Image Processing Toolbox Research Articles

Image analysis for detection of bugholes on concrete surface

Surface bughole of concrete is one of surface imperfections of concrete appearance, and the detection and evaluation of surface bugholes have always been a difficult problem. This paper established a method to detect the surface bugholes of concrete by the image analysis, and put forward the evaluation parameters of the surface bugholes. The shooting distance can affect the shooting area and the detection accuracy of the image, the method of partition shooting must be used to ensure the detection accuracy according to the size of the concrete member. Based on the image processing toolbox of MATLAB, image gray, contrast enhancement and OTSU image threshold segmentation technology are used to extract the characteristics of bugholes on the concrete surface, and the threshold value of shape characteristic coefficient to distinguish the cracks and the surface bugholes is chosen as 45. The relationship between CIB scale and the area ratio of bughole is established. The parameters of area ratio and maximum diameter of bugholes can comprehensively evaluate the surface quality of concrete.

Magnetic resonance imaging of contaminated and damaged core cells in polymer composite sandwich panels

Computed tomography magnetic resonance imaging has been successfully applied to fully detect typical aircraft hydrogen-rich liquid contaminants entrapped in honeycomb core cells of structural polymer composite sandwich panels. With the aid of Bayesian-based image processing toolbox, the quantification, identification, and discrimination of the contaminants were also rapidly accomplished. Computed tomography magnetic resonance imaging has also been auspiciously applied to accurately define the extent of crushed-core damage in liquid impregnated honeycomb cells. Presented results strengthen the potential of magnetic resonance imaging as safe, fast, reliable, and user-friendly nondestructive testing technique to all engineering fields employing composite sandwich panels as high-demanding structural members.

Accurate Personal Identification Using Left and Right Palmprint Images Based on ANFIS Approach

The aim of present research work on palmprint recognition using discrete wavelet packet transform (DWPT) algorithm for feature extraction & ANFIS (Adaptive Neuro-Fuzzy Inference System) for palmprint matching. Biometrics based fingerprint, face, iris recognition has been investigated over many year. Palmprint recognition is an emerging technology in recent years due to the transaction frauds, security breaches and personal identification etc. compare to fingerprint, palmprint contain rich features like, principle line, wrinkles, ridges, and minute points, and it provides high standard security. This paper developing multibiometrics using left and right palmprint images and gives higher accuracy then single biometrics system. Registered IITD palmprint database is collected from IIT Delhi, biometric research library. It consist 2600 images from both left and right hand. This experiment perform palmprint recognition for enhance security using IITD database. MATLAB have been used as the programming tool to implement and investigate the performance of the segmentation and feature extraction method using image processing toolbox.

Detection of Lung Cancer Using Digital Image Processing Techniques: A Comparative Study

This paper focuses on early stage lung cancer detection. Lung cancer is prominent cancer as it states large number of deaths of more than a million every year. It creates need of detecting the lung nodule at early stage in Computer Tomography medical images. So to detect the occurrence of cancer nodule at early stage, the requirement of methods and techniques is increasing. There are different methods and techniques existing but none of them provide a better accuracy of detection. One of the techniques is content based image retrieval Computer Aided Diagnosis System (CAD) for early detection of lung nodules from the Chest Computer Tomography (CT) images. This optimization algorithm allows physicians to identify the nodules present in the CT lung images in the early stage hence the lung cancer. The MATLAB image processing toolbox based implementation is done on the CT lung images and the classifications of these images are carried out. The performance measures like the classification rate and the false positive rates are analyzed.

Detection of soybean aphids in a greenhouse using an image processing technique

Soybean aphid (Aphis glycines) is one of the most important insect pests of soybeans in North America. Insecticide application is performed if the aphids count exceeds the economic threshold of 250 per plant. Precise estimates of aphid densities are needed for field conditions to maximize insecticide application efficiency. The current method of identifying and counting aphids on a plant is a labor-intensive and time consuming process. The objective of this study was to use image processing technique to detect and count different sized soybean aphids on a soybean leaf. The trials were conducted with soybean plants grown in a greenhouse. Three sets of data were collected on different dates using replicate plants from 4 soybean varieties infested with a range of aphid densities. Images of infested soybean trifoliate leaves were captured with different cameras under 2 different illumination conditions with different cameras used across the different data sets. The images captured were processed in MATLAB™ R2014a software using the Image Processing Toolbox to identify and count aphids. In order to evaluate the accuracy of the algorithm, the aphids counted with the sensing system were compared to a count generated manually by a trained expert. The algorithm counting with SONY™ camera images correlated (r2=0.96) very well with manual counts. The misclassification percentage was low for most cameras with different resolutions under high illumination conditions. The results also showed that images captured with an inexpensive regular digital camera gave satisfactory results under high illumination conditions.

Biometric template protection based on Bloom filters and honey templates

Biometric verification can be considered one of the most reliable approaches to person authentication. However, biometrics are highly sensitive personal data and any information leakage poses severe security and privacy risks. Biometric templates should hence be protected and impersonation with stolen templates must be prevented, while preserving system's performance. In this study, a general biometric template protection scheme based on honey templates and Bloom filters is proposed, in order to grant privacy protection to the enrolled subject and detect the use of stolen templates. The performance and security evaluations show the soundness of the proposed scheme for facial verification. The benchmark is conducted with the publicly available BioSecure Multimodal DB and the free Bob image processing toolbox, so that research is fully reproducible.

Parts Surface Structure Image Classification Detection System Design

In order to accomplish the automatic nondestructive testing, a parts surface structure image classification detection system is designed. A series of parts surface texture images have been obtained from different processing methods for feature analysis and the combination of pre-processing method by MATLAB image processing toolbox has been put forward, using statistical analysis method for feature extraction. Based on the established BP neural network training optimization identification system, this paper realized the recognition of parts surface resulted from four kinds of processing methods: turning, milling, planing and grinding. The research results show that the deficit value of gray level co-occurrence matrix and the histogram matrix variance value can be regarded as characteristic parts of the surface texture structure value, providing foundations for further development of parts surface structure detection.

An artificial vision solution for reusing discarded parts resulted after a manufacturing process

The profit of a factory can be improved by reusing the discarded components produced. This paper is based on the case of a manufacturing process where rectangular metallic sheets of different sizes are produced. Using an artificial vision system, the shapes and the sizes of the produced parts can be determined. Those sheets which do not respect the requirements imposed are labeled as discarded. Instead of throwing these parts, a decision algorithm can analyze if another metallic sheet with smaller dimensions can be obtained from these. Two methods of decision are presented in this paper, considering the restriction that the sides of the new sheet has to be parallel with the axis of the coordinate system. The coordinates of each new part obtained from a discarded sheet are computed in order to be delivered to a milling machine. Details about implementing these algorithms (image processing and decision respectively) in the MATLAB environment using Image Processing Toolbox are given.

Development of Computed Tomography Scanner Application: Prototype Model Approach

The development of software application for image reconstruction system is essential in the research study of computed tomography (CT). An experimental prototype was the research tool used in developing a series of useful prototype to evaluate the reconstruction methods. A CT scanner software prototype was created using the MATLAB image processing toolbox together with the Graphical User Interface (GUI) and Graphical User Interface Development Environment (GUIDE). The prototype model was selected to guide the development of the prototype application and mainly to provide a platform to update a system from the available knowledge. The prototype model was capable in creating a CT scanner synthetic datasets, display a sinogram image from the synthetic datasets, construct images using back projection technique and displaying cross-section images. Two types of images were acquired from this research, the first type was the unfiltered and blurred image and the second type was the filtered and clear image. This research also focused on two-dimensional parallel-beam and fan-beam geometry configuration; the principle of transforming fan-beam datasets into parallel-beam datasets was carried out using the classical rebinning concept.

As-Applied Estimation of Volumetric Flow Rate from a Single Sprayer Nozzle Series Using Water-Sensitive Spray Cards

<abstract> The objective of this study was to test the feasibility of using coverage measurements from water-sensitive spray cards to estimate the volumetric flow rate at an individual sprayer nozzle. TeeJet VisiFlow Even Flat Spray Tips were selected due to their uniform distribution of coverage. Spray distribution for each nozzle was validated using a spray patternator table with 2.5 cm sampling widths. A rotary test fixture translated water-sensitive spray cards through the spray dispersion (water at ambient conditions) at a constant angular velocity and a radius of 1.2 m. The test fixture measured volumetric flow and pressure at the nozzle and recorded data at a rate of 10 Hz. A helical gear pump and a piston-type pressure regulating valve were used to provide constant pressure. The first experiment fixed the test fixture speed at 3.14 rad s-1 and used varying pressures from 70 to 552 kPa (10 to 80 psi) in 70 kPa (10 psi) increments. First-order and second-order regression models were developed for the nozzle series, and validation data were collected at intermediate pressures to test the ability of the model to predict volumetric flow rates. The second experiment fixed the system pressure at 310 kPa (45 psi) and varied the speed of the test fixture at seven increments between 2.0 and 3.8 rad s-1. Spray cards were digitized using a scanner and processed for coverage using the MATLAB image processing toolbox. Results showed that the accuracy of the spray card method was within 1% full-scale of a commercial impeller flowmeter for a single series of nozzles moving at constant speed. Varying speed could be accounted for but required knowledge of the individual nozzle model.

A quantitative method for assessing the quality of meibomian glands

IntroductionMeibomian gland dysfunction is a common cause of dry eye syndrome which can also lead to eyelid inflammation. Today, diagnostics of meibomian glands is not fully automatic yet and is based on a qualitative assessment made by an ophthalmologist. Therefore, this article proposes a new automatic analysis method which provides a quantitative assessment of meibomian gland dysfunction. MethodThe new algorithm involves a sequence of operations: image acquisition (acquisition of data from OCULUS Keratograph® 5M); image pre-processing (image conversion to gray levels, median filtering, removal of uneven lighting, normalization); main image processing (binarization, morphological opening, labeling, Gaussian filtering, skeletonization, distance transform, watersheds). The algorithm was implemented in Matlab with Image Processing Toolbox (Matlab: Version 7.11.0.584, R2010b) on a PC running Windows 7 Professional, 64-bit with the Intel Core i7-4960X CPU @ 3.60GHz. Results and conclusionsThe algorithm described in this article has the following features: it is fully automatic, provides fully reproducible results – sensitivity of 99.3% and specificity of 97.5% in the diagnosis of meibomian glands, and is insensitive to parameter changes. The time of image analysis for a single subject does not exceed 0.5s. Currently, the presented algorithm is tested in the Railway Hospital in Katowice, Poland.

TH‐CD‐206‐01: Expectation‐Maximization Algorithm‐Based Tissue Mixture Quantification for Perfusion MRI

Purpose:To investigate the feasibility of estimating the tissue mixture perfusions and quantifying cerebral blood flow change in arterial spin labeled (ASL) perfusion MR images.Methods:The proposed perfusion MR image analysis framework consists of 5 steps: (1) Inhomogeneity correction was performed on the T1‐ and T2‐weighted images, which are available for each studied perfusion MR dataset. (2) We used the publicly available FSL toolbox to strip off the non‐brain structures from the T1‐ and T2‐weighted MR images. (3) We applied a multi‐spectral tissue‐mixture segmentation algorithm on both T1‐ and T2‐structural MR images to roughly estimate the fraction of each tissue type ‐ white matter, grey matter and cerebral spinal fluid inside each image voxel. (4) The distributions of the three tissue types or tissue mixture across the structural image array are down‐sampled and mapped onto the ASL voxel array via a co‐registration operation. (5) The presented 4‐dimensional expectation‐maximization (4D‐EM) algorithm takes the down‐sampled three tissue type distributions on perfusion image data to generate the perfusion mean, variance and percentage images for each tissue type of interest.Results:Experimental results on three volunteer datasets demonstrated that the multi‐spectral tissue‐mixture segmentation algorithm was effective to initialize tissue mixtures from T1‐ and T2‐weighted MR images. Compared with the conventional ASL image processing toolbox, the proposed 4D‐EM algorithm not only generated comparable perfusion mean images, but also produced perfusion variance and percentage images, which the ASL toolbox cannot obtain. It is observed that the perfusion contribution percentages may not be the same as the corresponding tissue mixture volume fractions estimated in the structural images.Conclusion:A specific application to brain ASL images showed that the presented perfusion image analysis method is promising for detecting subtle changes in tissue perfusions, which is valuable for the early diagnosis of certain brain diseases, e.g. multiple sclerosis.

Designing and Performance Evaluation of an Advanced Method for Corner Detection using Harris Technique

Corner detection is a significant task in different machine vision and image processing systems because corners play an important role in describing object unique features for recognition and identification. Corner detection comes within reach of computer visualization systems to extract certain kinds of characteristics and understand the contents of an image. In this work modify the Harris technique in order to enhance the performance of corner detection. To include the effect of Morphology technique on the modified Harris corner technique. Observe the simulation results of proposed detection technique & compare results with traditional method. MATLAB R2013a has been used as an implementation platform using generalized MATLAB toolbox and image processing tool box.

Numerical analysis of corneal curvature dynamics based on Corvis tonometer images.

The paper presents numerical analysis of corneal curvature distribution, based on Corvis ST images. It was shown that a new approach to analysis of corneal curvature from tonometer images enables a better description and understanding of processes during fast corneal deformation. Ten healthy volunteers participated in nine repeated measurements on one eye. 90 sequences of images were processed with software written in Matlab, with the use of the Image Processing Toolbox. Time-spatial distribution of the local curvature distribution of the corneal profile was obtained for each and every measurement. Some new curvature parameters were proposed and analyzed. A high repeatability for individual subjects was obtained for the proposed parameters. For four of these new parameters, the ICC coefficients were higher than 0.85. The ICC value for the calculated curvature of the cornea before deformation reaches 0.989. Such high repeatability of the proposed new parameters can be useful in examination and differentiation of corneas due to their geometrical and biomechanical properties.

A camera and image processing system for floc size distributions of suspended particles

The observation of floc size distribution (FSD) for quantitative description of its properties over a sufficient size range, from a few microns to a few millimeters, is still a challenge in most marine environments. In this study, an inexpensive image acquisition and processing system is developed for achieving this objective. Images are acquired by using a Sony Alpha NEX-5R camera body with a CMOS sensor, a Sony E-mount to Nikon F-mount adaptor, extension tubes, a Nikon macro lens, and a close-up lens that can identify flocs with a minimum size of 5μm. The light source and camera trigger are controlled by a micro-controller that was assembled for this project. These images are analyzed by using MATLAB Image Processing Toolbox. The processed floc size and their statistical distributions are confirmed with two available sample sets. The validated process is then applied to measure the steady state FSDs of kaolinite suspensions for different shear rates, suspended sediment concentrations, salinities, and a selected organic matter, guar gum. Although the presence of salt promotes flocculation of suspended kaolinite, only a small amount of salt, around 0.5ppt, is needed to reach the saturation status. Thus for the test salinities (0.5, 1, 2, 3, 5, and 9ppt), the measured FSDs show little difference among each other. On the other hand, guar gum affects kaolinite flocculation significantly and the maximum effect happens at a guar gum concentration around 15mg/L when the kaolinite concentration is around 0.52g/L. At this dosage the characteristic floc size is the largest.

A novel method for detection and extraction of human face for video surveillance applications

This paper deals with the algorithm for extracting human skin region through skin detection and skin segmentation from a video. At first, the change of shot is detected and then extraction of image (if any) is done from detected shots. Once the image is detected, it gets converted into an HSV image and then skin segmentation is done. Conversion of an image into an HSV helps to work in single variable (i.e. variable being the only hue value). This algorithm will automatically provide change of shots, skin detection, skin segmentation and then extraction of the face. This entire algorithm is done under the Image Processing Toolbox (IPT) of MATLAB. Moreover, Fuzzy Logic is also used in this paper for thresholding the hue values for skin segmentation and skin detection. This paper provides a detailed idea of extracting the human face from a video automatically.

Designing an Efficient Image Encryption-Compression System using a New HAAR, SYMLET and COIFLET Wavelet Transform

In the modern world, hidden information plays a decisive role in protecting the data and reducing the space in the memory as well as on disk drives. If encryption and compression works properly than it leads to high speed computation. Encryption of an image can be done in many ways and several techniques use different methods for encryption. Image encryption scheme operated in the prediction error domains which are able to provide a high level of security reasonably, after that we can efficiently compress the encrypted images. In this paper the full image is encrypted in an efficient and secure manner with Data Encryption Algorithm along with a new modified International Haar, SYMLET and COIFLET Wavelet. After achieving encryption on the original file, compression will be performed to obtain a compressed image. The approach based on Arithmetic coding is also demonstrated which can be utilized efficiently to compress the encrypted images. The existing encryption-then-compression (ETC) solutions encourage significant forfeiture on the compression efficiency. For better compression efficiency we are using HAAR and COIFLET wavelet transform along with ETC, for the implementation of this proposed work, the Image Processing Toolbox under MATLAB software is used. Keywordscompression, ETC, Haar wavelet, wavelet and

Face Recognition using PCA and SVM with Surf Technique

Face Recognition is a biometric application which can be controlled through hybrid systems instead of a solitary procedure. This paper focus at Principal Component Analysis system alongside SVM and SURF for Face Recognition. Preprocessing abrogates improper, superflous and unnecessary information. PCA naturally decreases dimensionality and Feature extraction to minimize highlights. Furthermore, after element extraction, the recognition is performed on these elements to perceive the person. SVM classifier is a classifier which is utilized as a part of this paper for performing the recognition capacity and SURF is utilized for matching the source image with the database. This outcomes in an adequate error rate and accuracy furthermore this gives better MSE and PSNR results. In this paper, a novel facial methodology is used to hunt the element space down the ideal component subset where elements are extricated by PCA , while matching and recognition is done utilizing SVM classifier and SURF Technique. For the usage of this proposed work we utilize Image Processing Toolbox under the MATLAB programming.

Shape Recognition and Measurement of Position and Orientation of Different Parts Produced within a Manufacturing Process

In a manufacturing process it may be necessary to distinguish the parts of various types produced by different machine-tools and placed on a conveyor. Using an artificial vision system represents a possible solution. Images of the parts can be periodically taken using a video camera. It is considered that all parts are positioned with one of the faces which defines its type on the upper side. Thus, parts’ recognition can be solved by recognizing the shapes from the images. In addition, information about position and orientation of parts can be determined using the captured images. All these information are listed in a text file which can be used by a decision algorithm. This algorithm can choose which parts are useful to assemble different objects. An industrial robot can be commanded using a program written in RobotStudio environment’s programming language (RAPID) to pick the needed parts and place them in a storage area.This paper describes a recognition and measurement of position and orientation method of the different parts produced. In addition, details about implementing this method in MATLAB environment using Image Processing Toolbox and geometrical relations are provided gradually.

A blind digital image watermarking method based on the dyadic wavelet packet transform and fast interval arithmetic techniques

We propose a new digital image watermarking method based on the dyadic wavelet packet transform (DYWPT) and fast interval arithmetic (IA) techniques. Because the DYWPT has a redundant representation, like the dyadic wavelet transform (DYWT), the amount of information that the watermark must contain is greater than in the case of methods based on ordinary discrete wavelet transforms (DWTs) and the discrete wavelet packet transform (DWPT). However, the order of the high frequency components is not necessarily the same as the order of their frequency domain. Therefore, in our approach, we rearrange the order of the high frequency components in descending order of frequency components and embed a watermark selectively into higher frequency components. Our watermark is a ternary-valued logo that is embedded into higher frequency components through use of the DYWPT and fast IA techniques. We describe our watermarking procedure in detail and present experimental results demonstrating that our method produces watermarked images that have better quality and are robust with respect to various types of attacks, including marking, clipping, median filtering, contrast tuning (histeq and imadjust commands in the MATLAB Image Processing Toolbox), addition of Gaussian white noise, addition of salt &amp; pepper noise, JPEG and JPEG 2000 compressions, rotation, and resizing.