into BPNN model to identify the decay classes of fruit. The identification accuracy of training set was 86.7%, and that of the validation set was 90%. According to magnetic resonance imaging (MRI), twice threshold segmentation algorithm was proposed to segment the decayed region with dark color. A total of 15 features were extracted from gray histogram, gray level co-occurrence matrix (GLCM) and gray level-gradient co-occurrence matrix (GGCM) of the image for correlation analysis. Five features were then input into a back propagation neural network (BPNN) model. The identification accuracy of training set was 92.2%, and that of the validation set was 83.3%. Finally, 11 variables, including transverse relaxation features and image features, were input into the BPNN model. The identification accuracy of training set was 98.8%, and that of the validation set was 94.2%, which showed the highest identification accuracy. The results showed that LF-NMR and MRI are suitable for analyzing and detecting the decay disease of fruit, which provides a theoretical basis for nondestructive detection of fruit disease.

Recognition of Concrete and Gray Brick Based on Color and Texture Features

Abstract Identification and classification of construction waste are two important aspects of construction waste recycling. This study proposes a method based on image processing to identify gray brick and concrete, the most difficult types to identify that have the highest percentage of construction waste. By combining color features with texture features, machine learning algorithms are used for training and recognition. We paid great attention to the comparison of the performance of different color models, which includes Red, Green, Blue (RGB), Hue, Saturation, Value (HSV), and Lab. We found that gray histograms and color moments were suitable as color features of concrete and gray bricks. Meanwhile, the eigenvalues of the gray-level co-occurrence matrix (GLCM) were also discussed. Contrast, angular second moment, inverse different moment, and correlation in the five eigenvalues of GLCM were selected as texture features via experiments. We used three machine learning algorithms to train the extracted data. The results showed that the extreme learning machine had the lowest accuracy (96.25 %), whereas the support vector machine and back propagation algorithm had higher accuracy of 96.875 % and 98.125 %, respectively. The online testing had the accuracy of 95 %, indicating that the selected features are effective, and the accuracy can meet the engineering needs.

Paraspinal Muscle Segmentation Based on Deep Neural Network.

The accurate segmentation of the paraspinal muscle in Magnetic Resonance (MR) images is a critical step in the automated analysis of lumbar diseases such as chronic low back pain, disc herniation and lumbar spinal stenosis. However, the automatic segmentation of multifidus and erector spinae has not yet been achieved due to three unusual challenges: (1) the muscle boundary is unclear; (2) the gray histogram distribution of the target overlaps with the background; (3) the intra- and inter-patient shape is variable. We propose to tackle the problem of the automatic segmentation of paravertebral muscles using a deformed U-net consisting of two main modules: the residual module and the feature pyramid attention (FPA) module. The residual module can directly return the gradient while preserving the details of the image to make the model easier to train. The FPA module fuses different scales of context information and provides useful salient features for high-level feature maps. In this paper, 120 cases were used for experiments, which were provided and labeled by the spine surgery department of Shengjing Hospital of China Medical University. The experimental results show that the model can achieve higher predictive capability. The dice coefficient of the multifidus is as high as 0.949, and the Hausdorff distance is 4.62 mm. The dice coefficient of the erector spinae is 0.913 and the Hausdorff distance is 7.89 mm. The work of this paper will contribute to the development of an automatic measurement system for paraspinal muscles, which is of great significance for the treatment of spinal diseases.

Flame front identification and its effect on turbulent premixed flames topology at high pressure

Image processing is of primary importance in the laser diagnostic on turbulent combustion, which can provide quantitative information, such as velocity field, intermediate species profile. Turbulent premixed flame front indicates the flame-turbulence interaction, can be decided from the OH-PLIF (Planar Laser Induced Fluorescence) technique due to the sharp increase of the OH distribution from unburned to burned region. In this paper, an adaptive threshold binarization method was proposed based on the local gray histogram of the OH-PLIF images when the signal-noise ratio is relatively low, i.e. turbulent flames at intensive turbulence and high pressure. The noise was eliminated by seed-mediated growth to obtain the legible flame front. Effect of different flame front identification methods, namely global binarization method, the canny operator of Matlab and the proposed adaptive threshold binarization method, on the flame structure parameters at various conditions was investigated. Results show that the flame fronts are seriously vague using the global binarization and the canny operator when the signal-noise ratio is low at intensive turbulence and high pressure, while continuous flame front can still be attracted by the proposed adaptive threshold binarization method. The turbulent flame front parameters from different methods are almost identical at weak turbulence and atmospheric pressure. While due to the noise introduced, the value of flame brush thickness, flame height and flame surface density from the proposed method is smaller than that of other two methods at high pressure. The adaptive threshold binarization method can obtain a better flame front identification at low signal-noise ratio conditions, results in reasonable premixed turbulent flame front parameters at intensive turbulence and high pressure.

Performance Evaluation of Kernel-Based Feature Extraction Techniques for Face Recognition System

Face recognition is considered to be one of the most reliable biometrics where security issues are of concerned. Feature extraction which is a functional block of a face recognition system becomes a critical problem when there is need to obtain the best feature with minimum classification error and low running time. Most existing face recognition systems have adopted different non-linear feature extraction techniques for face recognition but identification of the most suitable non-linear kernel variants for these systems remain an open problem. Hence, this research work analyzed the performance of three kernel feature extraction technique (Kernel Principal Component Analysis, Kernel Linear Discriminant Analysis and Kernel Independent Component Analysis) for face recognition system. A database of 360 face images was created by obtaining facial images from LAUTECH Biometric Research Group consisting of six facial expressions of 60 persons. Images were preprocessed (gray scaling, cropping and histogram equalization) and the kernel variants were used to extract distinctive features and reduce the dimensionality of each of the images from 600x800 pixels to four smaller dimensions: 50x50, 100x100, 150x150 and 200x200 pixels. Euclidean Distance similarity measure was used for classification. The performance of the three kernel variants was evaluated for face recognition system using 180 images for training and 180 images for testing using the following metrics: Recognition Accuracy (RA) and Recognition Time (RT). Empirical result indicate that KLDA performs best for face recognition system with an average accuracy of 94.52%. The larger image dimension also results in better recognition performance. We intend to experiment on other classifiers for face recognition system in our future work. Keywords— Biometrics, Face, Feature extraction, Kernel, KICA, KPCA, KLDA, Linear, Non-linear;

Cracking Evolution and Failure Characteristics of Longmaxi Shale Under Uniaxial Compression Using Real-Time Computed Tomography Scanning

To determine the cracking and failure characteristics of Longmaxi shale in deformation and failure under loading, cylindrical specimens were prepared to conduct a series of uniaxial compression tests. Real-time computed tomography (CT) at different stress levels were used to obtain reconstructed stereograms, and horizontal CT images and vertical slices were obtained for analysis. Based on the CT images and slices, the cracking evolution of Longmaxi shale in the horizontal and vertical direction was determined qualitatively, the quantitative distributions of crack area during the loading were revealed and the variation in crack volume at different stress levels was first obtained. Based on the grey histogram of the reconstructed three-dimensional volume, the initial mineral distribution, internal pore evolution and final crack morphologies and volumes were established and their inter-relationship was discussed. These qualitative and quantitative results are necessary to characterize and understand the cracking evolution and failure characteristics of the Longmaxi shale.

Gray Scale Histogram Analysis of Carpal Tunnel Syndrome with Ultrasonography.

In this study, we aim to evaluate the diagnostic value of echogenicity ratio with histogram analyses. This retrospective study was performed on 22 patients with 44 hands. The patients had clinical presentations consistent with CTS, in at one hand. Quantitative ultrasound scanning and image capture were completed using a diagnostic sonography machine. For gray scale histogram analysis, image J software was used. Mean flexor tendons histogram analysis echogenicity/Mean median nerve histogram analysis echogenicity was significantly high for 1,7 cutoff value. Mean FTE/MNE ratio may be a useful sonographic parameter for CTS.

A Modified Robust FCM Model with Spatial Constraints for Brain MR Image Segmentation

In brain magnetic resonance (MR) images, image quality is often degraded due to the influence of noise and outliers, which brings some difficulties for doctors to segment and extract brain tissue accurately. In this paper, a modified robust fuzzy c-means (MRFCM) algorithm for brain MR image segmentation is proposed. According to the gray level information of the pixels in the local neighborhood, the deviation values of each adjacent pixel are calculated in kernel space based on their median value, and the normalized adaptive weighted measure of each pixel is obtained. Both impulse noise and Gaussian noise in the image can be effectively suppressed, and the detail and edge information of the brain MR image can be better preserved. At the same time, the gray histogram is used to replace single pixel during the clustering process. The results of segmentation of MRFCM are compared with the state-of-the-art algorithms based on fuzzy clustering, and the proposed algorithm has the stronger anti-noise property, better robustness to various noises and higher segmentation accuracy.

Sub-pixel extraction of laser stripe in complex background

The complex background and laser stripe noise affect laser stripe extraction. Adaptive double threshold segmentation method and the improved gray weight model are proposed in this study. First, the characteristics of the laser stripe and the source of noise in the image are investigated. Bilateral filter is applied to remove the noise of images. Subsequently, the gray histogram of laser image and the double threshold are computed. By sub-regional processing, initial stripe center and stripe width of binary images are obtained. Finally, the sub-pixel center of the laser strip is extracted by the proposed model. The double threshold segmentation method and the improved gray weight model are compared with the traditional algorithms. The results show that the double threshold method is more accuracy in extracting the laser stripe region than the extreme value method and the Otsu method. Comparing with the residual value of sub-pixel center, the improved gray weight model (0.23) has better results than the gray-gravity method (0.71), the extreme value method (0.86), and the Gaussian fitting method (0.86). The algorithms proposed in this study avoid the impacts of complex background and laser stripe noise, increase the accuracy of the laser stripe center positioning and extract the stripe center extraction fast and accurately in complex backgrounds.

A novel local texture feature extraction method called multi-direction local binary pattern

A novel method named MD-LBP (Multi-Direction Local Binary Pattern) is proposed in this paper to capture the excellent local texture features. Based on LBP (Local Binary Pattern), the proposed method is a local feature extraction method, which optimized the coding scheme by considering the relationship between the center pixel and the weighted pixels in its neighborhood. Furthermore, unlike the original gray scale histogram method, the proposed method used a new way to get the feature vector which not only describes the holistic spatial information of image, but also reduces the image dimension. The proposed method is evaluated by extensive experiments on benchmark databases, such as CMU PIE and Extended Yale B face database, PolyU and CASIA Palmprint database. The experimental results show that the proposed method MD-LBP, can significantly capture the useful local texture features, and improve the recognition rates both in face and palmprint fields.

A fast threshold segmentation method for froth image base on the pixel distribution characteristic

With the increase of the camera resolution, the number of pixels contained in froth image is increased, which brings many challenges to image segmentation. Froth size and distribution are the important index in froth flotation. The segmentation of froth images is always a problem in building flotation model. In segmenting froth images, Otsu method is usually used to get a binary image for classification of froth images, this method can get a satisfactory segmentation result. However, each gray level is required to calculate each of the between-class variance, it takes a longer time in froth images with a large number of pixels. To solve this problem, an improved method is proposed in this paper. Most froth images have the pixel distribution characteristic that the gray histogram curve is a sawtooth shape. The proposed method uses polynomial to fit the curve of gray histogram and takes the characteristic of gray histogram's valley into consideration in Otsu method. Two performance comparison methods are introduced and used. Experimental comparison between Otsu method and the proposed method shows that the proposed method has a satisfactory image segmentation with a low computing time.