Gray Histogram Research Articles

Recognition of facial sketch styles

Abstract The style recognition of facial sketches drawn by artists contributes great to the painting authentication, digital entertainment and law enforcement. This paper presents a framework to automatically classify different styles of facial sketches based on support vector machines (SVM) and selective ensemble (SE) strategy. Some handwritten features are deployed to feed into SVM classifiers. The framework proceeds as follows: firstly, each geometrically normalized image is divided into five important parts: the whole image, left eye, right eye, nose, and mouth; Secondly, based on the analysis to the technique of the facial sketch artists, gray histogram, gray moment, speeded up robust feature and multiscale local binary patterns are explored to extract handwritten features from each part; Thirdly, SVM is explored to learn the mapping relationship from handwritten features of each part to the style of the artist and thus we obtain multiple classification scores; Finally, we combine these complementary classification scores via SE scheme. Our model is able to achieve the recognition rates of 94% and 96% respectively on two groups of sketches drawn by five artists which would be available on the website.

MULTI-PARAMETER MRI ANALYSIS IN THE NATIONAL PRION COHORT

Quantitative MRI measures can detect the presence of microstructural pathology in human prion disease not visible on conventional MR imaging. Few studies have examined longitudinal change and correlation with clinical measures. To test if longitudinal change could be identified on quantitative MRI, we performed a multiple-parameter analysis in the largest data set of patients with prion disease to date. Multiple-parameter analysis of quantitative MRI sequences including diffusion tensor imaging, magnetisation transfer ratio and T2-weighted imaging was performed in 106 subjects (37 asymptomatic gene mutation carriers, 39 symptomatic patients and 30 healthy controls). The analysis included voxel-based morphometry, voxel-based analysis of diffusion tensor imaging and magnetisation transfer imaging measures, grey and white matter histograms and region of interest analysis. Symptomatic patients showed significant longitudinal grey matter atrophy. Additionally a significant decrease in magnetisation transfer ratio and mean diffusivity was observed in grey matter structures; the decline in all MRI parameters strongly correlated with a decline in a functionally orientated outcome measure, the MRC Prion Disease Rating Scale. These data show that multi-parameter MRI analysis can identify longitudinal microstructural grey matter changes and may be able to provide objective and anatomically-specific biomarkers of disease progression in future clinical trials.

Adaptive Moving Vehicle Detection Algorithm Based on Hybrid Background Subtraction and Frame Difference

This paper proposes an adaptive moving vehicle detection algorithm based on hybrid background subtraction and frame difference. The background image of continuous video frequency is reconstructed by calculating the maximun probability grayscale using grey histogram; Moving regions is gained by frame defference, the initial target image is obtained by background difference method,moving regions image and initial target image AND,XOR and OR operations to get the vehicle moving target images. Experimental results show that the algorithm can response timely to the actual scene changes and improve the quality of moving vehicle detection.

Imaging critical fluctuations of pure fluids and binary mixtures.

We use optical microscopy techniques to directly visualize the structures that emerge in binary mixtures and pure fluids near their respective critical points. We attempt to understand these structures by studying the image formation using both a phase contrast and a dark field filter to our microscope. We found that images of critical fluctuations for both liquid-liquid and liquid-gas critical systems have gray level intensity histograms with Gaussian shape. For all fluids investigated, the temperature-dependent standard deviation of the Gaussian histogram follows a power law with the same exponent. Since the image intensity fluctuations are determined by order parameter fluctuations, this direct imaging method allowed us to estimate the critical exponent of compressibility with very good accuracy.

Wood species identification using improved active shape model

In this paper, we propose a robust wood species identification scheme by using color wood surface images. First, a novel wood image acquirement system is devised, and the wood color image is converted into a V1V2I color-base image. Second, the corresponding grey histograms for V1 and V2 are established. Third, an improved active shape model is used to fulfill the curve deformation of the histogram curve of the standard specimen. This active shape model will then converge to the histogram curve of the test specimen. Finally, wood recognition is performed by comparing the initial and final active shape models with the histogram curve of the test specimen. We have experimentally proved that this scheme improves the mean recognition accuracy to approximately 90% for 5 wood species and that it can also be applied to the Gaussian noisy images. Moreover, the recognition accuracy can be further improved by combining this scheme with the texture feature recognition.

An Improved LBP Method for Face Recognition

In order to improve the accuracy of human face recognition and reduce the computational complexity, we proposed a based Low Resolution Completed Local Binary Pattern method. Firstly, we used the preprocessed face images to extract the low resolution image during the filtering operation; then CLBP operator is used to extract the face gray image histogram; and fused into a CLBP histogram for comparison; finally the face image will be identified according to the proximity principle. The experimental results on ORL and AR show that the method has a better recognition effect, with shorter, more robust.

Analyses on CT Image of Gray Rock Uniaxial Compressive Failure Process Based on MATLAB

The uniaxial compressive failure process CT images of gray rock were analysised based on Matlab. Matlab is used to transfer gray rock CT images into gray histogram which can be observed directly so as to see clearly the damage evolution process of gray rock under loading. By comparison, gray histogram is consistent with the result presented by original CT image. The gray histogram equalized by Matlab can show clearly the change trend and process of gray rock internal defects and micro cracks. Gray histogram is a good method to observe and analyses CT images.

Study on an Improved Median Filtering Algorithm

Median filter is a very effective method of non-linear smoothing filtering. However, the data ordering for traditional median filtering (TMF) is very time-consuming and hardly satisfy real-time image processing. This article proposes a kind of fast median filtering algorithm based on grey histogram, the filter seeks the median through the grey histogram of mask window, not the numeric sort, which decreases the comparison times. Moreover, the update of histogram by using the overlap of mask window increases the arithmetic processing speed. Meanwhile, in the proposed algorithm, the two-level self-adapting threshold comparison, with a higher precision of detection, is used to implement the inspection of noise point and improve the image quality and increase the signal-noise ratio by processing the noise point and non-noise point respectively. The experiments by matlab simulation can prove the availability of this algorithm.

Lane Mark Identifying and Tracking Base on Edge Enhancement

In order to improve the accuracy of lane mark line identifying and tracking, this paper uses the LOG operator for edge enhancement, so the useful information is changed into straight lines and the useful feature is obvious. And the paper uses the algorithm of 2-D gray histogram to segment the image. Then it uses Hough transformation to identify the lane mark’s two edges and account its intercept and slope, then draws the midline as the final identifying result. Finally in order to reduce the count time, the paper uses the identifying results of the last frame image limit the current frame image recognition areas in tracking lane mark. The experiments results show that the lane mark can be tracking dependably and the algorithms are real-time, moreover, when the algorithm is failure, the system can also recover in time, and locks the tracking target accurately again.

Date quality evaluation using short-wave infrared imaging

An efficient histogram analysis algorithm is proposed for real-time automated fruit surface quality evaluation. This approach, based on short-wave infrared imaging, provides excellent image contrast between the fruit surface and delaminated skin, which allows significant simplification of image processing algorithm and reduction of computational power requirements. The proposed method employs a very efficient training procedure to produce a normalized gray scale histogram and its corresponding skin threshold for each quality class. By histogram comparison, the test fruit is assigned to one of the four quality classes and an adaptive threshold is calculated for segmenting skin delamination areas from the fruit surface. The final quality grade is determined according to the fruit size and the percentage of delaminated skin. Experiment was performed in a packing facility in Arizona, USA. Testing results show the proposed method achieves 95–98% grading accuracy for different grades. Although this paper uses Medjool dates as an example to demonstrate the performance of the proposed method, it is suitable for and can be easily adapted to other fruit or vegetable grading applications. The proposed method has been implemented and used for commercial production for date quality evaluation.

Insight on AV-45 binding in white and grey matter from histogram analysis: a study on early Alzheimer's disease patients and healthy subjects.

AV-45 amyloid biomarker is known to show uptake in white matter in patients with Alzheimer's disease (AD), but also in the healthy population. This binding, thought to be of a non-specific lipophilic nature, has not yet been investigated. The aim of this study was to determine the differential pattern of AV-45 binding in white matter in healthy and pathological populations. We recruited 24 patients presenting with AD at an early stage and 17 matched, healthy subjects. We used an optimized positron emission tomography-magnetic resonance imaging (PET-MRI) registration method and an approach based on an intensity histogram using several indices. We compared the results of the intensity histogram analyses with a more canonical approach based on target-to-cerebellum Standard Uptake Value (SUVr) in white and grey matter using MANOVA and discriminant analyses. A cluster analysis on white and grey matter histograms was also performed. White matter histogram analysis revealed significant differences between AD and healthy subjects, which were not revealed by SUVr analysis. However, white matter histograms were not decisive to discriminate groups, and indices based on grey matter only showed better discriminative power than SUVr. The cluster analysis divided our sample into two clusters, showing different uptakes in grey, but also in white matter. These results demonstrate that AV-45 binding in white matter conveys subtle information not detectable using the SUVr approach. Although it is not more efficient than standard SUVr in discriminating AD patients from healthy subjects, this information could reveal white matter modifications.

A Novel Automatic Extraction Approach of Pollutants for Mobile Camera

Rapid and automatic extraction of pollutants is of great importance for mobile camera in real-world scenarios. In the moving process of robot, the camera is treated as dynamic background, and the pollutants on the camera are treated as static target. So as to realize the detection of static target in dynamic scene, this paper presents an automatic extraction algorithm for pollutants based on frame difference accumulation. Firstly, this algorithm can determine whether pollutants exist or not by the overall trend of gray histogram of the cumulative frame difference images. And then if existing pollutants, Otsu algorithm was adopted to adaptively calculate threshold to convert the gray image into binary image. In this paper, analysis of the important parameters of the algorithm - cumulative frame number and frame difference threshold was implemented. Moreover, feasibility of the algorithm was verified by experiments on the automatic extraction of pollutants for gun-type camera.

Fast intracoding unit size decision algorithm for high-efficiency video coding

In order to reduce the computational complexity for the high-efficiency video coding standard, an algorithm is proposed. First, we create a histogram based on the distribution of gray values in each coding tree unit. By using a self-correlation function of the gray histogram, we can skip some of the depth levels that are unnecessary. Second, the relationship between the sum of absolute transformed difference (SATD) and coding unit (CU) is used to decide an early termination for the split of the current CU, if the minimum SATD of this CU is smaller than a threshold. Experimental results show that the proposed algorithm can save an average of 38.39% of the encoding time with negligible degradation of coding efficiency compared with the reference model HM10.1.

ヒストグラム形状の復元に基づく画像濃度階調復元法

This paper proposes a restoration method in quantization for the image with the reduced gray scale value. Since the vision systems are likely to capture images with insufficient contrast or with the reduced number of gray levels, some theoretical countermeasure must be introduced. From this reason, OKQT (Oteru-Koshimizu's Quantization Theory) was introduced for providing the minimum quantization levels by which we can completely restore the full quantization levels of the histogram, or by which we can generate the super resolution in gray level. If no countermeasures are prepared, for example, the full potential of the display system cannot be utilized and furthermore the sufficient information in the gray value histogram cannot be provided for the sufficient performance of the image processing. This paper proposes an image restoration method in quantization guided by the histogram restoration. In this method, the histogram with sparse frequency is interpolates by using Sinc function, and we obtain the restored image by converting the gray scale values guided by the interpolated histogram.

An Algorithm of Image Quality Assessment Based on Data Fitting of Image Histogram

Based on research the connection between the gray image histogram and the gray image quality assessment,an algorithm of the gray image quality assessment based on data fitting of image histogram is proposed.The improved algorithm also applies to the color image.During the course of the color image quality assessment,the histogram is fitted respectively based on the color components and the color quantization.The difference weight data of the fitting coefficients about the image to be evaluted and the reference image is calculated. And the two element evaluation is given according to in the given threshhold range. The experiments show that the image quality assessment is good when the difference weight data of the fitting coefficients about the image to be evaluted and the reference image Less than or equal to 5×10 -5 .The two element evaluation is also effectively given according to the fitting data about color histogram of the color image based on the color components and the color quantization. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3021

Maximum Entropy Threshold Segmentation for Target Matching Using Speeded-Up Robust Features

This paper proposes a 2-dimensional (2D) maximum entropy threshold segmentation (2DMETS) based speeded-up robust features (SURF) approach for image target matching. First of all, based on the gray level of each pixel and the average gray level of its neighboring pixels, we construct a 2D gray histogram. Second, by the target and background segmentation, we localize the feature points at the interest points which have the local extremum of box filter responses. Third, from the 2D Haar wavelet responses, we generate the 64-dimensional (64D) feature point descriptor vectors. Finally, we perform the target matching according to the comparisons of the 64D feature point descriptor vectors. Experimental results show that our proposed approach can effectively enhance the target matching performance, as well as preserving the real-time capacity.

A semi-automated hybrid algorithm for accurate detection and counting of chemically etched tracks

In this paper, we present an accurate and comprehensive semi-automated algorithm for detection and counting the chemically etched tracks on polycarbonate nuclear Track detectors. The proposed algorithm consists of two main phases: a preprocessing phase for image preparation and quality improvement. It uses a format conversion into gray-scale image and contrast enhancement procedure. The contrast enhancement procedure employs the first-order fuzzy moment of the image and the Sugeno class of fuzzy complements to maximize the parametric indices of fuzziness of the image. In one feature extraction phase, two intrinsic characteristics of tracks are defined and formulated as topological feature (TF) and chromatic feature (CF). TF refers to tracks shape and geometry which are characterized and quantized by calculating the local Gray Level Spatial Correlation histogram of the tracks and CF refers to the color intensity difference of the tracks borders and tracks centric areas. The CF characterizes this difference specified to the tracks. After the feature extraction phase, the algorithm enters the detection and counting phase in which the fuzzy sets of background, noise (including small objects, notches, etc.) and track are constructed. Detected objects are then characterized according to their membership values to the fuzzy sets. The algorithm is designed in order to be applicable for different forms of tracks and track counting systems. Accuracy, linearity, sensitivity to the input parameters and comprehensibility of the method are validated in the simulation section.

Liquid metal angiography for mega contrast X-ray visualization of vascular network in reconstructing in-vitro organ anatomy.

Visualization on the anatomical vessel networks plays a vital role in the physiological or pathological investigations. However, so far it still remains a big challenge to identify the fine structures of the smallest capillary vessel networks via conventional imaging ways. Here, the room temperature liquid metal angiography was proposed for the first time to generate mega contrast X-ray images for multiscale vasculature mapping. Particularly, gallium was adopted as the room temperature liquid metal contrast agent and infused into the vessels of in vitro pig hearts and kidneys. We scanned the samples under X-ray and compared the angiograms with those obtained via conventional contrast agent--the iohexol. As quantitatively demonstrated by the grayscale histograms and numerical indexes, the contrast of the vessels to the surrounding tissues in the liquid metal angiograms is orders higher than that of the iohexol enhanced images. And the angiogram has reached detailed enough width of 0.1 mm for the tiny vessels, which indicated that the capillaries can be clearly distinguished under the liquid metal enhanced images. Further, with tomography from the micro-CT, we also managed to reconstruct the 3-D structures of the kidney vessels. Tremendous clarity and efficiency of the method over existing approaches have been experimentally clarified. It was disclosed that the usually invisible capillary networks now become distinctively clear in the gallium angiograms. This basic mechanism has generalized purpose and can be extended to a wide spectrum of 3-D computational tomographic areas. It opens a new soft tool for quickly reconstructing high-resolution spatial channel networks for scientific researches as well as engineering practices where complicated and time-consuming resections are no longer a necessity.

LED wafer edge detection based on improved Canny operator

An improved Canny operator was proposed to ensure the accuracy of the Light Emitting Diode( LED) wafer edge detection applied in the vision system of automatic LED die bonder. In the traditional Non-Maxima Suppression( NMS)process, inaccuracy would be caused by selecting two pixels near gradient direction as contrastive points. To solve this problem, bilinear interpolation based on the center pixel and three pixels around was made along gradient direction to implement new NMS process. In addition, the gray histogram of LED wafer was characterized by typical three peaks, and then the high threshold and the low threshold could be got by Otsu dual threshold method with new evaluation function to replace traditional artificial adjustment. The experimental results indicate that greater wafer outline and poles edges can be got by the improved Canny algorithm which is appropriate for LED wafer edge detection.

Interactive segmentation algorithm optimized by multi-threshold with application in medical images

Interactive image segmentation methods usually ask users to mark much more initial seeds or more than one interaction when they are used for medical image segmentation with fuzzy boundaries.This paper presented an optimized interactive image segmentation algorithm with multi-threshold technology.Based on GorwCut algorithm put forward by Vladimir,the optimized algorithm introduced image gray histogram with more than one threshold values to generate initial seeds template automatically and then used improved cellular automaton iterative algorithm to realize image segmentation.The algorithm simplified the user interactive operations and improved the segmentation accuracy.In applications,the algorithm was used to test on 100 plaque and liver image segmentations respectively,of which the results show that the optimized algorithm is of good performance.