Displaying publications 61 - 80 of 112 in total

Abstract:
Sort:
  1. Adeshina AM, Hashim R, Khalid NE, Abidin SZ
    Interdiscip Sci, 2012 Sep;4(3):161-72.
    PMID: 23292689 DOI: 10.1007/s12539-012-0132-y
    CT and MRI scans are widely used in medical diagnosis procedures, but they only produce 2-D images. However, the human anatomical structure, the abnormalities, tumors, tissues and organs are in 3-D. 2-D images from these devices are difficult to interpret because they only show cross-sectional views of the human structure. Consequently, such circumstances require doctors to use their expert experiences in the interpretation of the possible location, size or shape of the abnormalities, even for large datasets of enormous amount of slices. Previously, the concept of reconstructing 2-D images to 3-D was introduced. However, such reconstruction model requires high performance computation, may either be time-consuming or costly. Furthermore, detecting the internal features of human anatomical structure, such as the imaging of the blood vessels, is still an open topic in the computer-aided diagnosis of disorders and pathologies. This paper proposes a volume visualization framework using Compute Unified Device Architecture (CUDA), augmenting the widely proven ray casting technique in terms of superior qualities of images but with slow speed. Considering the rapid development of technology in the medical community, our framework is implemented on Microsoft.NET environment for easy interoperability with other emerging revolutionary tools. The framework was evaluated with brain datasets from the department of Surgery, University of North Carolina, United States, containing around 109 MRA datasets. Uniquely, at a reasonably cheaper cost, our framework achieves immediate reconstruction and obvious mappings of the internal features of human brain, reliable enough for instantaneous locations of possible blockages in the brain blood vessels.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  2. Shyam Sunder R, Eswaran C, Sriraam N
    Comput Biol Med, 2006 Sep;36(9):958-73.
    PMID: 16026779
    In this paper, 3-D discrete Hartley transform is applied for the compression of two medical modalities, namely, magnetic resonance images and X-ray angiograms and the performance results are compared with those of 3-D discrete cosine and Fourier transforms using the parameters such as PSNR and bit rate. It is shown that the 3-D discrete Hartley transform is better than the other two transforms for magnetic resonance brain images whereas for the X-ray angiograms, the 3-D discrete cosine transform is found to be superior.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  3. Latha B, Venkatesh B
    Genomics Proteomics Bioinformatics, 2004 Nov;2(4):222-36.
    PMID: 15901251
    As the topological properties of each spot in DNA microarray images may vary from one another, we employed granulometries to understand the shape-size content contributed due to a significant intensity value within a spot. Analysis was performed on the microarray image that consisted of 240 spots by using concepts from mathematical morphology. In order to find out indices for each spot and to further classify them, we adopted morphological multiscale openings, which provided microarrays at multiple scales. Successive opened microarrays were subtracted to identify the protrusions that were smaller than the size of structuring element. Spot-wise details, in terms of probability of these observed protrusions, were computed by placing a regularly spaced grid on microarray such that each spot was centered in each grid. Based on the probability of size distribution functions of these protrusions isolated at each level, we estimated the mean size and texture index for each spot. With these characteristics, we classified the spots in a microarray image into bright and dull categories through pattern spectrum and shape-size complexity measures. These segregated spots can be compared with those of hybridization levels.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods
  4. Mousavi Kahaki SM, Nordin MJ, Ashtari AH, J Zahra S
    PLoS One, 2016;11(3):e0149710.
    PMID: 26985996 DOI: 10.1371/journal.pone.0149710
    An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics--such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient--are insufficient for achieving adequate results under different image deformations. Thus, new descriptor's similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  5. Chow LS, Rajagopal H, Paramesran R, Alzheimer's Disease Neuroimaging Initiative
    Magn Reson Imaging, 2016 07;34(6):820-831.
    PMID: 26969762 DOI: 10.1016/j.mri.2016.03.006
    Medical Image Quality Assessment (IQA) plays an important role in assisting and evaluating the development of any new hardware, imaging sequences, pre-processing or post-processing algorithms. We have performed a quantitative analysis of the correlation between subjective and objective Full Reference - IQA (FR-IQA) on Magnetic Resonance (MR) images of the human brain, spine, knee and abdomen. We have created a MR image database that consists of 25 original reference images and 750 distorted images. The reference images were distorted with six types of distortions: Rician Noise, Gaussian White Noise, Gaussian Blur, DCT compression, JPEG compression and JPEG2000 compression, at various levels of distortion. Twenty eight subjects were chosen to evaluate the images resulting in a total of 21,700 human evaluations. The raw scores were then converted to Difference Mean Opinion Score (DMOS). Thirteen objective FR-IQA metrics were used to determine the validity of the subjective DMOS. The results indicate a high correlation between the subjective and objective assessment of the MR images. The Noise Quality Measurement (NQM) has the highest correlation with DMOS, where the mean Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank Order Correlation Coefficient (SROCC) are 0.936 and 0.938 respectively. The Universal Quality Index (UQI) has the lowest correlation with DMOS, where the mean PLCC and SROCC are 0.807 and 0.815 respectively. Student's T-test was used to find the difference in performance of FR-IQA across different types of distortion. The superior IQAs tested statistically are UQI for Rician noise images, Visual Information Fidelity (VIF) for Gaussian blur images, NQM for both DCT and JPEG compressed images, Peak Signal-to-Noise Ratio (PSNR) for JPEG2000 compressed images.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  6. Majeed A, Mt Piah AR, Ridzuan Yahya Z
    PLoS One, 2016;11(3):e0149921.
    PMID: 26967643 DOI: 10.1371/journal.pone.0149921
    Maxillofacial trauma are common, secondary to road traffic accident, sports injury, falls and require sophisticated radiological imaging to precisely diagnose. A direct surgical reconstruction is complex and require clinical expertise. Bio-modelling helps in reconstructing surface model from 2D contours. In this manuscript we have constructed the 3D surface using 2D Computerized Tomography (CT) scan contours. The fracture part of the cranial vault are reconstructed using GC1 rational cubic Ball curve with three free parameters, later the 2D contours are flipped into 3D with equidistant z component. The constructed surface is represented by contours blending interpolant. At the end of this manuscript a case report of parietal bone fracture is also illustrated by employing this method with a Graphical User Interface (GUI) illustration.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods
  7. Tan JH, Acharya UR, Chua KC, Cheng C, Laude A
    Med Phys, 2016 May;43(5):2311.
    PMID: 27147343 DOI: 10.1118/1.4945413
    The authors propose an algorithm that automatically extracts retinal vasculature and provides a simple measure to correct the extraction. The output of the method is a network of salient points, and blood vessels are drawn by connecting the salient points using a centripetal parameterized Catmull-Rom spline.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  8. Ali Shah SA, Laude A, Faye I, Tang TB
    J Biomed Opt, 2016 Oct;21(10):101404.
    PMID: 26868326 DOI: 10.1117/1.JBO.21.10.101404
    Microaneurysms (MAs) are known to be the early signs of diabetic retinopathy (DR). An automated MA detection system based on curvelet transform is proposed for color fundus image analysis. Candidates of MA were extracted in two parallel steps. In step one, blood vessels were removed from preprocessed green band image and preliminary MA candidates were selected by local thresholding technique. In step two, based on statistical features, the image background was estimated. The results from the two steps allowed us to identify preliminary MA candidates which were also present in the image foreground. A collection set of features was fed to a rule-based classifier to divide the candidates into MAs and non-MAs. The proposed system was tested with Retinopathy Online Challenge database. The automated system detected 162 MAs out of 336, thus achieved a sensitivity of 48.21% with 65 false positives per image. Counting MA is a means to measure the progression of DR. Hence, the proposed system may be deployed to monitor the progression of DR at early stage in population studies.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  9. Sharif KM, Rahman MM, Azmir J, Khatib A, Sabina E, Shamsudin SH, et al.
    Biomed Chromatogr, 2015 Dec;29(12):1826-33.
    PMID: 26033701 DOI: 10.1002/bmc.3503
    Multivariate analysis of thin-layer chromatography (TLC) images was modeled to predict antioxidant activity of Pereskia bleo leaves and to identify the contributing compounds of the activity. TLC was developed in optimized mobile phase using the 'PRISMA' optimization method and the image was then converted to wavelet signals and imported for multivariate analysis. An orthogonal partial least square (OPLS) model was developed consisting of a wavelet-converted TLC image and 2,2-diphynyl-picrylhydrazyl free radical scavenging activity of 24 different preparations of P. bleo as the x- and y-variables, respectively. The quality of the constructed OPLS model (1 + 1 + 0) with one predictive and one orthogonal component was evaluated by internal and external validity tests. The validated model was then used to identify the contributing spot from the TLC plate that was then analyzed by GC-MS after trimethylsilyl derivatization. Glycerol and amine compounds were mainly found to contribute to the antioxidant activity of the sample. An alternative method to predict the antioxidant activity of a new sample of P. bleo leaves has been developed.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  10. Mookiah MR, Acharya UR, Fujita H, Koh JE, Tan JH, Noronha K, et al.
    Comput Biol Med, 2015 Aug;63:208-18.
    PMID: 26093788 DOI: 10.1016/j.compbiomed.2015.05.019
    Age-related Macular Degeneration (AMD) is an irreversible and chronic medical condition characterized by drusen, Choroidal Neovascularization (CNV) and Geographic Atrophy (GA). AMD is one of the major causes of visual loss among elderly people. It is caused by the degeneration of cells in the macula which is responsible for central vision. AMD can be dry or wet type, however dry AMD is most common. It is classified into early, intermediate and late AMD. The early detection and treatment may help one to stop the progression of the disease. Automated AMD diagnosis may reduce the screening time of the clinicians. In this work, we have introduced LCP to characterize normal and AMD classes using fundus images. Linear Configuration Coefficients (CC) and Pattern Occurrence (PO) features are extracted from fundus images. These extracted features are ranked using p-value of the t-test and fed to various supervised classifiers viz. Decision Tree (DT), Nearest Neighbour (k-NN), Naive Bayes (NB), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) to classify normal and AMD classes. The performance of the system is evaluated using both private (Kasturba Medical Hospital, Manipal, India) and public domain datasets viz. Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) using ten-fold cross validation. The proposed approach yielded best performance with a highest average accuracy of 97.78%, sensitivity of 98.00% and specificity of 97.50% for STARE dataset using 22 significant features. Hence, this system can be used as an aiding tool to the clinicians during mass eye screening programs to diagnose AMD.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  11. Wan Ahmad WS, Zaki WM, Ahmad Fauzi MF
    Biomed Eng Online, 2015;14:20.
    PMID: 25889188 DOI: 10.1186/s12938-015-0014-8
    Unsupervised lung segmentation method is one of the mandatory processes in order to develop a Content Based Medical Image Retrieval System (CBMIRS) of CXR. The purpose of the study is to present a robust solution for lung segmentation of standard and mobile chest radiographs using fully automated unsupervised method.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  12. Vicnesh J, Wei JKE, Ciaccio EJ, Oh SL, Bhagat G, Lewis SK, et al.
    J Med Syst, 2019 Apr 26;43(6):157.
    PMID: 31028562 DOI: 10.1007/s10916-019-1285-6
    Celiac disease is a genetically determined disorder of the small intestine, occurring due to an immune response to ingested gluten-containing food. The resulting damage to the small intestinal mucosa hampers nutrient absorption, and is characterized by diarrhea, abdominal pain, and a variety of extra-intestinal manifestations. Invasive and costly methods such as endoscopic biopsy are currently used to diagnose celiac disease. Detection of the disease by histopathologic analysis of biopsies can be challenging due to suboptimal sampling. Video capsule images were obtained from celiac patients and controls for comparison and classification. This study exploits the use of DAISY descriptors to project two-dimensional images onto one-dimensional vectors. Shannon entropy is then used to extract features, after which a particle swarm optimization algorithm coupled with normalization is employed to select the 30 best features for classification. Statistical measures of this paradigm were tabulated. The accuracy, positive predictive value, sensitivity and specificity obtained in distinguishing celiac versus control video capsule images were 89.82%, 89.17%, 94.35% and 83.20% respectively, using the 10-fold cross-validation technique. When employing manual methods rather than the automated means described in this study, technical limitations and inconclusive results may hamper diagnosis. Our findings suggest that the computer-aided detection system presented herein can render diagnostic information, and thus may provide clinicians with an important tool to validate a diagnosis of celiac disease.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  13. Shah SAA, Tang TB, Faye I, Laude A
    Graefes Arch Clin Exp Ophthalmol, 2017 Aug;255(8):1525-1533.
    PMID: 28474130 DOI: 10.1007/s00417-017-3677-y
    PURPOSE: To propose a new algorithm of blood vessel segmentation based on regional and Hessian features for image analysis in retinal abnormality diagnosis.

    METHODS: Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast of the dark objects (blood vessels) against the background, the dot product of the grayscale image with itself was generated. To rectify the variation in contrast, we used a 5 × 5 window filter on each pixel. Based on 5 regional features, 1 intensity feature and 2 Hessian features per scale using 9 scales, we extracted a total of 24 features. A linear minimum squared error (LMSE) classifier was trained to classify each pixel into a vessel or non-vessel pixel.

    RESULTS: The DRIVE dataset provided 20 training and 20 test color fundus images. The proposed algorithm achieves a sensitivity of 72.05% with 94.79% accuracy.

    CONCLUSIONS: Our proposed algorithm achieved higher accuracy (0.9206) at the peripapillary region, where the ocular manifestations in the microvasculature due to glaucoma, central retinal vein occlusion, etc. are most obvious. This supports the proposed algorithm as a strong candidate for automated vessel segmentation.

    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  14. Sheikh Abdullah SN, Bohani FA, Nayef BH, Sahran S, Al Akash O, Iqbal Hussain R, et al.
    Comput Math Methods Med, 2016;2016:8603609.
    PMID: 27516807 DOI: 10.1155/2016/8603609
    Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods
  15. Yousef Kalafi E, Tan WB, Town C, Dhillon SK
    BMC Bioinformatics, 2016 Dec 22;17(Suppl 19):511.
    PMID: 28155722 DOI: 10.1186/s12859-016-1376-z
    BACKGROUND: Monogeneans are flatworms (Platyhelminthes) that are primarily found on gills and skin of fishes. Monogenean parasites have attachment appendages at their haptoral regions that help them to move about the body surface and feed on skin and gill debris. Haptoral attachment organs consist of sclerotized hard parts such as hooks, anchors and marginal hooks. Monogenean species are differentiated based on their haptoral bars, anchors, marginal hooks, reproductive parts' (male and female copulatory organs) morphological characters and soft anatomical parts. The complex structure of these diagnostic organs and also their overlapping in microscopic digital images are impediments for developing fully automated identification system for monogeneans (LNCS 7666:256-263, 2012), (ISDA; 457-462, 2011), (J Zoolog Syst Evol Res 52(2): 95-99. 2013;). In this study images of hard parts of the haptoral organs such as bars and anchors are used to develop a fully automated identification technique for monogenean species identification by implementing image processing techniques and machine learning methods.

    RESULT: Images of four monogenean species namely Sinodiplectanotrema malayanus, Trianchoratus pahangensis, Metahaliotrema mizellei and Metahaliotrema sp. (undescribed) were used to develop an automated technique for identification. K-nearest neighbour (KNN) was applied to classify the monogenean specimens based on the extracted features. 50% of the dataset was used for training and the other 50% was used as testing for system evaluation. Our approach demonstrated overall classification accuracy of 90%. In this study Leave One Out (LOO) cross validation is used for validation of our system and the accuracy is 91.25%.

    CONCLUSIONS: The methods presented in this study facilitate fast and accurate fully automated classification of monogeneans at the species level. In future studies more classes will be included in the model, the time to capture the monogenean images will be reduced and improvements in extraction and selection of features will be implemented.

    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  16. Mosleh MA, Baba MS, Malek S, Almaktari RA
    BMC Bioinformatics, 2016 Dec 22;17(Suppl 19):499.
    PMID: 28155649 DOI: 10.1186/s12859-016-1370-5
    BACKGROUND: Cephalometric analysis and measurements of skull parameters using X-Ray images plays an important role in predicating and monitoring orthodontic treatment. Manual analysis and measurements of cephalometric is considered tedious, time consuming, and subjected to human errors. Several cephalometric systems have been developed to automate the cephalometric procedure; however, no clear insights have been reported about reliability, performance, and usability of those systems. This study utilizes some techniques to evaluate reliability, performance, and usability metric using SUS methods of the developed cephalometric system which has not been reported in previous studies.

    METHODS: In this study a novel system named Ceph-X is developed to computerize the manual tasks of orthodontics during cephalometric measurements. Ceph-X is developed by using image processing techniques with three main models: enhancements X-ray image model, locating landmark model, and computation model. Ceph-X was then evaluated by using X-ray images of 30 subjects (male and female) obtained from University of Malaya hospital. Three orthodontics specialists were involved in the evaluation of accuracy to avoid intra examiner error, and performance for Ceph-X, and 20 orthodontics specialists were involved in the evaluation of the usability, and user satisfaction for Ceph-X by using the SUS approach.

    RESULTS: Statistical analysis for the comparison between the manual and automatic cephalometric approaches showed that Ceph-X achieved a great accuracy approximately 96.6%, with an acceptable errors variation approximately less than 0.5 mm, and 1°. Results showed that Ceph-X increased the specialist performance, and minimized the processing time to obtain cephalometric measurements of human skull. Furthermore, SUS analysis approach showed that Ceph-X has an excellent usability user's feedback.

    CONCLUSIONS: The Ceph-X has proved its reliability, performance, and usability to be used by orthodontists for the analysis, diagnosis, and treatment of cephalometric.

    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  17. Abu A, Leow LK, Ramli R, Omar H
    BMC Bioinformatics, 2016 Dec 22;17(Suppl 19):505.
    PMID: 28155645 DOI: 10.1186/s12859-016-1362-5
    BACKGROUND: Taxonomists frequently identify specimen from various populations based on the morphological characteristics and molecular data. This study looks into another invasive process in identification of house shrew (Suncus murinus) using image analysis and machine learning approaches. Thus, an automated identification system is developed to assist and simplify this task. In this study, seven descriptors namely area, convex area, major axis length, minor axis length, perimeter, equivalent diameter and extent which are based on the shape are used as features to represent digital image of skull that consists of dorsal, lateral and jaw views for each specimen. An Artificial Neural Network (ANN) is used as classifier to classify the skulls of S. murinus based on region (northern and southern populations of Peninsular Malaysia) and sex (adult male and female). Thus, specimen classification using Training data set and identification using Testing data set were performed through two stages of ANNs.

    RESULTS: At present, the classifier used has achieved an accuracy of 100% based on skulls' views. Classification and identification to regions and sexes have also attained 72.5%, 87.5% and 80.0% of accuracy for dorsal, lateral, and jaw views, respectively. This results show that the shape characteristic features used are substantial because they can differentiate the specimens based on regions and sexes up to the accuracy of 80% and above. Finally, an application was developed and can be used for the scientific community.

    CONCLUSIONS: This automated system demonstrates the practicability of using computer-assisted systems in providing interesting alternative approach for quick and easy identification of unknown species.

    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  18. Ahmadi H, Gholamzadeh M, Shahmoradi L, Nilashi M, Rashvand P
    Comput Methods Programs Biomed, 2018 Jul;161:145-172.
    PMID: 29852957 DOI: 10.1016/j.cmpb.2018.04.013
    BACKGROUND AND OBJECTIVE: Diagnosis as the initial step of medical practice, is one of the most important parts of complicated clinical decision making which is usually accompanied with the degree of ambiguity and uncertainty. Since uncertainty is the inseparable nature of medicine, fuzzy logic methods have been used as one of the best methods to decrease this ambiguity. Recently, several kinds of literature have been published related to fuzzy logic methods in a wide range of medical aspects in terms of diagnosis. However, in this context there are a few review articles that have been published which belong to almost ten years ago. Hence, we conducted a systematic review to determine the contribution of utilizing fuzzy logic methods in disease diagnosis in different medical practices.

    METHODS: Eight scientific databases are selected as an appropriate database and Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method was employed as the basis method for conducting this systematic and meta-analysis review. Regarding the main objective of this research, some inclusion and exclusion criteria were considered to limit our investigation. To achieve a structured meta-analysis, all eligible articles were classified based on authors, publication year, journals or conferences, applied fuzzy methods, main objectives of the research, problems and research gaps, tools utilized to model the fuzzy system, medical disciplines, sample sizes, the inputs and outputs of the system, findings, results and finally the impact of applied fuzzy methods to improve diagnosis. Then, we analyzed the results obtained from these classifications to indicate the effect of fuzzy methods in decreasing the complexity of diagnosis.

    RESULTS: Consequently, the result of this study approved the effectiveness of applying different fuzzy methods in diseases diagnosis process, presenting new insights for researchers about what kind of diseases which have been more focused. This will help to determine the diagnostic aspects of medical disciplines that are being neglected.

    CONCLUSIONS: Overall, this systematic review provides an appropriate platform for further research by identifying the research needs in the domain of disease diagnosis.

    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  19. AlDahoul N, Md Sabri AQ, Mansoor AM
    Comput Intell Neurosci, 2018;2018:1639561.
    PMID: 29623089 DOI: 10.1155/2018/1639561
    Human detection in videos plays an important role in various real life applications. Most of traditional approaches depend on utilizing handcrafted features which are problem-dependent and optimal for specific tasks. Moreover, they are highly susceptible to dynamical events such as illumination changes, camera jitter, and variations in object sizes. On the other hand, the proposed feature learning approaches are cheaper and easier because highly abstract and discriminative features can be produced automatically without the need of expert knowledge. In this paper, we utilize automatic feature learning methods which combine optical flow and three different deep models (i.e., supervised convolutional neural network (S-CNN), pretrained CNN feature extractor, and hierarchical extreme learning machine) for human detection in videos captured using a nonstatic camera on an aerial platform with varying altitudes. The models are trained and tested on the publicly available and highly challenging UCF-ARG aerial dataset. The comparison between these models in terms of training, testing accuracy, and learning speed is analyzed. The performance evaluation considers five human actions (digging, waving, throwing, walking, and running). Experimental results demonstrated that the proposed methods are successful for human detection task. Pretrained CNN produces an average accuracy of 98.09%. S-CNN produces an average accuracy of 95.6% with soft-max and 91.7% with Support Vector Machines (SVM). H-ELM has an average accuracy of 95.9%. Using a normal Central Processing Unit (CPU), H-ELM's training time takes 445 seconds. Learning in S-CNN takes 770 seconds with a high performance Graphical Processing Unit (GPU).
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
  20. Kahaki SMM, Arshad H, Nordin MJ, Ismail W
    PLoS One, 2018;13(7):e0200676.
    PMID: 30024921 DOI: 10.1371/journal.pone.0200676
    Image registration of remotely sensed imagery is challenging, as complex deformations are common. Different deformations, such as affine and homogenous transformation, combined with multimodal data capturing can emerge in the data acquisition process. These effects, when combined, tend to compromise the performance of the currently available registration methods. A new image transform, known as geometric mean projection transform, is introduced in this work. As it is deformation invariant, it can be employed as a feature descriptor, whereby it analyzes the functions of all vertical and horizontal signals in local areas of the image. Moreover, an invariant feature correspondence method is proposed as a point matching algorithm, which incorporates new descriptor's dissimilarity metric. Considering the image as a signal, the proposed approach utilizes a square Eigenvector correlation (SEC) based on the Eigenvector properties. In our experiments on standard test images sourced from "Featurespace" and "IKONOS" datasets, the proposed method achieved higher average accuracy relative to that obtained from other state of the art image registration techniques. The accuracy of the proposed method was assessed using six standard evaluation metrics. Furthermore, statistical analyses, including t-test and Friedman test, demonstrate that the method developed as a part of this study is superior to the existing methods.
    Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links