Ultrasound Speckle Reduction Based on Histogram Curve Matching and Region Growing

The quality of ultrasound scanning images is usually damaged by speckle noise.This paper proposes a method based on local statistics extracted from a histogram to reduce ultrasound speckle through a region growing algorithm.Unlike single statistical moment-based speckle reduction algorithms,this method adaptively smooths the speckle regions while preserving the margin and tissue structure to achieve high detectability.The criterion of a speckle region is defined by the similarity value obtained by matching the histogram of the current processing window and the reference window derived from the speckle region in advance.Then,according to the similarity value and tissue characteristics,the entire image is divided into several levels of speckle-content regions,and adaptive smoothing is performed based on these classification characteristics and the corresponding window size determined by the proposed region growing technique.Tests conducted from phantoms and in vivo images have shown very promising results after a quantitative and qualitative comparison with existing work.

Histogram Matched Chest X-Rays Based Tuberculosis Detection Using CNN

Tuberculosis(TB)is a severe infection that mostly affects the lungs and kills millions of people’s lives every year.Tuberculosis can be diagnosed using chest X-rays(CXR)and data-driven deep learning(DL)approaches.Because of its better automated feature extraction capability,convolutional neural net-works(CNNs)trained on natural images are particularly effective in image cate-gorization.A combination of 3001 normal and 3001 TB CXR images was gathered for this study from different accessible public datasets.Ten different deep CNNs(Resnet50,Resnet101,Resnet152,InceptionV3,VGG16,VGG19,DenseNet121,DenseNet169,DenseNet201,MobileNet)are trained and tested for identifying TB and normal cases.This study presents a deep CNN approach based on histogram matched CXR images that does not require object segmenta-tion of interest,and this coupled methodology of histogram matching with the CXRs improves the accuracy and detection performance of CNN models for TB detection.Furthermore,this research contains two separate experiments that used CXR images with and without histogram matching to classify TB and non-TB CXRs using deep CNNs.It was able to accurately detect TB from CXR images using pre-processing,data augmentation,and deep CNN models.Without histogram matching the best accuracy,sensitivity,specificity,precision and F1-score in the detection of TB using CXR images among ten models are 99.25%,99.48%,99.52%,99.48%and 99.22%respectively.With histogram matching the best accuracy,sensitivity,specificity,precision and F1-score are 99.58%,99.82%,99.67%,99.65%and 99.56%respectively.The proposed meth-odology,which has cutting-edge performance,will be useful in computer-assisted TB diagnosis and aids in minimizing irregularities in TB detection in developing countries.

Efficient Forgery Detection Approaches for Digital Color Images

This paper is concerned with a vital topic in image processing:color image forgery detection. The development of computing capabilitieshas led to a breakthrough in hacking and forgery attacks on signal, image,and data communicated over networks. Hence, there is an urgent need fordeveloping efficient image forgery detection algorithms. Two main types offorgery are considered in this paper: splicing and copy-move. Splicing isperformed by inserting a part of an image into another image. On the otherhand, copy-move forgery is performed by copying a part of the image intoanother position in the same image. The proposed approach for splicingdetection is based on the assumption that illumination between the originaland tampered images is different. To detect the difference between the originaland tampered images, the homomorphic transform separates the illuminationcomponent from the reflectance component. The illumination histogramderivative is used for detecting the difference in illumination, and henceforgery detection is accomplished. Prior to performing the forgery detectionprocess, some pre-processing techniques, including histogram equalization,histogram matching, high-pass filtering, homomorphic enhancement, andsingle image super-resolution, are introduced to reinforce the details andchanges between the original and embedded sections. The proposed approachfor copy-move forgery detection is performed with the Speeded Up RobustFeatures (SURF) algorithm, which extracts feature points and feature vectors. Searching for the copied partition is accomplished through matchingwith Euclidian distance and hierarchical clustering. In addition, some preprocessing methods are used with the SURF algorithm, such as histogramequalization and single-mage super-resolution. Simulation results proved thefeasibility and the robustness of the pre-processing step in homomorphicdetection and SURF detection algorithms for splicing and copy-move forgerydetection, respectively.

Enhanced Destriping of Satellite Data of Ice Surface in Antarctica

This paper briefly reviews the cause of the striping and then develops a tapered (Chebwin & Kaiser) window finite impulse response (FIR) filter and a constrained least squares FIR filter by reason of the striping of ASTER satellite data . Both filters minimize the stripes in the visible data and simultaneously minimize any distortion in the filtered data. Finally, the results obtained by using these new filtering methods are quantitatively compared with those produced by other destriping methods.

A stereo matching algorithm based on SIFT feature and homography matrix

Aiming at the low speed of traditional scale-invariant feature transform(SIFT) matching algorithm, an improved matching algorithm is proposed in this paper. Firstly, feature points are detected and the speed of feature points matching is improved by adding epipolar constraint; then according to the matching feature points, the homography matrix is obtained by the least square method; finally, according to the homography matrix, the points in the left image can be mapped into the right image, and if the distance between the mapping point and the matching point in the right image is smaller than the threshold value, the pair of matching points is retained, otherwise discarded. Experimental results show that with the improved matching algorithm, the matching time is reduced by 73.3% and the matching points are entirely correct. In addition, the improved method is robust to rotation and translation.