Showing papers in "Journal of Image and Graphics in 2013"
TL;DR: A new method supporting hand gesture recognition in the static form, using artificial neural network is proposed, which has been tested with high accuracy (98%) and is promising.
Abstract: Computers are widely used in all fields. However, the interaction between human and machine is done mainly through the traditional input devices like mouse, keyboard etc. To satisfy the requirements of users, computers need other ways to interact more conveniently, such as using speech or body language (e.g. gestures, posture). In this paper, we propose a new method supporting hand gesture recognition in the static form, using artificial neural network. The proposed solution has been tested with high accuracy (98%) and is promising.
46 citations
TL;DR: The main purpose for speckle reduction is to improve the visualization of the image and it is the preprocessing step for segmentation, feature extraction and registration in ultrasound medical imaging.
Abstract: Digital image acquisition and processing techniques plays important role in clinical diagnosis. Medical images are generally corrupted by noise during their acquisition and transmission. Removing noise from the original medical image is still a challenging problem for researchers. Ultrasound imaging is widely used for diagnosis over the other imaging modalities like Positron Emission Tomography (PET), Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) due to its noninvasive nature, portable, accurate, harmless to the human beings and capability of forming real time imaging. The presence of signal dependant noise known as speckle degrades the usefulness of ultrasound imaging. The main purpose for speckle reduction is to improve the visualization of the image and it is the preprocessing step for segmentation, feature extraction and registration. Over a period, a number of methods have been proposed for speckle reduction in ultrasound imaging. While using techniques for speckle reduction as an aid for visualization, certain speckle contains diagnostic information and should be retained. The scope of this paper is to give an overview about despeckling techniques in ultrasound medical imaging.
42 citations
TL;DR: A quality measure which is calculated in spatial domain to determine the quality of blurred images is proposed and is very important for modern image processing applications.
Abstract: Determination of quality of an image is a very challenging task and is very important for modern image processing applications. One of the most common distortions in images is blurring. For a human visual system excessive blurring in an image is not visually pleasing and creates difficulty in identifying objects. In this paper we propose a quality measure which is calculated in spatial domain to determine the quality of blurred images.
22 citations
TL;DR: LQR based fuzzy controller is designed and its performance is compared with Linear Quadratic Regulator controller using Matlab and Simulink and shows that LQRbased fuzzy controller produced better response as compared to L QR control strategy.
Abstract: Abstract—The objective of this paper is to compare performance between two type of controller for a double inverted pendulum system. Double inverted pendulum is a non-linear, unstable and fast reaction system. DIP is stable when its two pendulums allocated in vertically position and have no oscillation and movement and also inserting force should be zero. The objective is to determine the control strategy that to delivers better performance with respect to pendulum angle’s and cart position. In this paper LQR based fuzzy controller is designed and its performance is compared with Linear Quadratic Regulator controller using Matlab and Simulink. The results shows that LQR based fuzzy controller produced better response as compared to LQR control strategy.
21 citations
TL;DR: In this paper, the authors examined the role of publish media in influencing women in wearing Hijab, and found that media is fully utilizing their tools in influence women wearing hijab regardless of their real intention.
Abstract: The purpose of this study is to examine the roles of publish media in influencing women in wearing Hijab. With the publications as well as media involvement in dissemination on Hijab styles somehow propagate women in wearing Hijab. In analysis of the roles of media in influencing women in wearing Hijab, the purpose and their awareness on fashion in Hijab have been questioned. In order to determine whether media is commercializing in Hijab modernization to influences women in wearing Hijab, a quantitative analysis have been conducted over 80 women to prove such suggestion. Findings were tabulated and the results proved that media is fully utilizing their tools in influence women wearing Hijab regardless of their real intention. Media commercializing Hijab fashion to move forward in fashion line. Muslim women are still hold onto the Islamic regulations in styling up fashion. As in the modern era today, technology helps in disseminating information or updates on modern Hijab fashion towards modern Muslim women. Modification in Hijab fashion can be accepted in this era as one of fashion styles. However, the importance or the real perspectives of Hijab should be strengthen up in order for no mislead of Islam's missionary.
21 citations
TL;DR: A segmentation technique is presented which joins a multi-scale texture based approach and a fuzzy segmentation method using the color gradient of Di Zenzo, which leads to segmentation using a step of watershed flooding, with few parameters to set.
Abstract: In this paper, we present a segmentation technique which joins a multi-scale texture based approach and a fuzzy segmentation method using the color gradient of Di Zenzo. Thus maps of homogeneous texture patterns are enhanced by edge localization. A topographic distance is used to calculate membership degrees to each region. Both lead to segmentation using a step of watershed flooding, with few parameters to set. Moreover computation complexity has been reduced to allow treatments of images in full size and colors.
21 citations
TL;DR: An intelligent traffic light that controls the flow of traffic was introduced that makes a real time decision that determines the interval of green light time for each traffic light at each intersection.
Abstract: Abstract—In this paper, an intelligent traffic light that controls the flow of traffic was introduced. The proposed system detects the level of congestion and the abnormal situations in two main highways and four intersections. The system collects the data and the information from a video imaging system, which captures and interprets images to detect, and count of the vehicles. This data will be sent to another system based on genetic algorithm. This system makes a real time decision that determines the interval of green light time for each traffic light at each intersection. This system is simulated theoretically and the results indicate the efficiency of the system. We suggest other inputs from VANET techniques and Mobile track system, which can be added to the system, to improve its output. Index Terms—Intelligent traffic light, genetic algorithm, VANET, and video image detection system.
20 citations
TL;DR: This cryptosystem also utilize a new mapping method is introduced to convert every pixel of plain image into a point on an elliptic curve, which is a mandatory prerequisite for any ECC based encryption.
Abstract: In this paper an encryption technique is proposed based on elliptic curves for securing images to transmit over public channels. This cryptosystem also utilize a new mapping method is introduced to convert every pixel of plain image into a point on an elliptic curve, which is a mandatory prerequisite for any ECC based encryption. Encryption and decryption process are given in details with implementation. After applying encryption, security analysis is performed to evaluate the robustness of proposed technique to statistical attacks.
19 citations
TL;DR: Preliminary experimental results show that the proposed region based image retrieval system provides better retrieving result than retrieval using some of the existing methods.
Abstract: This paper proposes a region based image retrieval system using the local colour and texture features of image sub regions. The regions of interest (ROI) are roughly identified by segmenting the image into fixed partitions, finding the edge map and applying morphological dilation. The colour and texture features of the ROIs are computed from the histograms of the quantized HSV colour space and Gray Level co- occurrence matrix (GLCM) respectively. Each ROI of the query image is compared with same number of ROIs of the target image that are arranged in the descending order of white pixel density in the regions, using Euclidean distance measure for similarity computation. Preliminary experimental results show that the proposed method provides better retrieving result than retrieval using some of the existing methods.
18 citations
TL;DR: In this article, a universal approximation characteristic of feedforward neural is taken to achieve both of these requirements in a simple but very efficient way, which facilitates the solution as universal solution for different types of noise removal compare to conventional solutions which are based on noise characteristics.
Abstract: In image processing based applications there are very important requirements of noise removal and edge detection. In this paper universal approximation characteristic of feedforward neural is taken to achieve both of these requirements in a simple but very efficient way. Concept of local pattern generated by small region pixels which define the possibility of relation among pixels is presented. This approach facilitates the solution as universal solution for different types of noise removal compare to conventional solutions which are based on noise characteristics. Same model of neural network with little extension can also be utilized as edge detector has also presented. Another benefit of proposed model is contrast enhancement without any extra computation cost. In effect this solution can be considered as universal solution for noise reduction, edge detection and contrast enhancement. Comparison has made with well established solution like median filter and adaptive Wiener filter for noise reduction where as Canny and Prewitt detectors have taken for edge detection comparison.
11 citations
TL;DR: This paper has used the platform-based design approach to design a configurable real-time image and video streaming module for vision-based systems on an Virtex-5 FPGA and implemented a real- time image andVideo acquisition module for a smart camera system.
Abstract: Implementation of an efficient, complex real-time image and video processing system has many different contrary design needs. These systems require managing and processing a large amount of data in a timely manner. The robust implementation requires design reuse and flexibility, which is very crucial for an ever-increasing application need. A combination of hardware and software which form a platform fulfills the demands of the continuously developing application domain. The platform-based design has recently gained in importance which allows to explore the trade-offs between various designs requirements for the hardware and software implementation of real-time image and video processing algorithms and its systems. In this paper, we present the exploration of platform-based design approach for implementing a real-time vision system. We have used the platform-based design approach to design a configurable real-time image and video streaming module for vision-based systems on an Virtex-5 FPGA. We have also implemented a real-time image and video acquisition module for a smart camera system.
TL;DR: A new ground plane segmentation method is proposed for obstacle detection to improve the mobility of the visually impaired people by means of a novel electronic cane "Smartcane" which gives better obstacle detection than available color based obstacle detection approaches.
Abstract: In this paper, a new ground plane segmentation method is proposed for obstacle detection to improve the mobility of the visually impaired people by means of a novel electronic cane "Smartcane". Monocular camera was used which has the merits to get simple computation and cheap hardware and it's promising to realize real time navigation. The proposed method is based on an appearance-based approach by combining both color and texture information extracted from monocular image. The algorithm is tested with a challenging indoor image set. It gives better obstacle detection than available color based obstacle detection approaches.
TL;DR: Simulation experiments show that SIRT can reconstruct a HR image with superior quality compared to conventional super-resolution reconstruction methods.
Abstract: In this paper, an iterative super-resolution reconstruction method is introduced for license plate recognition. A high-resolution image of the license plate is reconstructed by fusing the information derived from a set of subpixel shifted low-resolution images. The reconstruction problem is formulated as a system of linear equations that is solved by using the simultaneous algebraic reconstruction technique (SIRT). Simulation experiments show that SIRT can reconstruct a HR image with superior quality compared to conventional super-resolution reconstruction methods.
TL;DR: A novel multiple camera tracking helmet system is presented, which stitch views from multiple cameras mounted on the helmet to one wide view in which to tracking objects, this simplifies the task of object tracking from several cameras.
Abstract: Object tracking in multiple cameras has been largely studied in the literature. However there are still unsolved problems, such as camera handoff, objects association, etc. In this paper we presents a novel multiple camera tracking helmet system, we stitch views from multiple cameras mounted on the helmet to one wide view in which we tracking objects, this simplifies the task of object tracking from multiple cameras. And combining with online training tracking algorithm, our tracking system demonstrates real-time and robust tracking performance.
TL;DR: A novel fingerprint orientation map estimation based on Wave atoms transform is proposed and the results show that this method has a serious potential in fingerprint orientation evaluation.
Abstract: Most systems of fingerprint identification and/or authentication need a ridge direction map, commonly called the orientation map. In addition, the estimation of orientation field plays an important role in the fingerprint enhancement. In this paper, A novel fingerprint orientation map estimation based on Wave atoms transform is proposed. This paper aims to open a new gateway by proposing a different approach for analyzing fingerprints and try to unify steps of automatic fingerprint identification system( AFIS): classification, compression, quality measure, local orientation and identification. Wave atoms is one of the new geometric multiscale-multidirectional transform, which is more appropriate to represent fingerprint structures. In order to evaluate the performance of the algorithm, FVC2004 database has been considered. The results show that this method has a serious potential in fingerprint orientation evaluation.
TL;DR: A contour matching method using the similarity of the sub contour centroid value is introduced which is fast enough equivalence to the requirement of reconstruction technique which has to be time and space effective.
Abstract: A bstract—Reconstruction of real object often involves branching contour cases. An effective technique is required to determine the correct corresponding sub contour between two connected contours. This is to ensure the accuracy of the resulted image. This study has introduced a contour matching method using the similarity of the sub contour centroid value. The technique is fast enough equivalence to the requirement of reconstruction technique which has to be time and space effective. The matched sub contours then are connected by introducing an intermediate contour called as composite contour. The technique has been applied in the reconstruction of human head and Stanford bunny from CT images. Beta-spline was employed as the fitted surface as this surface has capability to give smoothed and accurate result.
TL;DR: An improved algorithm to track 3D straight edges, facilitated by the use of Kinect to provide RGB color image as well as the depth map through IR sensor on it is provided.
Abstract: The paper describes our contribution in the field of visual localization as a desirable feature of an autonomous mobile robot in an unknown environment. Reviewing current approaches, our paper provides an improved algorithm to track 3D straight edges, facilitated by the use of Kinect (a camera developed by Microsoft corporation) to provide RGB color image as well as the depth map through IR sensor on it. Correspondence between edges in two consecutive frames is established through edge templates. Following this is the determination of rotation and translation of edges from one frame to the matched corresponding edge in other frames using a set of edge descriptors (six parameters of a straight edge in 3D) to update subsequent camera positions. Finally, we compare the result with measurements made from an independent source, the Personal Space Tracker (PST-110) manufactured by Personal Space Technologies.
TL;DR: In computer stereo vision, the fundamental matrix is the algebraic representation of the epipolar geometry that relates two images of a scene observed from two different viewpoints as mentioned in this paper, and the most important feature of the fundamental matrices is its independence of the scene structure.
Abstract: In computer stereo vision, the fundamental matrix is the algebraic representation of the epipolar geometry that relates two images of a scene observed from two different viewpoints. The most important feature of the fundamental matrix is its independence of the scene structure. Different methods have been proposed to derive the fundamental matrix equation. This paper reviews one of these methods and reveals that it is based on flawed statements to conclude the existence of a homography between the points on the two images. This derivation of the fundamental matrix equation is based on the existence of a homography between the two images.
TL;DR: Experimental results show the importance of jointly managing both problems for gaitbased gender classification, and it seems that the best strategy consists of applying resampling followed by feature selection.
Abstract: Abstract—Two intrinsic data characteristics that arise in many domains are the class imbalance and the high dimensionality, which pose new challenges that should be addressed. When using gait for gender classification, benchmarking public databases and renowned gait representations lead to these two problems, but they have not been jointly studied in depth. This paper is a preliminary study that pursues to investigate the benefits of using several techniques to tackle the aforementioned problems either singly or in combination, and also to evaluate the order of application that leads to the best classification performance. Experimental results show the importance of jointly managing both problems for gaitbased gender classification. In particular, it seems that the best strategy consists of applying resampling followed by feature selection.
TL;DR: The presented method is capable of estimating the visual motion parameters in a complicated 6 degrees of freedom motion and in real time with suitable accuracy for mobile robots visual navigation.
Abstract: Visual motion cues play an important role in animal and humans locomotion without the need to extract actual ego-motion information. This paper demonstrates a method for estimating the visual motion parameters, namely the Time-To-Contact (TTC), Focus of Expansion (FOE), and image angular velocities, from a sparse optical flow estimation registered from a downward looking camera. The presented method is capable of estimating the visual motion parameters in a complicated 6 degrees of freedom motion and in real time with suitable accuracy for mobile robots visual navigation.
TL;DR: A blur kernel estimation method based on the new concept of the Multiplicative Multiresolution Decomposition (MMD) that quantifies the blur effect in the MMD's domain by analyzing edges spreading through a multiresolution analysis.
Abstract: The aim of this article is to propose a blur kernel estimation method based on the new concept of the Multiplicative Multiresolution Decomposition (MMD). This method quantifies the blur effect in the MMD’s domain by analyzing edges spreading through a multiresolution analysis. The histogram of edges spreading over the entire image is used as information about the blur amount in the image. Tests on blurred images from the LIVE database show that, the proposed approach provides an accurate blur kernel estimation.
TL;DR: A image compression algorithm: PCA for image compression based on improved JohnsonLindenstrauss Lemma is proposed, which has its significant advantages: good performance in removing of correlations, and high compression ratio.
Abstract: Principal Components Analysis (PCA) is one of the most frequently used dimensionality reduction methods. PCA is suitable in time-critical case (i.e., when distance calculations involving only a few dimensions can be afforded) [1] . When it comes to image compression, PCA has its significant advantages: good performance in removing of correlations, and high compression ratio. JohnsonLindenstrauss Lemma is a probability method leading to a deterministic statement of dimensionality reduction. This paper proposes a image compression algorithm: PCA for image compression based on improved JohnsonLindenstrauss Lemma.
TL;DR: In this paper, the evolution of the coastal landscape of Kuwait has been studied from remotely sensed images, historical pictures, aerial video survey and various visuals, and the important tool used for the study was Remote Sensing Techniques, Geographical Information System, Interpretation of Images, Analytical Hierarchical Procedure, Rapid Impact Assessment Matrix, and Carrying Capacity Model.
Abstract: The development, life style and supportive system have exploited the coast more rather than the interior offshore land of Kuwait, thereby altering the morphological landscape through built up structures, population migration, coastline change, habitat change and land use apart from natural process. As a result Kuwait’s coastal landscape has been subjected to tremendous evolution which was studied from remotely sensed images, historical pictures, aerial video survey and various visuals. Each of the section documents the research result in itself that was accomplished with specific purpose that takes the entire studies to the ultimate goal of exploring the trend in coastal evolution. The important tool used for the study was Remote Sensing Techniques, Geographical Information System, Interpretation of Images, Analytical Hierarchical Procedure, Rapid Impact Assessment Matrix, and Carrying Capacity Model.
TL;DR: In this article, a new Electronic Laser Speckle Pattern Interferometer based on Michelson interferometer is designed, where an object beam back scattered of an object surface and a reference beam originating from the same laser light source are superimposed on a charge couple device and form the interference fringe pattern (speckle gram).
Abstract: Digital speckle image correlation techniques have been successfully proven to be an accurate displacement analysis tool for a wide range of applications. In this paper, a new Electronic Laser Speckle Pattern Interferometer based on Michelson interferometer is designed. An object beam back scattered of an object surface and a reference beam, originating from the same laser light source are superimposed on a charge couple device and form the interference fringe pattern (speckle gram). Subtraction of speckle pattern before and after deformation of aluminum plate gives the measurement of displacement by using fringe analysis with a suitable image processing algorithm.
Journal Article•
TL;DR: In this article, a skew correction method based on feature points matching is proposed, which does not use actual lines, but relies on the lines constructed by the feature points extracted from the images.
Abstract: For images without obvious lines,a novel skew correction method based on feature points matching is proposed.In this method,the correction does not use actual lines,but relies on the lines constructed by the feature points extracted from the images.It is translation and scale invariant.Through bidirectional best correlative coefficients calculation,a high matching rate can be achieved.Mismatching can be decreased,by using the method based on the Law of Large Numbers.It can get the correct slant angles by using only two matching pairs.In addition,due to the special application background of this paper,a disk template is designed to extract the Eigenvector of the features,which leads to rotation invariance.
TL;DR: A novel algorithm is proposed, which robustly detects fingertip and archives touch-operated controls with a high precision of few millimeters, and a simple and robust hand detection method which can work well in a wide variety of situations including dark and luminous ambient illumination.
Abstract: In this paper, we propose a vision based human computer interaction (HCI) system, and user can interact with the computer by using the fingertip. And a novel algorithm is proposed, which robustly detects fingertip and archives touch-operated controls with a high precision of few millimeters. The fingertip detection algorithm is developed based on the prediction of the contents which is projected by projector, and a binocular vision system based on two cameras is applied for detecting the depth of fingertips and touch operation. The experiment shows good results and good performance. We have two important contributions: first, we develop a simple and robust hand detection method which can work well in a wide variety of situations including dark and luminous ambient illumination. Second, the two cameras comprise a stereo vision system. We determine whether a physical touch takes places by triangulation.
Journal Article•
TL;DR: In this paper, an algorithm of stellar targets suppression based on temporal-spatial domain fusion is proposed to suppress stellar targets with similar image characteristics that interfere with space targets detection in fixed-direction terrestrial opto-electronic observation systems.
Abstract: Regarding the numerous stellar targets with similar image characteristics that interfere with space targets detection in fixed-direction terrestrial astronomical opto-electronic observation systems,an algorithm of stellar targets suppression based on temporal-spatial domain fusion is proposed.In the time domain,the conventional image difference algorithm is improved and the dilative difference method is used to suppress stellar targets.In the space domain,mathematical morphological reconstruction is used to restore the full image of the detected stellar targets,and then stellar targets are suppressed through the difference between images before and after the morphological reconstruction.Based on different temporal-spatial domain fusion mechanics,two different temporal-spatial fusion methods are proposed to suppress stellar targets.Through comparison of real-measured data,the results show that the algorithm presented in this paper achieves a good stellar targets suppressing effect: 1)stellar targets and their edge pixels are efficiently suppressed;2)the faint stellar targets are suppressed well;3)signal-to-noise ratio of space targets are improved after the suppression of stellar targets.
TL;DR: In this paper, the authors proposed a new hybrid model by adding the passive aggregation represented by an appropriate physical force to increase wind speed prediction accuracy, and experiment results showed that the influence of passive aggregation in improving the prediction accuracy.
Abstract: The electricity production of wind farms is fluctuating because its dependency on the wind speed, so, improving of technical and economic integration of wind energy into the electricity supply system requires improving wind speed prediction accuracy. Thus, we propose a new hybrid model by adding the passive aggregation represented by an appropriate physical force to increase wind speed prediction accuracy. Experiment study shows significantly the influence of the passive aggregation in improving the prediction accuracy.
TL;DR: Four subtypes of the small, round blue-cell tumors (SRBCTs) were classified in this research and a classification method based on a fuzzy neural network (FNN) and a three-level classification model was developed.
Abstract: A bstract—An approach for cancer molecular classification based on their gene expression profiles is proposed. Four subtypes of the small, round blue-cell tumors (SRBCTs) were classified in this research. The Bhattacharyya distance of each gene was used as the gene selection method to select the twelve preliminary good genes for the SRBCTs subtypes classification. We then developed a classification method based on a fuzzy neural network (FNN) and a three-level classification model. Using the twelve preliminary good genes we did 100,000 iterations for each experiment on each level by using the FNN. After the experiments we got the number of bad cases (BC) for each gene. By the number of BC we deleted the bad genes one by one by using the FNN. Finally, we selected four genes for the SRBCTs subtype classification with 100% classification accuracy.
TL;DR: In this article, a comparison of DCT based image compression on hexagonal and rectangular sampling grid is performed using alternate pixel suppressal method and mean square error and peak signal to noise ratio is considered for the performance analysis.
Abstract: The advantages of processing images on hexagonal lattice are higher degree of circular symmetry, uniform connectivity, greater angular resolution, and a reduced need of storage and computation in image processing operations. In this work a comparison of DCT based Image compression on hexagonal and rectangular sampling grid is performed. DCT based image compression is performed on both rectangular domain and hexagonal domain using alternate pixel suppressal method. Mean Square Error and Peak Signal to Noise Ratio is considered for the performance analysis. Compression on hexagonal domain gives better results compared to compression on rectangular domain