Search

There are two main techniques to convert written or printed text into digital format. The first technique is to create an image of written/printed text, but images are large in size so they require huge memory space to store, as well as text in image form cannot be undergo further processes like edit, search, copy, etc. The second technique is to use an Optical Character Recognition (OCR) system. OCR's can read documents and convert manual text documents into digital text and this digital text can be processed to extract knowledge. A huge amount of Urdu language's data is available in handwritten or in printed form that needs to be converted into digital format for knowledge acquisition. Highly cursive, complex structure, bi-directionality, and compound in nature, etc. make the Urdu language too complex to obtain accurate OCR results. In this study, supervised learning-based OCR system is proposed for Nastalique Urdu language. The proposed system evaluations under a variety of experimental settings apprehend 98.4% training results and 97.3% test results, which is the highest recognition rate ever achieved by any Urdu language OCR system. The proposed system is simple to implement especially in software front of OCR system also the proposed technique is useful for printed text as well as handwritten text and it will help in developing more accurate Urdu OCR's software systems in the future. [ABSTRACT FROM AUTHOR]

Power dissipation has been the prime concern for CMOS circuits. Approximate computing is a potential solution for addressing this concern as it reduces power consumption resulting in improved performance in terms of power–delay product (PDP). Decrease of power consumption in approximate computing is achieved by approximating the demand of accuracy as per the error tolerance of the system. This paper presents a new approach for designing approximate adder by introducing inexactness in the existing logic gate(s). Approximated logic gates provide flexibility in designing low power error-resilient systems depending on the error tolerance of the applications such as image processing and data mining. The proposed approximate adder (PAA) has higher accuracy than existing approximate adders with normalized mean error distance of 0.123 and 0.1256 for 16-bit and 32-bit adder, respectively, and lower PDP of 1.924E − 18 J for 16-bit adder and 5.808E − 18 J for 32-bit adder. The PAA also performs better than some of the recent approximate adders reported in literature in terms of layout area and delay. Performance of PAA has also been evaluated with an image processing application. [ABSTRACT FROM AUTHOR]

Biomedical signal/image processing and analysis are always fascinating tasks in scientific researches, both theoretical and practical. One of the powerful tools in such topics is wavelet theory which has been proved to be challenging since its discovery. One of the best measures of the optimality of reconstruction of signals/images is the well-known Shannon's entropy. In wavelet theory, this is very well known and researchers are familiar with it. In the present work, a step forward is proposed based on more general wavelet tools. New approach is proposed for the reconstruction of signals/images provided with multiwavelets Shannon-type entropy to evaluate the order/disorder of the reconstructed signals/images. Efficiency and accuracy of the approach is confirmed by a simulation study on several models such as ECG, EEG and DNA/Proteins' signals. [ABSTRACT FROM AUTHOR]

Face annotation, a modern research topic in the area of image processing, has useful real-life applications. It is a really difficult task to annotate the correct names of people to the corresponding faces because of the variations in facial appearance. Hence, there still is a need for a robust feature to improve the performance of the face annotation process. In this work, a novel approach called the Deep Gabor-Oriented Local Order Features (DGOLOF) for feature representation has been proposed, which extracts deep texture features from face images. Seven recently proposed face annotation methods are considered to evaluate the proposed deep texture feature under uncontrolled situations like occlusion, expression changes, illumination and pose variations. Experimental results on the LFW, IMFDB, Yahoo and PubFig databases show that the proposed deep texture feature provides efficient results with the Name Semantic Network (NSN)-based face annotation. Moreover, it is observed that the proposed deep texture feature improves the performance of face annotation, regardless of all the challenges involved. [ABSTRACT FROM AUTHOR]

A vision-based method for detecting the cracks in the concrete sleepers of the railway tracks will be introduced in this paper. The method is able to detect and partially classify the cracks of the concrete sleepers in two successive steps based on the image processing and pattern recognition techniques. The method has been implemented on the acquired image data frames followed by the analysis, experimental, comparison results and evaluation. The presented results are reasonable which indicates the goodness of the introduced method. The preliminary results of this work have been presented in [A. Delforouzi, A. H. Tabatabaei, M. H. Khan and M. Grzegorzek, A vision-based method for automatic crack detection in railway sleepers, in Kurzynski, M., Wozniak, M., Burduk, R. (eds.), Proceedings of the 10th International Conference on Computer Recognition Systems CORES 2017, Polanica Zdroj, Poland. CORES 2017. Advances in Intelligent Systems and Computing, Vol. 578 (Springer, Cham, 2018), pp. 130–139, doi: 10.1007/978-3-319-59162-9_14]. [ABSTRACT FROM AUTHOR]

Localization of vessel Region of Interest (ROI) from medical images provides an interactive approach that can assist doctors in evaluating carotid artery diseases. Accurate vessel detection is a prerequisite for the following procedures, like wall segmentation, plaque identification and 3D reconstruction. Deep learning models such as CNN have been widely used in medical image processing, and achieve state-of-the-art performance. Faster R-CNN is one of the most representative and successful methods for object detection. Using outputs of feature maps in different layers has been proved to be a useful way to improve the detection performance, however, the common method is to ensemble outputs of different layers directly, and the special characteristic and different importance of each layer haven't been considered. In this work, we introduce a new network named Attention Layer R-CNN(AL R-CNN) and use it for automatic carotid artery detection, in which we integrate a new module named Attention Layer Part (ALP) into a basic Faster R-CNN system for better assembling feature maps of different layers. Experimental results on carotid dataset show that our method surpasses other state-of-the-art object detection systems. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has made tremendous contributions to image processing. Recently, the DL has also attracted attention in the specialized field of neural decoding from raw myoelectric signals (electromyograms, EMGs). However, to our knowledge, most existing methods require some measure of preprocessing of the raw EMGs. Moreover, research to date has not accounted for the variability in the signal during time sequences. In this paper, we propose a new convolutional neural network (CNN) structure that can directly process raw EMG signals for hand gesture classification. More specifically, we assess the effects of various window sizes and of two different EMG representations (time sequence and frequency spectra) on open EMG datasets. We found that the frequency spectra derived from raw EMGs is more suitable as the model input in the task of gesture classification. Meanwhile, the combination use of long window could improve the classification accuracy (CA) and the window of 1024 ms achieved the best results on two open datasets (7 3. 5 ± 5. 5 % and 9 1. 7 ± 2. 5 %). Further, our model requires no feature extraction procedures and is comparable with the optimal combination of features and classifier used by the traditional methods in the performance of specific tasks. [ABSTRACT FROM AUTHOR]

Image enhancement and segmentation are the two imperative steps while processing digital images. The goal of enhancement is to improve the quality of images so as to nullify the effect of poor illumination conditions during image acquisition. Afterwards, segmentation is performed to extract region of interest (ROI) from the background details of the image. There is a vast literature available for both the techniques. Therefore, this paper is intended to summarize the basic as well as advanced enhancement and segmentation techniques under a single heading; to provide an insight for future researches in the field of pattern recognition. [ABSTRACT FROM AUTHOR]

Duck eggs are rich in good protein and deeply favored by consumers. Among them, double-yolked duck eggs have high commercial value but are not easy to incubate, so they are often picked out by inspection before processing, circulation or being incubated in egg products industry. This paper used the computer vision technology on single- and double-yolked duck eggs with similar shape and size that were hard to distinguish merely by their external characteristics, studied the effective image processing algorithm and built a cognition model. Then, we collected duck eggs' transmission light color image, extracted B channel image, carried out iterative morphological open reconstruction and threshold segmentation to acquire yolk area, used convexity defects to identify double-yolked eggs and finally utilized watershed and ellipse fitting to separate yolk. Through inspection, 150 single- and double-yolked eggs were distinguished by using this method, with correct recognition rate reaching to 99% and 100%, respectively. The experimental results indicate that this method has a high accuracy in recognizing double-yolked duck eggs and can provide technical support in nondestructive identification of double-yolked duck egg. [ABSTRACT FROM AUTHOR]

This study proposed a method for multiple motion-sensitive devices (i.e. one Kinect v2 and two Leap Motions) to integrate gesture data in Unity. Other depth cameras could replace the Kinect. The general steps in integrating gesture data for motion-sensitive devices were introduced as follows. (1) A method was proposed to recognize the fingertip from depth images for the Kinect v2. (2) Coordinates observed by three motion-sensitive devices were aligned in space in three steps. First, preliminary coordinate conversion parameters were obtained through joint calibration of the three devices. Second, two types of devices were approached to the observed value of the standard Leap Motion by the least squares method twice (i.e. one Kinect and one Leap Motion on the first round, then two Leap Motions on the second round). (3) Data of the three devices were aligned with time by using Unity while applying the data plan. On this basis, a human hand interacted with a virtual object in Unity. Experimental results demonstrated that the proposed method had a small recognition error of hand joints and realized the natural interaction between the human hand and virtual objects. [ABSTRACT FROM AUTHOR]

Moment invariants of images are important features for pattern recognition and image processing. Many methods have been proposed to derive moment invariants of images under different group actions. However, the completeness and independence of a set of moment invariants are two open problems. In this paper, we use the moving frame method to derive affine moment invariants of color images. The moving frame for the normalized color moment space under the action of the affine group is presented. Using this moving frame, we obtain a complete and independent set of affine moment invariants of color images. This system of affine moment invariants is also invariant under diagonal photometric changes. Experimental results are provided to validate the correctness of the derivation. [ABSTRACT FROM AUTHOR]

A reconstruction-based image processing algorithm is developed to automatically extract feature points of digitalized 2D objects. This algorithm, which is introduced using a bumblebee flight case, is made up of two parts: a four-connected dot chasing rearrangement scheme and an extreme point extraction on a polarized contour. It is then applied to a dune evolution case that is simulated with a cellular automation model. The results show that the proposed algorithm is effective in characterizing individual moving objects. An additional algorithm is developed to categorize the extracted feature points of a bumblebee with translucent wings. [ABSTRACT FROM AUTHOR]

Batch processes and phenomena in traffic video data processing, such as traffic video image processing and intelligent transportation, are commonly used. The application of batch processing can increase the efficiency of resource conservation. However, owing to limited research on traffic video data processing conditions, batch processing activities in this area remain minimally examined. By employing database functional dependency mining, we developed in this study a workflow system. Meanwhile, the Bayesian network is a focus area of data mining. It provides an intuitive means for users to comply with causality expression approaches. Moreover, graph theory is also used in data mining area. In this study, the proposed approach depends on relational database functions to remove redundant attributes, reduce interference, and select a property order. The restoration of selective hidden naive Bayesian (SHNB) affects this property order when it is used only once. With consideration of the hidden naive Bayes (HNB) influence, rather than using one pair of HNB, it is introduced twice. We additionally designed and implemented mining dependencies from a batch traffic video processing log for data execution algorithms. [ABSTRACT FROM AUTHOR]

This paper focused on the illumination model of machined surface based on micro-image. According to micro-image forming condition, the theory that the image brightness is related to the microfacet topography and surface reflection characteristics is presented. The distribution rule of micro-topography and reflection characteristics of sample surface is analyzed according to the measured data. An illumination mode of machined surface is established based on the analysis result, and the model parameters are obtained by using the simulated annealing algorithm. Verification results show that this proposed model can improve the simulation accuracy significantly and describe the lighting effect of machined surface. The research will provide a new idea and method for the 3D reconstruction. [ABSTRACT FROM AUTHOR]

Since edge detection is a field of study used by various disciplines, it is of vital importance to calculate it accuretly. In addition, an edge detection algorithm may be involved in many image processing phases. A recent and contemporary approach, neutrosophy is based on neutrosophic logic, neutrosophic probability, neutrosophic set and neutrosophic statistics. This method yields better results compared to various other optimization methods. Neutrosophic Set (NS) is based on the origin, nature and scope of neutralities. In NS, problems are separated into true, false and indeterminacy subsets. It helps solve indeterminate situations effectively. It has recently been used in the field of image processing as indeterminate situations are also encountered in this field. Chan–Vese (CV) model is one of the successful region-based segmentation methods. The present study proposes a new NS-based edge detection method using CV algorithm. The proposed method combines the philosophical view of NS with successful segmentation characteristics of CV model. Obtained edge detection results are compared with different edge detection methods. The performances of each method are analyzed by using Figure of Merit (FOM) and Peak Signal-To-Noise Ratio (PSNR). The results suggest that the proposed method displays a better performance assessment compared to the used well-known methods. [ABSTRACT FROM AUTHOR]

This research is aimed at the optimization of a two-dimensional (2D) empirical graph under a certain height and dark conditions for a UAV, using the bionic sonar system to replace the visual sensor's BatSLAM mode and audio perceptual hash closed-loop detection. The BatSLAM model uses Sum of Absolute Difference (SAD) image processing methods to update the bionic sonar template. This method only judges whether the appearance of the two cochlear images is consistent and does not have geometric processing and feature extraction. Because the cochlear images produce various noises during the acquisition and transmission, there are some differences in cochlear maps obtained at the same position, which can lead to the distortion of the constructed empirical map. In this research, an audio perceptual hash closed-loop detection algorithm is developed to extract features of cochlea. It considers both the appearance and the energy difference between adjacent bands to improve the accuracy of closed-loop detection, thus solving the distortion problem and improving the experience map. The simulation experiment shows that the improved BatSLAM model based on the audio perceptual hash closed-loop detection can improve the 2D experience map for UAV under certain height and dark conditions, through improving the accuracy of the closed-loop detection to solve the distortion problem and thus implementing the optimization of the experience graph. [ABSTRACT FROM AUTHOR]

Using image processing technology to extract important information, such as isoline and weather system of the meteorological facsimile chart, is conducive to integration with other information, and has important practical value in navigation operations, marine weather forecasting, target recognition, and image retrieval. In meteorological facsimile charts, there are many types of medium-value lines, dense lines in some areas, superimposition and presence of multiple information, such as isolines and isoline characters, intersection of specific weather system symbols, etc. For different types of contours, numeric characters, weather system symbols and other object characteristics, the corresponding object extraction and recognition methods are proposed: Remove the latitude and longitude lines and coastline in the meteorological facsimile map by basemap matching; According to the position and shape features of the figure box, extract the meteorological fax figure box, separate and remove the different character tagging information; On the basis of identifying triangles and semicircles in weather symbols of the frontal system, the frontal symbols are extracted based on the circumscribed triangles and template matching. First the contour character on the fax image is expanded into a block connected region. Determine the position of the character information by judging the number of pixels in the connected region, and then use rotation and template matching to identify the numeric character. Using the meteorological facsimile maps of the US Meteorological Center and the Japan Meteorological Center for the main information extraction, experiments show that the method of this paper has a good effect on the complete and accurate symbol extraction of frontal weather systems, and reduces the computational complexity of contour detection, isoline extraction and numerical recognition. The methods can detect some information from weather charts properly and the error rate is very low. [ABSTRACT FROM AUTHOR]

The color PET-MRI medical image fusion is a growing research area in medical image processing domain. MRI imagery provides the picture of the anatomy of brain tissues without any functional information, while the color PET imagery gives the functional information of brain tissues with low spatial resolution. An ideal fusion model should maintain both the functional and spatial information of the images without any spatial distortion or color deformation. In this work, we present a novel fusion technique for color PET-MRI medical images using Two-Dimensional Discrete Fourier (2DFT)-Karhunen–Loeve transform (KLT) and singular value decomposition (SVD) in shearlet domain. This method decomposes the source images into multi-scaled and multi-directional sub-bands by shearlet transform (ST). Then, SVD is utilized to eliminate superfluous ST coefficients; later, the 2DFT and KLT are utilized to estimate optimal low-pass ST coefficients in each of the decomposed images. Later, we combine the largest low-pass ST coefficients using a novel fusion strategy. The process of decomposing the source image has been discussed in detail. Finally, we use the inverse shearlet transformation (IST) to obtain the fused image. Experimental results establish the excellence of our proposed method in terms of quantitative and qualitative evaluation criteria compared to other state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

This paper presents the modification of a previously developed algorithm using fractional order calculus and its implementation on mobile-embedded devices such as smartphones. The system performs enhancement on three categories of images such as those exhibiting uneven illumination, faded features/colors and hazy appearance. The key contributions include the simplified scheme for illumination correction, contrast enhancement and de-hazing using fractional derivative-based spatial filter kernels. These are achieved without resorting to logarithmic image processing, histogram-based statistics and complex de-hazing techniques employed by conventional algorithms. The simplified structure enables ease of implementation of the algorithm on mobile devices as an image processing application. Results indicate that the fractional order version of the algorithm yields good results relative to the integer order version and other algorithms from the literature. [ABSTRACT FROM AUTHOR]

The increasing diverse demand for image feature recognition and complicated relationships among image pixels cannot be fully and effectively handled by traditional single image recognition methods. In order to effectively improve classification accuracy in image processing, a deep belief network (DBN) classification model based on probability measure rough set theory is proposed in our research. First, the incomplete and inaccurate fuzzy information in the original image is preprocessed by the rough set method based on probability measure. Second, the attribute features of the image information are extracted, the attribute feature set is reduced to generate the classification rules, and key components are extracted as the input of the DBN. Third, the network structure of the DBN is determined by the extracted classification rules, and the importance of the rough set attributes is integrated and the weights of the neuronal nodes are corrected by the backpropagation (BP) algorithm. Last, the DBN is trained to classify images. The experimental analysis of the proposed method for medical imagery shows that it is more effective than current single rough set approach or the taxonomy of deep learning. [ABSTRACT FROM AUTHOR]

A novel laser printing files detection method is proposed in this paper to solve the problem of low efficiency and difficulty in traditional detection. The new method is based on improved scale-invariant feature transform (SIFT) feature and histogram feature. Firstly, analyze the graphical features of different laser printing files. Different files have different printing texture features in valid data area. So segment the valid data area to remove the interference of background. Secondly, extract the histogram feature of the same character in the printing file. Normalize the histogram and then calculate the Bhattacharyya coefficient between the detected file and the original file to determine whether the detected file is right or fake. At the same time, calculate the SIFT features and match the detected file and the original file. To focus on the letter or character region, the SIFT features which are out of contour are deleted. Finally, the results of the two different methods are both used as the result of the identification. When any of the result is fake, the end result will be fake. In the self-built database experiment, in different printing files from different printers, the inkjet areas possess different image features. When scanning different files using 600 dpi, the detect accuracy is higher than 97%. This method was able to meet the reliability requirements of law. [ABSTRACT FROM AUTHOR]

Image cosegmentation is a newly emerging research area in image processing. It refers to the problem of segmenting the common objects simultaneously in multiple images by utilizing the similarity of foreground regions among these images. In this paper, a new active contour model is proposed by using shape-similarity and foreground discovery scheme. The foreground discovery scheme is used to obtain the rough contours of the common objects which are used as initial evolution curves. The energy function of the proposed model includes two parts: an intra-image energy and an inter-image energy. The intra-image energy explores the differences between foreground regions and background regions in each image. And the inter-image energy is used to explore the similarities of the common objects among target images, which composes of a region color feature energy term and a shape constraint energy term. The region color feature term indicates the foreground consistency and the background consistency among the images; and the shape constraint energy term allows the global changes of shapes and truncates the local variation caused by misleading features. Experimental results show that the proposed model can improve the accuracy of the image cosegmentation significantly through regularizing the changes of shapes. [ABSTRACT FROM AUTHOR]

Nowadays, digital watermarking is employed for authentication and copyright protection. In this paper, a secure image watermarking scheme based on lifting wavelet transform (LWT) and singular value decomposition (SVD), is proposed. Both LWT and SVD are used as mathematical tools for embedding watermark in the host image. In this work, the watermark is a speech signal which is segmented into shorted portions having the same length. This length is equal to 256 and these different portions constitute the different columns of a speech image. The latter is then embedded into a grayscale or color image (the host image). This procedure is performed in order to insert into an image a confidential data which is in our case a speech signal. But instead of embedding this speech signal directly into the image, we transform it into a matrix and treated it as an image ("a speech image"). Of course, this speech signal transformation permits us to use LWT-2D and SVD to both the host image and the watermark ("a speech image"). The proposed technique is applied to a number of grayscale and color images. The obtained results from peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) computations show the performance of the proposed technique. Experimental evaluation also shows that the proposed scheme is able to withstand a number of attacks such as JPEG compression, mean and median attacks. In our evaluation of the proposed technique, we used another technique of secure image watermarking based on DWT-2D and SVD. [ABSTRACT FROM AUTHOR]

Conventional techniques for security of data, designed by using only one of the security mechanisms, cryptography or steganography, are suitable for limited applications only. In this paper, we propose a crypto-stego system that would be appropriate for secure transmission of different forms of data. In the proposed crypto-stego system, we present a mechanism to provide secure transmission of data by multiple safety measures, firstly by applying encryption using Affine Transform and Discrete Cosine Transform (DCT) and then merging this encrypted data with an image, randomly chosen from a set of available images, and sending the image so obtained to the receiver at the other end through the network. The data to be sent over a communication channel may be a gray-scale or colored image, or a text document (doc,.txt, or.pdf file). As it is encrypted and sent hidden in an image, it avoids any attention to itself by the observers in the network. At the receiver's side, reverse transformations are applied to obtain the original information. The experimental results, security analysis and statistical analysis for gray-scale images, RGB images, text documents (.doc,.txt,.pdf files), show robustness and appropriateness of the proposed crypto-stego system for secure transmission of the data through unsecured network. The security analysis and key space analysis demonstrate that the proposed technique is immune from cryptanalysis. [ABSTRACT FROM AUTHOR]

The development of a reliable and efficient software application system requires a competent software architecture which can attune to any design improvement opportunity in the early stages of software architectural design. An Architectural Description Language provides a description of all the component elements and their interactions. The proposed model determines all possible ways of connecting the components and connectors, after eliminating the transitive and symmetric conflicts among the connections, followed by the generation of the software architectural specification. An estimate on the maximum number of architectural specifications generated for a given number of components has been carried out. The syntax for specifying the components and the connectors has been formulated. The model proposed in the current work is generic and it will significantly help a software architect in building reliable, efficient and flexible software architecture, for any valid combination of components and connectors. It has been successfully tested for two prototype applications that involve processing of images and documents. [ABSTRACT FROM AUTHOR]

Solar image consists of obvious regions of solar activities and peaceful regions of no activity. Identifying effective solar active areas from solar image is a typical application of image-processing technology in astronomical research. Benefiting from real-time solar observation data provided by Heliophysics Event Knowledgebase (HEK) of Solar Dynamics Observatory (SDO), this paper presents a method of solar activity identification based on HEK. In this method, we gather data of six kinds of solar activities (time, location, and area) and establish a multiscale transformation model for the full-disk solar image of the corresponding time. Combining both location data and area data, we design different gradient thresholds to segment different solar activities’ regions. Two kinds of boundary-identification methods are used to locate and recognize solar activities’ regions, respectively. Furthermore, we study the correlation of the characteristic parameters (six kinds of solar activities’ data) of solar image and get the best combination of the characteristic parameters of each solar activity. The method in the paper provides precise positioning and efficient identification of solar activities, which lays the foundation for further work. In addition to that, extracting specific combination of features from different solar activities’ regions can provide a feasible way to build a streamlined image feature set for content-based image retrieval (CBIR) systems. [ABSTRACT FROM AUTHOR]

Subspace clustering analysis algorithms are often employed when dealing with high-dimensional data. As a representative approach, Low-Rank Representation (LRR) of data has achieved great success for subspace segmentation tasks in applications such as image processing. The traditional LRR-related methods consist of two separate tasks: first, the affinity graph construction by using lowrank minimization techniques, and then the spectral clustering, which is done on the affinity graph to get the final segmentation. Since these two steps are independent of each other, this method does not guarantee that the results obtained by the algorithm are globally optimal. In this paper, a method called Robust Structured Low-Rank Representation (RSLRR) is proposed, by integrating the two above mentioned tasks and solve a joint optimization problem. This paper also puts forward a method to solve the joint optimization problem, which can efficiently get both the segmentation and the structured low-rank representation. Experiments on several standard datasets show that, compared with other algorithms, the algorithm proposed in this paper can achieve better clustering results. [ABSTRACT FROM AUTHOR]

For the problem that the limited star map field angle cannot obtain the complete star map accurately, the paper study astral intrinsic and imaging features, a star map stitching algorithm based on the principle of visual perception is proposed firstly. The matching models of time and space dimensions is constructed by simulating the visual perception, then the stars and the planets points are saved by searching the matching star group dynamically, the star map is stitched and reconstructed efficiently by creating the computer sparse storage model. The experimental results show that the algorithm can achieve data compression quickly, compression ratio is 99.54%, which can reduce complexity of manual processing and can achieve star map stitching accurately. [ABSTRACT FROM AUTHOR]

A biologically inspired image fusion mechanism is analyzed in this paper. A pseudo-color image fusion method is proposed based on the improvement of a traditional method. The proposed model describes the fusion process using several abstract definitions which correspond to the detailed behaviors of neurons. Firstly, the infrared image and visible image are respectively ON against enhanced and OFF against enhanced. Secondly, we feed back the enhanced visible images given by the ON-antagonism system to the active cells in the center-surrounding antagonism receptive field. The fused VISIR signal are obtained by feeding back the OFF-enhanced infrared image to the corresponding surrounding-depressing neurons. Then we feed back the enhanced visible signal from OFF-antagonism system to the depressing cells in the center-surrounding antagonism receptive field. The ON-enhanced infrared image is taken as the input signal of the corresponding active cells in the neurons, then the cell response of infrared-enhance-visible is produced in the process, it is denoted as IRVIS. The three kinds of signal are considered as R, G and B components in the output composite image. Finally, some experiments are performed in order to evaluate the performance of the proposed method. The information entropy, average gradient and objective image fusion measure are used to assess the performance of the proposed method objectively. Some traditional digital signal processing-based fusion methods are also evaluated for comparison in the experiments. In this paper, the Quantitative assessment indices show that the proposed fusion model is superior to the classical Waxman's model, and some of its performance is better than the other image fusion methods. [ABSTRACT FROM AUTHOR]

In remote sensing image classification, distance measurements and classification criteria are equally important; and less accuracy of either would affect classification accuracy. Remote sensing image classification was performed by combining support vector machine (SVM) and -nearest neighbor (KNN). This was based on the separability of classes using SVM and the spatial and spectral characteristics of remote sensing data. Moreover, a distance formula is proposed as the measure criterion that considers both luminance and direction of the vectors. First, the SVM is trained and the support vectors (SVs) are obtained for each class. In the testing phase, newly tested samples were entered, and average distance between the test samples and SVs for each class are calculated using the distance formula. Finally, decisions are made to classify the test samples into the class with minimal average distance. This procedure is repeated until all test samples are classified. In the combinatorial algorithm, the nearest neighbor classifier is used to classify a testing sample, i.e. the average Euclidean distance between the testing data point to each set of SVs from different categories is calculated and the nearest neighbor classifier identifies the category with minimum distance. The proposed combinatorial algorithm has advantages over the conventional KNN for eliminating the parameter selection problem and reducing heavy learning time. A comparison is carried out with SVM, KNN and Spectral Angle Mapper (SAM) classification using ALOS/PALSAR and PSM images, and the effectiveness of the proposed algorithm is demonstrated. [ABSTRACT FROM AUTHOR]

After the first initiation, the Fuel Air Explosive (FAE) cloud formed through fuel explosion dispersal and it will generate tremendous damaging power after being detonated the second time. As the damaging power is closely related to the determination of reinitiation time, it is of great significance to study the growth principle of FAE cloud by means of analyzing FAE cloud images. Combining with background subtraction and region growing, an improved region growing image processing method was proposed, in which the seeds of region growing abstracted through background subtraction method and the growing criterion was modified. With this method, the integrate area of cloud can be obtained for extracting geometric parameters. Experiments were carried out on both cloudy and sunny days, and image overlap score was used to quantitatively evaluate the accuracy of images segmentation. The result indicated that this image processing method has advantages of high precision and robustness. In addition, the computation burden is reduced significantly compared with traditional region growing method. [ABSTRACT FROM AUTHOR]

Because of the subjectivity of human beings, the evaluation of image complexity in the Human Vision System (HVS) cannot be provided accurately by traditional image complexity evaluation models. In the 2016 Conference on Computer Vision and Pattern Recognition (CVPR 2016), an evaluation method of visual search difficulty based on the visual search time was proposed for the first time. In this paper, the ordinal relation of the image complexity for human perception was discussed, and a quantitative evaluation model based on Convolutional Neural Network (CNN) features and Support Vector Ordinal Regression (SVOR) with explicit inequality constraints on the thresholds was proposed. The results showed that the evaluation models based on SVOR and pyramid CNN features of images can describe the order relation of image complexity among different images more accurately, which achieve the Kendall's tau correlation of 0.4858, better than SVR overall under the same condition, whose highest Kendall's tau correlation is 0.4794. [ABSTRACT FROM AUTHOR]

Saliency region detection methods have become one of the hotspots in the field of image processing as an important method to improve the real-time and accurate analysis of massive data. Integrating more effective prior knowledge is a viable direction for improving the performance of saliency region detection methods. Most of the methods based on background prior and boundary connectivity prior assume the boundary area of the image as the background, by restraining the background to highlight the salient area. When the boundary area of the image does not describe the background well (such as a large difference in border area features), if the entire frame of the image is put together to compute the background feature, the calculation of the background feature will be inaccurate. In view of the above shortcomings, this paper proposed a saliency region detection method based on background and spatial position. This method carried on the image boundary super pixel clustering, determined the background feature according to the clustering center, and used the difference between the super pixel on the image and the background super pixel, and its spatial position to calculate the salient of the super pixels. This approach used MATLAB to program and experiment. The method was compared with a series of the state-of-the-art methods. The AUC of proposed algorithm reaches 0.839, and the MAE is 0.220, showing the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we propose an image-based approach to detect the presence of a vehicle license plate (VLP) in a traffic image. This method is based on the fractal character difference between the VLP region and the other regions. The technique extracts information from fractal feature blocks and computes the dimension zone that describes the difference between the license plate and the other areas in the scene. A new fractal-dimension computing method aimed at gray-image data has been presented and been applied to image segmentation. Three indexes have been defined to measure the performance of the method. The fractal-dimension parameter's choice and self-adapting adjustment have been discussed in detail. Further, the proposed system has been evaluated using test and verification datasets and has been proven to be robust against common issues of traffic images, such as varying illumination, camera vibration, insensitivity to vehicle plate's color and location, and high noise levels. Since there is always a large number of fractal characteristic blocks around the same spatial location in traffic video frames, the efficiency of the proposed algorithm for video will be greatly improved. [ABSTRACT FROM AUTHOR]

In this work, we propose a framework that performs a number of popular image-processing operations in the continuous domain. This is in contrast to the standard practice of defining them as operations over discrete sequences of sampled values. The guiding principle is that, in order to prevent aliasing, nonlinear image-processing operations should ideally be performed prior to prefiltering and sampling. This is of course impractical, as we may not have access to the continuous input. Even so, we show that it is best to apply image-processing operations over the continuous reconstruction of the input. This transformed continuous representation is then prefiltered and sampled to produce the output. The use of high-quality reconstruction strategies brings this alternative much closer to the ideal than directly operating over discrete values. We illustrate the advantages of our framework with several popular effects. In each case, we demonstrate the quality difference between continuous image-processing, their discrete counterparts and previous anti-aliasing alternatives. Finally, our GPU implementation shows that current graphics hardware has enough computational power to perform continuous image processing in real-time. [ABSTRACT FROM AUTHOR]

Handwriting, printed character recognition is an interesting area in image processing and pattern recognition. It consists of a number of phases which are preprocessing, feature extraction and classification. The phase of feature extraction is carried out by different techniques; zoning, profile projection, and ameliored Freeman. The high number of features vector can increase the error rate and the training time. So, to solve this problem, we present in this paper a new method of selecting attributes based on the evolution strategy in order to reduce the feature vector dimension and to improve the recognition rate. The proposed model has been applied to recognize numerals and it obtained a better results and showed more robustness than without the selection system. [ABSTRACT FROM AUTHOR]

Eye-feature diagnosis is a time-honored method for studying many diseases in traditional Chinese medicine. There is a close relationship between eye-feature and viscera, and eye-feature is a reflection of visceral health status. Commercially used ophthalmology diagnosis instruments have disadvantages and cannot satisfy the requirements of eye-feature diagnosis. In this paper, we proposed a novel askiatic imaging method that removes the interference of an illumination source’s reflection shadow and is free from image splicing. We developed a novel imaging system to implement this method, and some eye-feature characteristics to analyze visceral diseases were obtained. [ABSTRACT FROM AUTHOR]

With widely availed clinically used radionuclides, Cerenkov luminescence imaging (CLI) has become a potential tool in the field of optical molecular imaging. However, the impulse noises introduced by high-energy gamma rays that are generated during the decay of radionuclide reduce the image quality significantly, which affects the accuracy of quantitative analysis, as well as the three-dimensional reconstruction. In this work, a novel denoising framework based on fuzzy clustering and curvature-driven diffusion (CDD) is proposed to remove this kind of impulse noises. To improve the accuracy, the Fuzzy Local Information C-Means algorithm, where spatial information is evolved, is used. We evaluate the performance of the proposed framework systematically with a series of experiments, and the corresponding results demonstrate a better denoising effect than those from the commonly used median filter method. We hope this work may provide a useful data pre-processing tool for CLI and its following studies. [ABSTRACT FROM AUTHOR]

A novel hybrid-fitting energy-based active contours model in the level set framework is proposed. The method fuses the local image fitting term and the global image fitting term to drive the contour evolution, and a special extra term that penalizes the deviation of the level set function from a signed distance function is also included in our method, so the complex and costly reinitialization procedure is completely eliminated. Our model can efficiently segment the images with intensity inhomogeneity no matter where the initial curve is located in the image. In its numerical implementation, two efficient numerical schemes are used to ensure the sufficient efficiency of the evolution process, one is the Lattice Boltzmann Model (LBM), which is used for breaking the restrictions on time step, the other is the Sparse Field Method (SFM), which is introduced for fast local computation. Compared with the traditional schemes, these two strategies can further shorten the time consumption of the evolution process, this allows the level set to quickly reach the true target location. The extensive and promising experimental results on numerous synthetic and real images have shown that our method can efficiently improve the image segmentation performance, in terms of accuracy, efficiency, and robustness. [ABSTRACT FROM AUTHOR]

In response to the fast propagation of videos on the Internet, Content-Based Video Retrieval (CBVR) was introduced to help users find their desired items. Since most videos concern humans, human action retrieval was introduced as a new topic in CBVR. Most human action retrieval methods represent an action by extracting and describing its local features as more reliable than global ones; however, these methods are complex and not very accurate. In this paper, a low-complexity representation method that more accurately describes extracted local features is proposed. In this method, each video is represented independently from other videos. To this end, the motion information of each extracted feature is described by the directions and sizes of its movements. In this system, the correspondence between the directions and sizes of the movements is used to compare videos. Finally, videos that correspond best with the query video are delivered to the user. Experimental results illustrate that this method can outperform state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In Finger-Knuckle-Print (FKP) recognition, feature extraction plays a very important role in the overall system performance. This paper merges two types of the histograms of oriented gradients (HOG)-based features extracted from reflectance and illumination images for FKP-based identification. The Adaptive Single Scale Retinex (ASSR) algorithm has been used to extract the illumination and the reflectance images from each FKP image. Serial feature fusion is used to form a large feature vector for each user, and extract the distinctive features in the higher-dimension vector space. Finally, the cosine similarity distance measure is used for classification. The Hong Kong Polytechnic University (PolyU) FKP database is used during all of the tests. Experimental results show that our proposed system achieves better results than other state-of-the-art system. [ABSTRACT FROM AUTHOR]

Image haze removal has been extensively studied, but there has been no such an image database regarding the haze level. It is not convenient for readers to verify the assumptions or priors that are supposed to be useful for haze removal, and meanwhile, it is not fair to compare the performance of haze removal methods, which are effective for images with different haze levels. To solve this problem, we built a database consisting of more than 3464 images of different kinds of outdoor scenes. The images of the database are grouped into four classes regarding the haze level. Along with the database, we also observe a frequency magnitude prior, i.e. the frequency magnitude decreases with the increasing haze level, which can be used as a prior to develop haze removal methods. Our purpose is to help develop image haze removal methods, as well as verify existing statistical priors and discover new ones that can be used for image processing. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of image segmentation, an improved adaptive level set method is proposed based on level set evolution without re-initialization method and adaptive distance preserving level set evolution method. A new definition of weight coefficient in evolution equations is the main innovation of this paper. The improved method can detect certain object boundaries, interior and exterior contours of an object, edges of multi-objects and weak boundaries of an object by synthetic and real images numerical experiments. Numerical results show that the improved adaptive level set method has faster segmentation speed and higher segmentation accuracy compared with the previous two methods, especially in weak boundaries and edges of multi-objects segmentation problems. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel scheme to learn high-level representative features and conduct classification for hyperspectral image (HSI) data in an automatic fashion. The proposed method is a collaboration of a wavelet-based extended morphological profile (WTEMP) and a deep autoencoder (DAE) ('WTEMP-DAE'), with the aim of exploiting the discriminative capability of DAE when using WTEMP features as the input. Each part of WTEMP-DAE is ingenious and contributes to the final classification performance. Specifically, in WTEMP-DAE, the spatial information is extracted from the WTEMP, which is then joined with the wavelet denoised spectral information to form the spectral-spatial description of HSI data. The obtained features are fed into DAE as the original input, where the good weights and bias of the network are initialized through unsupervised pre-training. Once the pre-training is completed, the reconstruction layers are discarded and a logistic regression (LR) layer is added to the top of the network to perform supervised fine-tuning and classification. Experimental results on two real HSI data sets demonstrate that the proposed strategy improves classification performance in comparison with other state-of-the-art hand-crafted feature extractors and their combinations. [ABSTRACT FROM AUTHOR]

Front vehicle detection technology is one of the hot spots in the advanced driver assistance system research field. This paper puts forward a method for front vehicles detection based on video-and-laser-information at night. First of all, video images and laser data are pre-processed with the region growing and threshold area expunction algorithm. Then, the features of front vehicles are extracted by use of a Gabor filter based on the uncertainty principle, and the distances to front vehicles are obtained through laser point cloud. Finally, front vehicles are automatically classified during identification with the improved sequential minimal optimization algorithm, which was based on the support vector machine (SVM) algorithm. According to the experiment results, the method proposed by this text is effective and it is reliable to identify vehicles in front of intelligent vehicles at night. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new image interpolation algorithm by using geometric subdivision. Similar to image upsampling, the geometric subdivision can supplement unknown data according to a certain rule, but it can only generate smooth data. To preserve the sharp edges of the high-resolution image, we adopt a rational subdivision scheme. By adjusting the weight coefficients of the rational subdivision, we can control the mesh shape near sharp edges. Hence, the image edges are preserved. [ABSTRACT FROM AUTHOR]

In this study, we propose a new framework for 3D porous media shape characterization using quantitative data driven shape descriptors. The main conceptual innovations are the introduction of shape descriptors based on geometrical parameters of the shape and empirical mode decomposition (EMD) of the shape skeleton. The EMD yields a decomposition with intrinsic mode functions based on local properties of the skeleton. Efficient methods for computing the defined descriptors from a network of balls representation of the pore space are provided. A multivariate analysis is carried out to describe the relationships between the shape descriptors and justify their use in the context of shape analysis. The proposed descriptors are also used to group together objects by their similarity and perform optimal approximation of the porous media by primitives set. Properties on the approximation are given and discussed. The proposed framework is illustrated with computed tomography images of real soil sample. The results have demonstrated the performance of our methodology for shape characterization, optimal shape decomposition and comparison. [ABSTRACT FROM AUTHOR]

In society, there exists a gap in communication between the sighted community and the visually challenged people due to different scripts followed to read and write. To bridge this gap there is a need for a system that supports automatic conversion of Braille script to text and speech in the corresponding language. Optical Braille Recognition (OBR) system converts the hand-punched Braille characters into their equivalent natural language characters. The Text-to-Speech (TTS) system converts the recognized characters into audible speech using speech synthesis techniques. Existing literature reveals that OBR and TTS systems have been well established independently for English. There is a scope for development of OBR and TTS systems for regional languages. In spite of Kannada being one of the most widely spoken regional languages in India, minimal work has been done towards Kannada OBR and TTS. There is no system that directly converts Braille script to speech, therefore, this development of Kannada Braille to text and speech system is one of a kind. The acquired image is processed and feature extraction is performed using -means algorithm and heuristics to convert the Braille characters to Kannada script. The concatenation based speech synthesis technique employing phoneme as the basic unit is used to convert Kannada TTS using Festival TTS framework. Performance evaluation of the proposed system is done using Kannada Braille database developed independently, and the results obtained are found to be satisfactory when compared to existing methods in the literature. [ABSTRACT FROM AUTHOR]

COrdinate Rotation DIgital Computer (CORDIC) is commonly utilized for the computation of cosine/sine i.e., the trigonometric functions, singular value decomposition, in digital signal processing (especially in image/video processing), etc. This paper introduces an energy efficient quality tunable CORDIC architecture that computes the cosine/sine values of any required angle in real-time, and is thus well suited for real time DSP applications, especially for image or video processing applications. The proposed architecture reduces the latency and overcomes data dependency by simultaneously performing all the five iterations, that may vary depending upon the desired energy efficiency. The novelty of this architecture is that, desired quality can be achieved by selecting one out of the available three modes. In order to assess the efficacy of the suggested architecture, some benchmark images are processed using the Discrete Cosine Transform (DCT) coefficients obtained via the proposed design. Energy saving is achieved at the cost of slight acceptable degradation in the output image quality. Further, the simulation results show that the proposed architecture is 92.3%, 2.8% and 49.08% more energy efficient than the existing basic, scale-free and lookahead CORDIC architectures, respectively. [ABSTRACT FROM AUTHOR]

The video surveillance system based on face analysis has played an increasingly important role in the security industry. Compared with identification methods of other physical characteristics, face verification method is easy to be accepted by people. In the video surveillance scene, it is common to capture multiple faces belonging to a same person. We cannot get a good result of face recognition if we use all the images without considering image quality. In order to solve this problem, we propose a face deduplication system which is combined with face detection and face quality evaluation to obtain the highest quality face image of a person. The experimental results in this paper also show that our method can effectively detect the faces and select the high-quality face images, so as to improve the accuracy of face recognition. [ABSTRACT FROM AUTHOR]