MyMedR

Displaying publications 1 - 20 of 247 in total

Abstract:

Sort:

RERS-CC: Robotic facial recognition system for improving the accuracy of human face identification using HRI

Jing W, Tao H, Rahman MA, Kabir MN, Yafeng L, Zhang R, et al.

Work, 2021;68(3):923-934.
PMID: 33612534 DOI: 10.3233/WOR-203426

BACKGROUND: Human-Computer Interaction (HCI) is incorporated with a variety of applications for input processing and response actions. Facial recognition systems in workplaces and security systems help to improve the detection and classification of humans based on the vision experienced by the input system.
OBJECTIVES: In this manuscript, the Robotic Facial Recognition System using the Compound Classifier (RERS-CC) is introduced to improve the recognition rate of human faces. The process is differentiated into classification, detection, and recognition phases that employ principal component analysis based learning. In this learning process, the errors in image processing based on the extracted different features are used for error classification and accuracy improvements.
RESULTS: The performance of the proposed RERS-CC is validated experimentally using the input image dataset in MATLAB tool. The performance results show that the proposed method improves detection and recognition accuracy with fewer errors and processing time.
CONCLUSION: The input image is processed with the knowledge of the features and errors that are observed with different orientations and time instances. With the help of matching dataset and the similarity index verification, the proposed method identifies precise human face with augmented true positives and recognition rate.

Matched MeSH terms: Image Processing, Computer-Assisted
ADA-SR: Activity detection and analysis using security robots for reliable workplace safety

Zhang G, Jing W, Tao H, Rahman MA, Salih SQ, Al-Saffar A, et al.

Work, 2021;68(3):935-943.
PMID: 33612535 DOI: 10.3233/WOR-203427

BACKGROUND: Human-Robot Interaction (HRI) has become a prominent solution to improve the robustness of real-time service provisioning through assisted functions for day-to-day activities. The application of the robotic system in security services helps to improve the precision of event detection and environmental monitoring with ease.
OBJECTIVES: This paper discusses activity detection and analysis (ADA) using security robots in workplaces. The application scenario of this method relies on processing image and sensor data for event and activity detection. The events that are detected are classified for its abnormality based on the analysis performed using the sensor and image data operated using a convolution neural network. This method aims to improve the accuracy of detection by mitigating the deviations that are classified in different levels of the convolution process.
RESULTS: The differences are identified based on independent data correlation and information processing. The performance of the proposed method is verified for the three human activities, such as standing, walking, and running, as detected using the images and sensor dataset.
CONCLUSION: The results are compared with the existing method for metrics accuracy, classification time, and recall.

Matched MeSH terms: Image Processing, Computer-Assisted
Solid waste bin detection and classification using Dynamic Time Warping and MLP classifier

Islam MS, Hannan MA, Basri H, Hussain A, Arebey M

Waste Manag, 2014 Feb;34(2):281-90.
PMID: 24238802 DOI: 10.1016/j.wasman.2013.10.030

The increasing requirement for Solid Waste Management (SWM) has become a significant challenge for municipal authorities. A number of integrated systems and methods have introduced to overcome this challenge. Many researchers have aimed to develop an ideal SWM system, including approaches involving software-based routing, Geographic Information Systems (GIS), Radio-frequency Identification (RFID), or sensor intelligent bins. Image processing solutions for the Solid Waste (SW) collection have also been developed; however, during capturing the bin image, it is challenging to position the camera for getting a bin area centralized image. As yet, there is no ideal system which can correctly estimate the amount of SW. This paper briefly discusses an efficient image processing solution to overcome these problems. Dynamic Time Warping (DTW) was used for detecting and cropping the bin area and Gabor wavelet (GW) was introduced for feature extraction of the waste bin image. Image features were used to train the classifier. A Multi-Layer Perceptron (MLP) classifier was used to classify the waste bin level and estimate the amount of waste inside the bin. The area under the Receiver Operating Characteristic (ROC) curves was used to statistically evaluate classifier performance. The results of this developed system are comparable to previous image processing based system. The system demonstration using DTW with GW for feature extraction and an MLP classifier led to promising results with respect to the accuracy of waste level estimation (98.50%). The application can be used to optimize the routing of waste collection based on the estimated bin level.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
An automated solid waste bin level detection system using a gray level aura matrix

Hannan MA, Arebey M, Begum RA, Basri H

Waste Manag, 2012 Dec;32(12):2229-38.
PMID: 22749722 DOI: 10.1016/j.wasman.2012.06.002

An advanced image processing approach integrated with communication technologies and a camera for waste bin level detection has been presented. The proposed system is developed to address environmental concerns associated with waste bins and the variety of waste being disposed in them. A gray level aura matrix (GLAM) approach is proposed to extract the bin image texture. GLAM parameters, such as neighboring systems, are investigated to determine their optimal values. To evaluate the performance of the system, the extracted image is trained and tested using multi-layer perceptions (MLPs) and K-nearest neighbor (KNN) classifiers. The results have shown that the accuracy of bin level classification reach acceptable performance levels for class and grade classification with rates of 98.98% and 90.19% using the MLP classifier and 96.91% and 89.14% using the KNN classifier, respectively. The results demonstrated that the system performance is robust and can be applied to a variety of waste and waste bin level detection under various conditions.

Matched MeSH terms: Image Processing, Computer-Assisted/instrumentation*
Fulltext ESTIMATION OF CORAL RUBBLE QUANTITY USING EDGE DETECTION AND MORPHOLOGICAL-BASED METHODS

MUHAMMAD SUZURI HITAM, NURSYAHIRAH HAFIZ, ZAINUDDIN BACHOK, ZAINUDDIN BACHOK, MOHD SAFUAN CHE DIN

UMT Journal of Undergraduate Research, 2019;1(3):105-119.
MyJurnal

Reef rubble representsthe broken components of the coraland reefstructure which could be in the form of dead,broken or other fragmented coral.The process to estimate the distribution of reef rubble is currently done manually and thus takesa long timeto completeand is laborious. This paper presentsan image-processing-basedmethod to estimate the distribution of reef rubbles in a coral reef environmentfrom a still image. The method is basically a series of image processing steps includingimage complement, image binarization, edgedetection, smoothing by Weiner filter and followed by erosion and dilation process.The experimentalresults showedthat the system wasable to roughly estimate the distribution of reef rubble.

Matched MeSH terms: Image Processing, Computer-Assisted
Fulltext Protein expression in sera of patients with amoebic liver abscess (ALA): potential use of haptoglobin as a surrogate disease marker

Othman N, Zainudin NS, Mohamed Z, Yahya MM, Leow VM, Noordin R

Trop Biomed, 2013 Jun;30(2):257-66.
PMID: 23959491 MyJurnal

The protein profile of serum samples from patients with amoebic liver abscess (ALA) was compared to those of normal individuals to determine their expression levels and to identify potential surrogate disease markers. Serum samples were resolved by two dimensional electrophoresis (2-DE) followed by image analysis. The up and down-regulated protein spots were excised from the gels and analysed by MS/MS. The concentration of three clusters of proteins i.e. haptoglobin (HP), α1-antitrypsin (AAT) and transferrin in serum samples of ALA patients and healthy controls were compared using competitive ELISA. In addition, serum concentrations of HP and transferrin in samples of patients with ALA and pyogenic liver abscess (PLA) were also compared. The results of the protein 2-DE expression analysis showed that HP cluster, AAT cluster, one spot each from unknown spots no. 1 and 2 were significantly up-regulated and transferrin cluster was significantly down-regulated in ALA patients' sera (p<0.05). The MS/MS analysis identified the unknown protein spot no.1 as human transcript and haptoglobin and spot no. 2 as albumin. Competitive ELISA which compared concentrations of selected proteins in sera of ALA and healthy controls verified the up-regulated expression (p<0.05) of HP and the down-regulated expression (p<0.01) of transferrin in the former, while there was no significant difference in AAT expression (p> 0.05). However, when ALA and PLA samples were compared, competitive ELISA showed significant increased concentration of HP (p<0.05) while transferrin levels were not different. In conclusion, this study showed that HP is a potential surrogate disease marker for ALA.

Matched MeSH terms: Image Processing, Computer-Assisted
Image analysis procedure for the optical scanning of fine-root dynamics: errors depending on the observer and root-viewing window size

Kume T, Ohashi M, Makita N, Kho LK, Katayama A, Endo I, et al.

Tree Physiol, 2018 12 01;38(12):1927-1938.
PMID: 30452737 DOI: 10.1093/treephys/tpy124

Clarifying the dynamics of fine roots is critical to understanding carbon and nutrient cycling in forest ecosystems. An optical scanner can potentially be used in studying fine-root dynamics in forest ecosystems. The present study examined image analysis procedures suitable for an optical scanner having a large (210 mm × 297 mm) root-viewing window. We proposed a protocol for analyzing whole soil images obtained by an optical scanner that cover depths of 0-210 mm. We tested our protocol using six observers with different experience in studying roots. The observers obtained data from the manual digitization of sequential soil images recorded for a Bornean tropical forest according to the protocol. Additionally, the study examined the potential tradeoff between the soil image size and accuracy of estimates of fine-root dynamics in a simple exercise. The six observers learned the protocol and obtained similar temporal patterns of fine-root growth and biomass with error of 10-20% regardless of their experience. However, there were large errors in decomposition owing to the low visibility of decomposed fine roots. The simple exercise revealed that a smaller root-viewing window (smaller than 60% of the original window) produces patterns of fine-root dynamics that are different from those for the original window size. The study showed the high applicability of our image analysis approach for whole soil images taken by optical scanners in estimating the fine-root dynamics of forest ecosystems.

Matched MeSH terms: Image Processing, Computer-Assisted*
Fulltext A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction

Rahman H, Khan AR, Sadiq T, Farooqi AH, Khan IU, Lim WH

Tomography, 2023 Dec 05;9(6):2158-2189.
PMID: 38133073 DOI: 10.3390/tomography9060169

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.

Matched MeSH terms: Image Processing, Computer-Assisted/methods
Fulltext Zone specific fractal dimension of retinal images as predictor of stroke incidence

Aliahmad B, Kumar DK, Hao H, Unnikrishnan P, Che Azemin MZ, Kawasaki R, et al.

ScientificWorldJournal, 2014;2014:467462.
PMID: 25485298 DOI: 10.1155/2014/467462

Fractal dimensions (FDs) are frequently used for summarizing the complexity of retinal vascular. However, previous techniques on this topic were not zone specific. A new methodology to measure FD of a specific zone in retinal images has been developed and tested as a marker for stroke prediction. Higuchi's fractal dimension was measured in circumferential direction (FDC) with respect to optic disk (OD), in three concentric regions between OD boundary and 1.5 OD diameter from its margin. The significance of its association with future episode of stroke event was tested using the Blue Mountain Eye Study (BMES) database and compared against spectrum fractal dimension (SFD) and box-counting (BC) dimension. Kruskal-Wallis analysis revealed FDC as a better predictor of stroke (H = 5.80, P = 0.016, α = 0.05) compared with SFD (H = 0.51, P = 0.475, α = 0.05) and BC (H = 0.41, P = 0.520, α = 0.05) with overall lower median value for the cases compared to the control group. This work has shown that there is a significant association between zone specific FDC of eye fundus images with future episode of stroke while this difference is not significant when other FD methods are employed.

Matched MeSH terms: Image Processing, Computer-Assisted*
Fulltext Investigation of CPD and HMDS sample preparation techniques for cervical cells in developing computer-aided screening system based on FE-SEM/EDX

Jusman Y, Ng SC, Abu Osman NA

ScientificWorldJournal, 2014;2014:289817.
PMID: 25610902 DOI: 10.1155/2014/289817

This paper investigated the effects of critical-point drying (CPD) and hexamethyldisilazane (HMDS) sample preparation techniques for cervical cells on field emission scanning electron microscopy and energy dispersive X-ray (FE-SEM/EDX). We investigated the visualization of cervical cell image and elemental distribution on the cervical cell for two techniques of sample preparation. Using FE-SEM/EDX, the cervical cell images are captured and the cell element compositions are extracted for both sample preparation techniques. Cervical cell image quality, elemental composition, and processing time are considered for comparison of performances. Qualitatively, FE-SEM image based on HMDS preparation technique has better image quality than CPD technique in terms of degree of spread cell on the specimen and morphologic signs of cell deteriorations (i.e., existence of plate and pellet drying artifacts and membrane blebs). Quantitatively, with mapping and line scanning EDX analysis, carbon and oxygen element compositions in HMDS technique were higher than the CPD technique in terms of weight percentages. The HMDS technique has shorter processing time than the CPD technique. The results indicate that FE-SEM imaging, elemental composition, and processing time for sample preparation with the HMDS technique were better than CPD technique for cervical cell preparation technique for developing computer-aided screening system.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext Intelligent screening systems for cervical cancer

Jusman Y, Ng SC, Abu Osman NA

ScientificWorldJournal, 2014;2014:810368.
PMID: 24955419 DOI: 10.1155/2014/810368

Advent of medical image digitalization leads to image processing and computer-aided diagnosis systems in numerous clinical applications. These technologies could be used to automatically diagnose patient or serve as second opinion to pathologists. This paper briefly reviews cervical screening techniques, advantages, and disadvantages. The digital data of the screening techniques are used as data for the computer screening system as replaced in the expert analysis. Four stages of the computer system are enhancement, features extraction, feature selection, and classification reviewed in detail. The computer system based on cytology data and electromagnetic spectra data achieved better accuracy than other data.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext A chaotic cryptosystem for images based on Henon and Arnold cat map

Soleymani A, Nordin MJ, Sundararajan E

ScientificWorldJournal, 2014;2014:536930.
PMID: 25258724 DOI: 10.1155/2014/536930

The rapid evolution of imaging and communication technologies has transformed images into a widespread data type. Different types of data, such as personal medical information, official correspondence, or governmental and military documents, are saved and transmitted in the form of images over public networks. Hence, a fast and secure cryptosystem is needed for high-resolution images. In this paper, a novel encryption scheme is presented for securing images based on Arnold cat and Henon chaotic maps. The scheme uses Arnold cat map for bit- and pixel-level permutations on plain and secret images, while Henon map creates secret images and specific parameters for the permutations. Both the encryption and decryption processes are explained, formulated, and graphically presented. The results of security analysis of five different images demonstrate the strength of the proposed cryptosystem against statistical, brute force and differential attacks. The evaluated running time for both encryption and decryption processes guarantee that the cryptosystem can work effectively in real-time applications.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*; Image Processing, Computer-Assisted/standards
Fulltext Image deconvolution by means of frequency blur invariant concept

Honarvar Shakibaei B, Jahanshahi P

ScientificWorldJournal, 2014;2014:951842.
PMID: 25202743 DOI: 10.1155/2014/951842

Different blur invariant descriptors have been proposed so far, which are either in the spatial domain or based on the properties available in the moment domain. In this paper, a frequency framework is proposed to develop blur invariant features that are used to deconvolve a degraded image caused by a Gaussian blur. These descriptors are obtained by establishing an equivalent relationship between the normalized Fourier transforms of the blurred and original images, both normalized by their respective fixed frequencies set to one. Advantage of using the proposed invariant descriptors is that it is possible to estimate both the point spread function (PSF) and the original image. The performance of frequency invariants will be demonstrated through experiments. An image deconvolution is done as an additional application to verify the proposed blur invariant features.

Matched MeSH terms: Image Processing, Computer-Assisted*
Fulltext Estimating body related soft biometric traits in video frames

Arigbabu OA, Ahmad SM, Adnan WA, Yussof S, Iranmanesh V, Malallah FL

ScientificWorldJournal, 2014;2014:460973.
PMID: 25121120 DOI: 10.1155/2014/460973

Soft biometrics can be used as a prescreening filter, either by using single trait or by combining several traits to aid the performance of recognition systems in an unobtrusive way. In many practical visual surveillance scenarios, facial information becomes difficult to be effectively constructed due to several varying challenges. However, from distance the visual appearance of an object can be efficiently inferred, thereby providing the possibility of estimating body related information. This paper presents an approach for estimating body related soft biometrics; specifically we propose a new approach based on body measurement and artificial neural network for predicting body weight of subjects and incorporate the existing technique on single view metrology for height estimation in videos with low frame rate. Our evaluation on 1120 frame sets of 80 subjects from a newly compiled dataset shows that the mentioned soft biometric information of human subjects can be adequately predicted from set of frames.

Matched MeSH terms: Image Processing, Computer-Assisted/methods
Fulltext Microscopic features of enamel and dentinal caries under confocal laser scanning microscopy (CLSM) and image analyzer: preliminary experimental study

Saini R, Azmi AS, Ghani NB, Al-Salihi KA

Med J Malaysia, 2007 Aug;62(3):238-40.
PMID: 18246915 MyJurnal

This study was designed to identify surface and subsurface microscopic changes in different carious lesions by using Confocal Laser Scanning Microscope (CLSM) and Image analyzer (light microscopy). Thirty extracted carious posterior teeth were fixed, embedded and polymerized in plastic fixation medium. The final thin sections (80mm) were stained with H&E and Masson Goldner's Tricome while others were left unstained. Under Confocal, marked differences between control sound enamel and dentin, and carious area of the samples were observed which illustrated that a correlation existed between the zone of autofluoresence, demineralization and carious enamel and dentin. Compared to CLSM, Image Analyzer only produce two-dimensional images but the histopathological changes were better appreciated by using various staining methods.

Matched MeSH terms: Image Processing, Computer-Assisted*
Fulltext Brain death: rapid evaluation using computerized radionuclide cerebral flow study

Paramsothy M, Ong GSY, Wong BH, Loh TG, Delilkan AE

Med J Malaysia, 1986 Sep;41(3):189-97.
PMID: 2823083

Demonstration of arrested intracerebral blood flow is the ultimate evidence of brain death. Computerized radionuclide cerebral flow study was done on 18 patients diagnosed clinically as brain dead. Correlation was made with clinical neurophysiological and EEG findings. The criteria for diagnosis of arrested intracerebral perfusion using radionuclide flow study were: non-visualization of blood flow activity in the intracranial arteries during the arterial phase, diffused cerebral activity during the capillary phase and non-filling of venous sinuses during the venous phase; visualization of typical 'hot nasal' activity; the time activity curve over the cerebral hemispheres lacks a bolus effect and instead shows a delayed gradual rise of activity. These features are pathognomonic of brain tamponade.
Arrested intracranial circulation was seen in 16 patients (ten had electrocerebral silence; one had extremely abnormal EEG with small voltage activity and five had no EEG done). In the remaining two patients, some cerebral blood flow was demonstrated (one had no definite cerebral activity and the other had diffused EEG activity).
Radionuclide cerebral flow study is a very sensitive, accurate, safe, simple, rapid and non-invasive modality in confirming brain death and is especially useful in patients on "brain-protection" regime, in hypothermia or in certain metabolic states where diagnosis based on clinical and EEG criteria is difficult. EEG need not be a required procedure once brain death is established by the demonstration of arrested intracranial circulation.

Matched MeSH terms: Image Processing, Computer-Assisted
Regression methods to investigate the relationship between facial measurements and widths of the maxillary anterior teeth

Isa ZM, Tawfiq OF, Noor NM, Shamsudheen MI, Rijal OM

J Prosthet Dent, 2010 Mar;103(3):182-8.
PMID: 20188241 DOI: 10.1016/S0022-3913(10)60028-5

In rehabilitating edentulous patients, selecting appropriately sized teeth in the absence of preextraction records is problematic.

Matched MeSH terms: Image Processing, Computer-Assisted
Denture microlabeling technique

Ibrahim WM

J Prosthet Dent, 1996 Jul;76(1):104.
PMID: 8814640
Matched MeSH terms: Image Processing, Computer-Assisted
Assessment of masticatory performance by geometric measurement of the mixing ability with 2-color chewing gum

Yousof Y, Salleh NM, Yusof F

J Prosthet Dent, 2019 Jun;121(6):916-921.
PMID: 30745100 DOI: 10.1016/j.prosdent.2018.09.005

STATEMENT OF PROBLEM: The 2-color mixing ability test has been recently introduced for objective assessment of masticatory performance. However, the ideal bicolor specimens have not yet been identified, and the color analysis of digital images requires improvement.
PURPOSE: The purpose of this clinical study was to formulate a custom-made, 2-color chewing gum for the mixing ability test and to develop an image-processing method for color mixing analysis.
MATERIAL AND METHODS: Specimens of red-green (RG) chewing gum were prepared as a test food. Twenty dentate participants (10 men, 10 women; mean age 21 years) took part in this study. Each participant masticated 1 piece of RG gum for 3, 6, 9, 15, and 25 cycles, and this task was repeated 3 times consecutively (total n=15 for each participant). The boluses were retrieved and flattened to 1-mm-thick wafers and scanned with a flatbed scanner. The digital images were analyzed using ImageJ software equipped with a custom-built plug-in to measure the geometric dispersion (GD) of baseline red segment. The predictive criterion validity of this method was determined by correlating GD to the number of mastication cycles. The hardness and mass of RG chewing gum were measured before and after mastication. Hardness loss (%) and mass loss (%) were then calculated and compared with those of a commercially available chewing gum.
RESULTS: The 2-way repeated-measures ANOVA with post hoc Bonferroni test showed that GD was able to discriminate among the groups of different numbers of mastication cycles (P

Matched MeSH terms: Image Processing, Computer-Assisted*
The hyoid bone in malay infants with cleft lip and palate

Rajion ZA, Townsend GC, Netherway DJ, Anderson PJ, Hughes T, Shuaib IL, et al.

Cleft Palate Craniofac J, 2006 Sep;43(5):532-8.
PMID: 16986987

To compare morphological and positional variations of the hyoid bone in unoperated infants with cleft lip and palate (CL/P) with those in noncleft infants.

Matched MeSH terms: Image Processing, Computer-Assisted

Filters

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

External Links