Image Extraction Method Research Articles

Weld pool image acquisition and contour extraction based on arc spectrum and camera quantum efficiency

Based on the arc spectral radiation characteristics of ZL201A aluminum ally in CMT + P process and camera’s quantum efficiency, we select 520 nm band-stop as the working band for weld pool imaging acquisition systems and obtain high signal-to-noise ratio aluminum alloy weld pool images at the base level of weld current. Through analyzing the characteristics of captured aluminum alloy weld pool image, a semi-supervised and adaptive contour extraction method is designed, called Maximal Similarity based Region Merging and Adaptive Matting (MSRM-AM). Firstly, an interactive image segmentation method based on super-pixel is used to obtain the initial contour, and then the initial contour is finely segmented to get the final segmentation result. Comparing with other contour extraction algorithms, the proposed algorithm has higher accuracy and reliability, and has verified through abundant experiments.

Automatic monitoring system for individual dairy cows based on a deep learning framework that provides identification via body parts and estimation of body condition score

Body condition score (BCS) is a common tool for indirectly estimating the mobilization of energy reserves in the fat and muscle of cattle that meets the requirements of animal welfare and precision livestock farming for the effective monitoring of individual animals. However, previous studies on automatic BCS systems have used manual scoring for data collection, and traditional image extraction methods have limited model performance accuracy. In addition, the radio frequency identification device system commonly used in ranching has the disadvantages of misreadings and damage to bovine bodies. Therefore, the aim of this research was to develop and validate an automatic system for identifying individuals and assessing BCS using a deep learning framework. This work developed a linear regression model of BCS using ultrasound backfat thickness to determine BCS for training sets and tested a system based on convolutional neural networks with 3 channels, including depth, gray, and phase congruency, to analyze the back images of 686 cows. After we performed an analysis of image model performance, online verification was used to evaluate the accuracy and precision of the system. The results showed that the selected linear regression model had a high coefficient of determination value (0.976), and the correlation coefficient between manual BCS and ultrasonic BCS was 0.94. Although the overall accuracy of the BCS estimations was high (0.45, 0.77, and 0.98 within 0, 0.25, and 0.5 unit, respectively), the validation for actual BCS ranging from 3.25 to 3.5 was weak (the F1 scores were only 0.6 and 0.57, respectively, within the 0.25-unit range). Overall, individual identification and BCS assessment performed well in the online measurement, with accuracies of 0.937 and 0.409, respectively. A system for individual identification and BCS assessment was developed, and a convolutional neural network using depth, gray, and phase congruency channels to interpret image features exhibited advantages for monitoring thin cows.

Method for Detecting Chinese Texts in Natural Scenes Based on Improved Faster R-CNN

In this study, a natural scene text detection method based on the improved faster region-based convolutional neural network (R-CNN) is proposed. This method extracts image features with the Inception-ResNet architecture, adopts a region proposal network to generate region proposals for the extracted features, merges the fine-tuned features with the region proposals, and finally, uses Fast R-CNN to classify and locate text. The proposed method solves the problems of varying text sizes and the text being obscured in the image. Compared with the original Faster R-CNN, the multilevel Inception-ResNet network model presented in this study can extract deeper text features. The extracted feature map is further sparsely represented by Reduction B, Inception ResNet C and Avg Pool, and then is fused with text regions obtained by the text feature mapping lower layer network to acquire the exact text regions. The text detection method presented in this study is tested on the 2017 dataset of ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17), which contains a large number of distorted, blurry, different scale and size texts. An accuracy of 76.4% is achieved in this platform, thereby proving the efficiency of the proposed method.

A Novel Extraction Method for Wildlife Monitoring Images with Wireless Multimedia Sensor Networks (WMSNs)

In remote areas, wireless multimedia sensor networks (WMSNs) have limited energy, and the data processing of wildlife monitoring images always suffers from energy consumption limitations. Generally, only part of each wildlife image is valuable. Therefore, the above mentioned issue could be avoided by transmitting the target area. Inspired by this transport strategy, in this paper, we propose an image extraction method with a low computational complexity, which can be adapted to extract the target area (i.e., the animal) and its background area according to the characteristics of the image pixels. Specifically, we first reconstruct a color space model via a CIELUV (LUV) color space framework to extract the color parameters. Next, according to the importance of the Hermite polynomial, a Hermite filter is utilized to extract the texture features, which ensures the accuracy of the split extraction of wildlife images. Then, an adaptive mean-shift algorithm is introduced to cluster texture features and color space information, realizing the extraction of the foreground area in the monitoring image. To verify the performance of the algorithm, a demonstration of the extraction of field-captured wildlife images is presented. Further, we conduct a comparative experiment with N-cuts (N-cuts), the existing aggregating super-pixels (SAS) algorithm, and the histogram contrast saliency detection (HCS) algorithm. A comparison of the results shows that the proposed algorithm for monitoring image target area extraction increased the average pixel accuracy by 11.25%, 5.46%, and 10.39%, respectively; improved the relative limit measurement accuracy by 1.83%, 5.28%, and 12.05%, respectively; and increased the average mean intersection over the union by 7.09%, 14.96%, and 19.14%, respectively.

RETRACTED ARTICLE: Improved watershed histogram thresholding with probabilistic neural networks for lung cancer diagnosis for CBMIR systems

The past few decades have witnessed a steep increase in image data analysis for lung cancer, leading to huge repositories in the area of research in the medical sector. Content Based medical Image Retrieval (CBMIR) methods for lung cancer have been tried with the objective of facilitating access to image data. Many research works have been developed in content based medical image retrieval. But the techniques have the drawback of low efficiency and high computation cost. Image segmentation, extraction and classification methods of various kinds was taken upusing traditional methodswhich involves extraction of a specific region of interest and given to medical experts for diagnosis. The extracted region of interest region provides information useful for the for diagnosis of the disease. But the segmentation methods have some limitations such as flat valleys, noise sensitive and computational expensive which lead to reduction in the entire system performance. This is addressed by animproved watershed histogram thresholding using the probabilistic neural networks (IWHT-PNN) approach. The algorithm introduced outperforms the existing techniques improving the segmentation ratio and recognition accuracy of lung cancer which can be validated using experimental analysis.

Segmentation and Extraction for the Diamond Grain Image Based on the Gauss-polymerized Enhancement

To solve the problem of many background noises in image segmentation of diamond grains under the complicated texture background, an image segmentation and extraction method for diamond grains based on the Gauss-polymerized enhancement was proposed in this work. Firstly, the original diamond grain image was pre-processed by the method of histogram equalization in order to enhance the overall contrast effect of the image. Secondly, the image was further processed by the method of Gauss-polymerized enhancement through setting proper Gauss filter parameters, which purpose is to enhance the boundary definition between the grain and the matrix, and reduce the complex background noises. On this basis, the morphological dilation was used to eliminate the non-interested regions of the complex background noises, and obtain the segmentation region of the interested target grain. Finally, the diamond grain can be extracted from the grain image based on the segmented region of the target grain through the operation of image multiplication. The results show that the proposed method can effectively reduce the influence of the complex texture background on the segmentation and extraction of the target grain. The extracted image of the target grain can be further used to analyse the grain size characteristics and grain wear pattern identification in a higher level.

Iterative learning control for image feature extraction with multiple-image blends

In this paper, a novel method of image extraction is proposed. Firstly, the image information is embedded into the parameters of the chaotic system, and then the image is overlapped and embedded to complete the image hiding. This process is equivalent to a dynamic system with unknown time-varying parameters. Secondly, the D-type iterative learning control algorithm is used to extract the information hidden in the image, because iterative learning can be used to estimate the time-varying parameter system completely in the time interval. Finally, the numerical simulation shows that the algorithm can effectively extract the hidden information under various attacks.

Copy-move forgery detection based on compact color content descriptor and Delaunay triangle matching

Copy-move (region duplication) is one of the most common types of image forgeries, in which at least one part of an image is copied and pasted onto another area of the same image. The main aims of the copy-move forgery are to overemphasize a concept or conceal objects by duplicating some regions. Keypoint based copy-move forgery detection (CMFD) method extracts image feature points and employs local image features to identify duplicated regions, which exhibits remarkable detection performance with respect to memory requirement, computational cost, and robustness. However, they usually do not work well when the objects are hidden in smooth background areas. Also, the detection and localization accuracy always be lowered because of poor local image feature computation. In this paper, we present a novel approach for the detection and localization of copy-move forgeries, which is based on color invariance SIFER (Scale-invariant feature detector with error resilience) and FQRHFMs (Fast quaternion radial harmonic Fourier moments). Firstly, the original forgery image is segmented into nonoverlapping and nearly uniform superpixel blocks, and the stable keypoints are extracted adaptively from each superpixel block by incorporating the superpixel contents and color invariance SIFER. Secondly, a set of connected Delaunay triangles is constructed using the extracted image keypoints, and suitable local image feature for each Delaunay triangle is computed by using FQRHFMs and gradient entropy. Thirdly, the local image features and coherency sensitive hashing (CSH) are utilized to match quickly the Delaunay triangles. Finally, the falsely matched Delaunay triangles are removed by employing dense linear fitting (DLF), and the duplicated regions are localized using optimized zero mean normalized cross-correlation (ZNCC) measure. We conduct extensive experiments to evaluate the performance of the proposed copy-move forgery detection scheme, in which encouraging results validate the effectiveness of the proposed technique.

Extracting sub-exposure images from a single capture through Fourier-based optical modulation

Through pixel-wise optical coding of images during exposure time, it is possible to extract sub-exposure images from a single capture. Such a capability can be used for different purposes, including high-speed imaging, high-dynamic-range imaging and compressed sensing. In this paper, we demonstrate a sub-exposure image extraction method, where the exposure coding pattern is inspired from frequency division multiplexing idea of communication systems. The coding masks modulate sub-exposure images in such a way that they are placed in non-overlapping regions in Fourier domain. The sub-exposure image extraction process involves digital filtering of the captured signal with proper band-pass filters. The prototype imaging system incorporates a Liquid Crystal over Silicon (LCoS) based spatial light modulator synchronized with a camera for pixel-wise exposure coding.

Fusion of local and global features for effective image extraction

Image extraction methods rely on locating interest points and describing feature vectors for these key points. These interest points provide different levels of invariance to the descriptors. The image signature can be described well by the pixel regions that surround the interest points at the local and global levels. This contribution presents a feature descriptor that combines the benefits of local interest point detection with the feature extraction strengths of a fine-tuned sliding window in combination with texture pattern analysis. This process is accomplished with an improved Moravec method using the covariance matrix of the local directional derivatives. These directional derivatives are compared with a scoring factor to identify which features are corners, edges or noise. Located interest point candidates are fetched for the sliding window algorithm to extract robust features. These locally-pointed global features are combined with monotonic invariant uniform local binary patterns that are extracted a priory as part of the proposed method. Extensive experiments and comparisons are conducted on the benchmark ImageNet, Caltech-101, Caltech-256 and Corel-100 datasets and compared with sophisticated methods and state-of-the-art descriptors. The proposed method outperforms the other methods with most of the descriptors and many image categories.

Depth resolution enhanced spatial filtering in integral imaging based on convolution property between periodic functions with interpolation method

We propose a depth resolution improved target depth image extraction method in integral imaging by using the convolution property between periodic functions (CPPF) with image interpolation algorithm. We derive the depth resolution equation of a direct pickup system and analyze the factors related to the change of the depth resolution which are the focal length of an elemental lens and the resolution of an elemental image. We investigate the effect according to the change of these factors. The simulation results show that the key factor to change the depth resolution is the resolution of an elemental image. To show the feasibility of the proposed method, we carry out the preliminary experiments and present the results.

Computational hemodynamics of abdominal aortic aneurysms: Three-dimensional ultrasound versus computed tomography.

The current criterion for surgical intervention in abdominal aortic aneurysms, based upon a maximal aortic diameter, is considered conservative due to the high mortality rate in case of rupture. The research community is actively investigating the use of computational mechanics tools combined with patient-specific imaging to help identify more accurate criteria. Widespread uptake of a successful metric will however be limited by the need for computed tomography, which is at present the primary image extraction method on account of the location and complex shape of the aneurysms. The use of three-dimensional ultrasound as the scanning method is more attractive on account of increased availability, reduced cost and reduced risk to patients. The suitability of three-dimensional ultrasound is assessed for this purpose in the present work; computational fluid dynamics simulations were performed on geometries obtained from the same patient using both ultrasound and computed tomography. The influence of different smoothing algorithms is investigated in the geometry preparation stage and Taubin's low-pass filter was found to best preserve geometry features. Laminar, Newtonian, steady-state simulation analysis identified haemodynamic characteristics to be qualitatively similar in terms of wall shear stress, velocity and vorticity. The study demonstrates the potential for three-dimensional ultrasound to be integrated into a more accessible patient-specific modelling tool able to identify the need for surgical intervention of abdominal aortic aneurysms.

Optimum Image Extraction and Phase Analysis for ESPI Measurements Under Environmental Disturbance

We propose a new technique for electronic speckle pattern interferometry (ESPI) for measuring static deformation under environmental disturbances. In this technique, a number of laser speckle images of the initial and deformed states are captured, and images appropriate for making interference fringes are extracted using the optimum image extraction method. The phase of the interference fringe pattern is evaluated from the extracted images using a random phase-stepping method. In this study, translation amounts by random vibration are used as the phase stepping amounts. To validate the effectiveness of the proposed technique, an in-plane rotation of a flat plate and a strain distribution around a weld line of a compressor tank are measured. A compact speckle interferometer constructed on a tripod is used for the measurement. As a result, an interference fringe can be obtained, and the subsequent phase analysis can be performed under the proposed method without a vibration isolator. It is expected that ESPI measurements under environmental disturbance will be possible using the proposed technique.

차량검출 GMM 2.0을 적용한 도로 위의 차량 검출 시스템 구축

This paper presents a vehicle detection system using the video as a input image what has moving of vehicles.. Input image has constraints. it has to get fixed view and downward view obliquely from top of the road. Road detection is required to use only the road area in the input image. In introduction, we suggest the experiment result and the critical point of motion history image extraction method, SIFT(Scale_Invariant Feature Transform) algorithm and histogram analysis to detect vehicles. To solve these problem, we propose using applied Gaussian Mixture Model(GMM) that is the Vehicle Detection GMM(VDGMM). In addition, we optimize VDGMM to detect vehicles more and named VDGMM 2.0. In result of experiment, each precision, recall and F1 rate is 9%, 53%, 15% for GMM without road detection and 85%, 77%, 80% for VDGMM2.0 with road detection.

매트릭스 패턴 영상의 관심 영역 추출 방법 및 하드웨어 구현

This paper presents the region of interest pattern image extraction method on a display printed matrix pattern. Proposed method can not use conventional method such as laser, ultrasonic waves and touch sensor. It searches feature point and rotation angle using luminance and pattern reliable feature points of input image, and then it extracts region of interest. In order to extract region of interest, we simulate proposed method using pattern image written various angles on display panel. The proposed method makes progress using the OpenCV and the window program, and was designed using Verilog-HDL and was verified through the FPGA Board(xc6vlx760) of Xilinx.

基于贝叶斯分类的两类天气图像自动识别

为实现天气现象的自动观测，本文提出了一种基于贝叶斯分类的室外图像的天气现象识别方法，该方法通过提取图像的色相、饱和度和亮度等特征，采用贝叶斯分类，对雾霾和沙尘两类天气现象进行判断。实验结果的准确率达到预期目标，并且能快速、准确地测量室外图像的天气现象。 To realize the automatic observation of weather phenomena, a method for recognizing weather phenomena of outdoor image based on Bayesian classification is proposed. This method extracts image characteristics of hue, saturation and brightness, and adopts Bayesian classification to estimate the haze and sand-dust weather. The accuracy of experiment results reaches the expected aim, and the experimental results show that this method can quickly and accurately measure the weather phenomena of outdoor image.

형태학적 특징을 이용한 향상된 치아 검출 방법

In this paper, we propose improved methods which are image conversion and extraction method of watershed seed using morphological characteristic of teeth on complement image. Conventional tooth segmentation methods are occurred low detection ratio at molar region and over, overlap segmentation owing to specular reflection and morphological feature of molars. Therefore, in order to solve the problems of the conventional methods, we propose the image conversion method and improved extraction method of watershed seed. First, the image conversion method is performed using RGB, HSI space of tooth image for to extract boundary and seed of watershed efficiently. Second, watershed seed is reconstructed using morphological characteristic of teeth. Last, individual tooth segmentation is performed using proposed seed of watershed by watershed algorithm. Therefore, as a result of comparison with marker controlled watershed algorithm and the proposed method, we confirmed higher detection ratio and accuracy than marker controlled watershed algorithm.

Extraction and Segmentation of Books Call Number Image for Books on the Shelves of Library

It is a key technology that extract and segment book call number from books’ backbone images for book retrieval and return robot to take an operation of sending and withdrawing books to or from the shelves of library. This paper presents an image extraction and segmentation method using color feature and edge information to segment adjacent book call number with similar background. Take thick, thicker, medium thick, thin, little thin and hybrid books’ backbone images as experiment samples, and the results show that this method effectively extracts and segments adjacent book call number. The segmentation approach provides a technical support for book retrieval and return robot to carry out automatic books’ retrieval and return operation.

Research on Color Vegetable Diseases in Greenhouse Image Pretreatment and Extraction Method

In order to realize the accurate identification of the image color vegetable diseases in Greenhouse, In this paper, by using computer image processing technology in the intelligent recognition of vegetable diseases in greenhouse leaf, First, the moving average method can effectively remove the noise by the image of R,G, B three channel gray level, Then separate three channel image using Sobel-operator and the 4 template based on the direction of gradient magnitude ,and then integrate the three channel edge ,it can overcome the shortcoming of traditional gray image information, and make up the deficiency of the traditional Sobel operator edge thinning geometric features.

A Comparative Study of Contemporary Color Tongue Image Extraction Methods Based on HSI.

Tongue image with coating is of important clinical diagnostic meaning, but traditional tongue image extraction method is not competent for extraction of tongue image with thick coating. In this paper, a novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately. A comparative study of several contemporary tongue image extraction methods is also made from the aspects of accuracy and efficiency. As the experimental results show, geodesic active contour is quite slow and not accurate, the other 3 methods achieve fairly good segmentation results except in the case of the tongue with thick coating, our method achieves ideal segmentation results whatever types of tongue images are, and efficiency of our method is acceptable for the application of quantitative check of tongue image.