• Nu S-Au Găsit Rezultate

View of Detection of Sickle Cell Anemia from Microscopic Blood Images Using Different Local Adaptive Thresholding Techniques

N/A
N/A
Protected

Academic year: 2022

Share "View of Detection of Sickle Cell Anemia from Microscopic Blood Images Using Different Local Adaptive Thresholding Techniques"

Copied!
16
0
0

Text complet

(1)

Detection of Sickle Cell Anemia from Microscopic Blood Images Using Different Local Adaptive Thresholding Techniques

D.Saravanan1, S.Rajasekaran2

,

Dr. D,Stalin David3, P.Hemalatha4, Dr.U.Palani5 Associate Professor1,Department of CSE, IFET College of Engineering, Villupuram,

Research Student2, Department of CSE, IFET College of Engineering, Villupuram, Assistant Professor 3,Department of IT, Annamalai University, Chidambaram, Senior Assistant Professor 3,Department of IT, Annamalai University, Chidambaram,

Professor5, Department of ECE, IFET College of Engineering, Villupuram, [email protected]1, [email protected]2, [email protected]3,

[email protected]4, [email protected]5 Abstract-

Modern image analysis methods are essential in treating and classification a range of medical abnormalities in today's world. There are a few points to bear in mind because once analyzing any image. The threshold phase is essential. Several scientists report their findings. Based on the situation, different image threshold models have been developed. Form of the requests Adaptive thresholding is a valuable diagnostic method for medical pictures of disease. This analysis uses adaptive image thresholding techniques. They are used to treat blood photos of patients who have sickle cell anaemia disease (SCD). The main focus of this paper is classification. Using Those methods is used to diagnose sickle cell Anaemia from blood smear images in the picture threshold and compare analysis.

Keywords: Adaptive thresholding, Sickle cell Disease, Segmentation, Red blood cells

I. INTRODUCTION.

The optimization phase is critical in medical photographs. When segmenting an image, it divides it into input image regions. It is impossible to diagnose an infection without using the proper segmentation procedure. Using the image processing method, a video object is a quick and easy way to segment an image—the process of identifying pixel values into one of two (or more) groups known as thresholding. Global and responsive (or local) thresholding are the two types of edge detection methods in general. For segmentation, edge detection is a thresholding technique in which a single pixel value is included in an image.

Iron-rich foods help to keep red blood cells in good shape. Vitamins are also required for the healthy formation of red blood cells. Vitamins B-2, B-12, and B-3 were amongst them and can be added to foods like eggs, pretty much the entire grains, and bananas. Folate is also advantageous. It can be found in probiotic foods, salted vegetables and fruits, orange juice, and

(2)

veggies. Red blood cells develop into a versatile oval, biconvex discs. To enhance red blood cell processing power, they lack a target cell and most organisms; they can be thought of as ferritin sacks with a cytoplasm as the sack. Every second, about 2.4 million new hepatocytes are formed in adults. [number four] Macrophages recycle the cells after forming in the stem cells and accumulate in the body for 100–120 days. Each contends about 60 seconds (one minute). (No. 5) About nearly two - thirds of the body cells are red blood cells, which number in the trillions. [the sixth] (nine) [nine].

II.LITERATURE REVIEW

In several situations and for a range of functions, teaching experts' excellence must conduct optical microscopy of a quality rate and well-stained blood smear. A thin blood scan is used to (a) verifying the identified computerized haematology results and (b) determine if a manual variability leukocyte count is required. A blood smear evaluation variance leukocyte count with blood testing (CBC) provides a complete hematologic picture of the case from a phenotypic expression standpoint. Blood malign analysis, with or without perception, ensures that no clinically essential results are missed.

Anaemia affects a large percentage of the population, especially the elderly. In many people, anaemia has been linked to reduced longevity and fitness quality of life. On the other hand, data on these impacts in the typical community is scarce. Moreover, there has been no agreement on the best way to describe anaemia. These issues were investigated using statistical analysis, scores from such a fitness quality of life list of questions (RAND-36), and haemoglobin accumulation from 138670 Lifelines cohort participants aged 18 to 93. Anaemia, which was further those most in people involved over the age of 60, was described using World Health Organization standards. Anaemia was discovered in 5510 (4.0%) of the 138670 participants and 516 (2.8%) of the 18667 people over 60. Anaemia had no influence on global sustainability and only a minor effect on wellness quality in persons under 60. In people over the age of 60, anaemia, on the other hand, significantly reduced survival chances and wellness quality of life.

The lower wellness quality of life was most noticeable in the performance is enhanced subscales.

Saliency is an appropriate perceptual cue at different stages of resolution. Aspects of saliency include symmetry, consistency, and closure. These characteristics are difficult to detect due to noise, size variability, and a lack of information. This paper introduces the incremental voting method that also uses focused kernels to deduce saliency as it applies to symmetry. The

(3)

technique's unique feature is the kernel terrain, which is an iterative process refined and reoriented.

Urine microscopy is a moment procedure that requires the technician to exercise extreme caution. So that to provide accurate results for accurate urine sample analysis, microscopic images must be correctly oriented. Similarly, while performing the task, the specialist must avoid contaminating the urine sample, especially during the treatment stage. There should be less human contact to prevent the transmission of contagious diseases. This article focuses on the use of image stabilization on a confocal microscope, as well as the development of an automatic vehicle electron microscopy slide appraiser with action recognition using the Deviation of Laplacian method and Scale Invariant Feature Transform (SIFT)

The author proposed a nonparametric and unprotected method for image differentiation threshold selection. The discriminant criterion selects an ideal threshold to maximize the interpretability of the consequent grey levels groups. The technique is simple, requiring only the zeroth- and first-order accumulated memories of the grey-level graph. The method can easily be applied to problems with multiple thresholds. Several experimental findings also support the method's validity.

For this paper, the watershed algorithm is used in conjunction with an image classification method for red blood cells based on morphological corrosion and the process models' growth. The way first uses 4 and 8 neighbours' structures of conflicting cell significantly affected to monitor the number of previous corrosions, followed by prolonged alternate erosion unit of measure of cells after rust area and the cells' equivalent diameter. The idea of increasing between neurons using the watershed algorithm is used to separate cell images. The characteristics of the red circle are the primary focus of this algorithm; based on the outcome of the experiments,

Blood cell segmentation is critical because it provides an immediate solution. Blood cells, on the other hand, may implement a standard that is difficult to distinguish. Furthermore, accurate overlapping cell recognition can enhance an automated DNA counting system's precision, and this information helps diagnose diseases like anaemia, leukaemia, RBC, WBC, and MCV. Using a Fuzzy system with several input parameters: area, perimeter, and solidity, the paper presents a method for separating overlapped cells and counting RBCs. The current outcomes yield a 91.07 per cent accuracy, with 6.50 per cent over classification and 6.04 per cent

(4)

under variety.

Leukaemia is frequently detected using light microscopic photographs. On the other hand, pathologists' requirements for clinical practice from photos are primarily qualitative and empirical. Even though leukaemia is a leukocyte cancer, research shows that it causes differential expression in red blood cells (RBCs). It was discovered by looking at super images of RBCs. A computational analysis of ultra-structural images has recently aided in finding underlying mechanisms of advancements in leukaemia patients. The application of light microscopic image analysis to this method could help become much more clinically viable.

III. METHODOLOGY

Among the essential steps that can be taken to anticipate different diseases is to identify and analyze RBC counts. Designers decided to use an image processing technology to reduce the RBC count even though image processing implementations are freeware and blood samples can be obtained in various ways. To create a one-of-a-kind method, the proposed RBC count filtration system utilizes a novel image processing technique. Based on resolution and image quality, the image pixels have been through a sequence of computer-controlled computer vision steps before being intercepted as circular artefacts. The new technique includes morphological image processing, colour threshold technique, and area segmentation.

Preprocessing:

This process includes reading the input training sample, adjusting the image if needed, and grayscale transformation.

Colour of the threshold:

In the Color Threshold app, feature selection can be an evolving procedure. To see if one binary image isolates a different item better than someone else, try segregating the image in one of the app's sponsored colour spaces. By choosing a region in the input image, you can perform an analysis system in any assisted colour spaces.

(5)

Using the Color Threshold App, create a mask image.

This chapter of the example demonstrates how to generate a mask image after classification. The segmented image, as well as the MATLAB code for creating the motion pictures, are also available.

Morphological Image Processing:

Binary images can suffer from several flaws. Sound and crispness distort the numeric regions created by simplistic thresholding in particular. By considering the image's shape and texture, phenotypic computer vision seeks to eradicate the above flaws. These methods may be beneficial to greyscale images. Morphological object detection is a set of non-linear operations concerned with the texture or morphology of feature representation. Morphological operations, according to Wikipedia, are well suitable for the retrieval of binary images because they rely primarily on the persuasive precedent of pixel values rather than their data variables.

(6)

MORPHOLOGICAL FILTERING:

In the MF of source images, chemical processes like trying to open are handled as filters.

It's feasible that they'll be used to filter shapes. For example, spreading with a disc originated from various features that helped smooth corners from the inside, even when shuttering with a disc softens corners the outside out. However, these activities can also extract any information from the shorter image in length than the intensity value, such as opening, which scales the colour mask to the intensity value's size. Smaller structures are stopped and erased from the filter's source images, which only passes these other parts of an idea that complement the transformation function.

Dilation (represented by the symbol ⊕ )

When a person's eyes dilate, this phenomenon occurs. The assigned structuring element is used to probe and expand the shapes contained in the input image. In this case, it acts as a maximum local filter. The polar opposite of erosion is dilation. It adds a layer of pixels to the inner and outer borders of the region. The output pixel's value is equal to the sum of all pixels' importance in the immediate vicinity. A pixel is set to 1 if all of its neighbours have the same value in a binary image. Morphological dilation makes artefacts more visible and fills in small gaps. The term "neighbourhood" refers to a group of people who live together. A pixel is set to 0 if all of its neighbours have the same value in a binary image.

Erosion (represented by the symbol ⊖)

The dilation is in the opposite direction. The designated potentially devastating is used to probe and reduce the forms in the input image. In this case, it acts as a minimum natural filter.

Furthermore, by discarding a layer with pixels from both the anterior and posterior regions, the formulating components help decrease an image's size. Erosion and minor details can be used to fill in holes but instead gaps between different areas. That is, the output pixel's voltage is

(7)

approximate to the highest number of all pixels nearby. A pixel is set to 0 if all of its neighbours and friends have the same value in a source image. Morphological erosion erodes islands and small objects away, leaving only considerable remains.

Opening (Ao B=(A⊖B)⊕B)

The same formulating factor is often used in both operational activities. The morphological opening is a method of removing nearby particles from an image while preserving the thickness of the larger objects in a snap. After the eroded image has been eroded, the entrance procedure dilates it.

2. Closing (A • B=(A⊕B)⊖B)

The closing activity dilates a photograph before diminishing it, and both procedures use the same organizing feature. Morphological closure is a strategy for trying to fill small holes in an image while preserving the objects' shape and size.

. WBC Extraction:

The procedure includes layering thought the whole blood over a density gradient medium, solvent extraction, separation of the eosinophil layer, and lysis of residual erythrocytes.

The tissues are scrubbed, recorded, and cells were suspended in the buffer to achieve the target

(8)

concentration.

RBC Count Extraction

An evaluation of the crashed red blood cells should be performed to improve accuracy.

The findings show that fully automated red blood cell removal and numbering begin with image processing, followed by single blood cell removal and eventually red blood cell estrangement, all with 74% or better consistency.

IV. RESULTS AND DISCUSSION

The ten-sample recognition system is fed into another thresholding technique mentioned above, and the identification results are compared. Figure 2 shows an example of a source sample image from the project's database. Figures 3 to 6 depict the segmented version of Figure 2 after colour the selling techniques have been applied. MORPHOLOGY FILTERING The value of the metric is reflected in these figures. each cell in the blood image to be able to tell them apart

Fig. 1 input image

Fig. 2 Segmented image Enhanced thresholding technique

(9)

Fig. 3 Segmented image wbc extraction technique

Fig. 4 Segmented image binarization technique

(10)

V. CONCLUSION

The retrieval of RBC count from the disease that can lead was effectively applied using Morphological clustering and colour threshold using MATLAB software 2017 version and Color threshold Application as an Add-on installed with 2017 version. In the graph above, the results are depicted and checked.

VI. REFERENCES

[1] Mehrotra S, Edmonds M, Lim RK. False elevation of carboxyhemoglobin: a case report.

PediatrEmerg Care 2011;27:138_40.

[2] Gulati G, Song J, Florea AD, Ging J. Purpose and criteria for blood smear scan, blood smear examination and blood smear review. Ann LabMed 2013;33:1_7.

[3] Endres HG, Wedding U, Pittrow D, Thiem U, et al. Prevalence of anaemia in elderly patients in primary care: impact on 5-year mortality risk and difference between men and women. Curr Med Res Opin2009;25:1143_58.

[4] Castel R, Tax MG, Droogendijk J, Leers MP, et al. Thetransferrin/log(ferritin) ratio: a new tool for diagnosing iron-deficiency anaemia. Clin Chem Lab Med 2012;50:1343_9.

[5] Goddard AF, James MV, McIntyre AS, Scott BB, et al. Guidelines for the management of iron deficiency anaemia. Gut 2011;60:1309_16.

[6] Parvin, B., Yang, Q., Han, J., Chang, H., Rydberg, B., Barcellos-Hoff, M.H.: Iterative voting for inference of structural saliency and characterization of subcellular events.

IEEE Transactions on ImageProcessing 16 (2007) 615–623

[7] Kothari, S., Chaudry, Q., Wang, W.D.: Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques. IEEE International Symposium on Biomedical Imaging(2009) 795–798

(11)

[8] Dela Cruz J.C. et al., "Determination of blood components (WBCs, RBCs, and Platelets) count in microscopic images using image processing and analysis," 2017IEEE 9th International Conference onHumanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), Manila, 2017, pp. 1-7.

[9] Quiñones, V.V., Macawile, M.J., Ballado, A., Dela Cruz, J.C., Caya, M.V.," Leukocyte segmentation and counting based on microscopic blood images using HSV saturation component with blob analysis," 2018 3rd International Conference on Control and Robotics Engineering, ICCRE 2018, pp 254-258.

[10] V.V., Macawile, Quiñones, M.J., Ballado, A., Dela Cruz, J.C., Caya, M.V.," White blood cell classification and counting using convolutional neural network," 2018 3rd International Conference on Control and robotics Engineering, ICCRE 2018, pp 259-263.

[11] OTSU N., A threshold selection method from grey-level histograms, IEEE Transactions on System, Man and Cybernetics, Vol. 9, No. 1,1979, pp. 62–66.

[12] Meyer, Fernand, "Topographic distance and watershed lines," SignalProcessing, Vol. 38, July 1994, pp. 113-125.[13] van den Boogaard, R, and R. van Balen, "Methods for FastMorphological Image Transforms Using Bitmapped Images," ComputerVision, Graphics, and Image Processing: Graphical Models and ImageProcessing, Vol. 54, Number 3, pp. 254-258, May 1992.

[13] Gonzalez, R. C., R. E. Woods, and S. L. Eddins, Digital ImageProcessing Using MATLAB, Gatesmark Publishing, 2009.

[14] J. Huang, "An improved algorithm of overlapping cell division," International Conference on Intelligent Computing and IntegratedSystems. IEEE, 2010, pp. 687–691.

[15] D Stalin David, 2020, 'An Intellectual Individual Performance Abnormality Discovery System in Civic Surroundings' International Journal of Innovative Technology and Exploring Engineering, Volume 9, Issue 5, PP.2196-2206.

[16] D Stalin David, 2020, 'Machine learning for the prelude diagnosis of dementia,' International Journal of Pharmaceutical Research, Volume 13, Issue 3, PP.2329-2335.

[17] Stalin David D, Saravanan D, 2020, 'Multi-perspective DOS Attack Detection Framework for Reliable Data Transmission in Wireless Sensor Networks based on Trust',

(12)

International Journal of Future Generation Communication and Networking, Volume 13, Issue 4, PP.1522–1539.

[18] J. K. S and D. S. David, "A Novel Based 3D Facial Expression Detection Using Recurrent Neural Network," 2020 International Conference on System, Computation, Automation and Networking (ICSCAN), Pondicherry, India, 2020, pp. 1-6, DOI:

10.1109/ICSCAN49426.2020.9262287.

[19] Stalin David D, Saravanan D, "Enhanced Glaucoma Detection Using Ensemble-based CNN and Spatially Based Ellipse Fitting Curve Model," Solid State Technology, Volume 63, Issue 6, PP.3581-3598.

[20] Stalin David D, Saravanan M, Jayachandran A, "Deep Convolutional Neural Network- based Early Diagnosis of multi-class brain tumour classification," Solid State Technology, Volume 63, Issue 6, PP.3599-3623.

[21] R.Parthiban, Dr.K.Santhosh Kumar, Dr R.Sathya, D.Saravanan," A Secure Data Transmission And Effective Heart Disease Monitoring Scheme Using Mecc And Dlmnn In The Cloud With The Help Of IoT," International Journal of Grid and Distributed Computing, ISSN: 2005 – 4262, Vol. 13, No. 2, (2020), pp. 834 – 856.

[22] R.Bhavya, G.I.Archanaa, D.Karthika, D.Saravanan," Reflex Recognition of Tb Via Shade Duplicate Separation Built on Geometric Routine," International Journal of Pure and Applied Mathematics 119 (14), 831-836.

[23] D Saravanan, R Bhavya, GI Archanaa, D Karthika, R Subban," Research on Detection of Mycobacterium Tuberculosis from Microscopic Sputum Smear Images Using Image Segmentation," 2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC).

[24] D Saravanan, R Parthiban," Automatic Detection of Tuberculosis Using Color Image Segmentation and Statistical Methods," International Journal of Advance Research in Science and Engineering, Volume 6, Issue 10.

[25] D Stalin David, 2020, 'Diagnosis of Alzheimer's Disease Using Principal Component Analysis and Support Vector Machine, International Journal of Pharmaceutical Research, Volume 12, Issue 2, PP.713-724.

[26] Jaswanth KS, Dr. D. Stalin David, "A Novel Based 3d Facial Expression Detection Using Recurrent Neural Network", International Journal of Scientific Research in Computer

(13)

Science, Engineering and Information Technology (IJSRCSEIT), ISSN: 2456-3307, Volume 6 Issue 2, pp. 48-53, March-April 2020.

[27] U.Palani, D.Saravanan, R.Parthiban, S.Usharani," Lossy Node Elimination Based on Link Stability Algorithm in Wireless Sensor Network," International Journal of Recent Technology and Engineering (IJRTE), Volume 7, Issue 6S5.

[28] S.G.Sandhya, D.Saravanan, U.Palani, S.Usharani," Handover Priority to the Data at Knob Level in Vanet," International Journal of Recent Technology and Engineering (IJRTE), Volume 7, Issue 6S5.

[29] D.Saravanan R.Parthiban, U.Palani S.G.Sandhya," Sheltered and Efficient Statistics Discrimination for Cluster-Based Wireless Antenna Networks," International Journal of Recent Technology and Engineering (IJRTE), Volume 7, Issue 6S5.

[30] D.Saravanan, Dr. K.Santhosh Kumar, R.Sathya, U.Palani, "An IoT Based Air Quality Monitoring And Air Pollutant Level Prediction System Using Machine Learning Approach – Dlmnn," International Journal of Future Generation Communication and Networking, Vol. 13, No. 4, (2020), pp. 925–945.

[31] Raghu Raman D, Saravanan D, Nivedha R," An Efficacious E-Portal for Rancher to Buy Seeds and Humus", International Journal of Recent Technology and Engineering (IJRTE), Volume-

8, Issue-1S5, June 2019.

[32] M.Sudha, D.Saravanan, S.Usharani," Security Improvement of Dropper Elimination Scheme for IoT Based Wireless Networks," International Journal of Engineering Trends and Technology (IJETT), Volume-45 Number3 -March 2017.

[33] K. Gayathri, D.Saravanan," An Innovative IoT security Enhancing Schema Based Gamed Theory Decryption Percentage," International Journal of Advanced Research in Science and Technology, Volume 6, Issue2, 2017, pp. 666-671.

[34] E.Kowsalya, D.Saravanan, R.Parthiban," Energy-Aware Resource Allocation for Throughput Maximized IoT Network," International Journal of Computer Trends and Technology (IJCTT) – Volume 45 Issue 2- March 2017.

[35] D Saravanan, J Feroskhan, R Parthiban, S Usharani, "Secure Violent Detection in Android Application with Trust Analysis in Google Play," Journal of Physics:

Conference Series 1717 (1), 012055.

(14)

[36] D Saravanan, E Racheal Anni Perianayaki, R Pavithra, R Parthiban," Barcode System for Hotel Food Order with Delivery Robot," Journal of Physics: Conference Series 1717 (1), 012054.

[37] D Raghu Raman, S Gowsalya Devi, D Saravanan," Locality based violation vigilant system using a mobile application," 2020 International Conference on System, Computation, Automation and Networking (ICSCAN-IEEE).

[38] R Parthiban, R Ezhilarasi, D Saravanan, "Optical Character Recognition for English Handwritten Text Using Recurrent Neural Network," 2020 International Conference on System, Computation, Automation and Networking (ICSCAN-IEEE).

[39] R Parthiban, V Abarna, M Banupriya, S Keerthana, D Saravanan," Web Folder Phishing Discovery and Prevention with Customer Image Verification," 2020 International Conference System, Computation, Automation and Networking (ICSCAN-IEEE).

[40] K Dhivya, P Praveen Kumar, D Saravanan, M Pajany," Evaluation of Web Security Mechanisms Using Vulnerability & Sql Attack Injection," International Journal of Pure and Applied Mathematics, Volume 119, Issue 14, 2018.

[41] D Saravanan, R Parthiban, S Usharani, K Santhosh Kumar," Furtive Video Recorder Using Intelligent Vehicle with the Help of Android Mobile," International Journal of Pure and Applied Mathematics, Volume 119, Issue 14, 2018.

[42] K Dheepa, D Saravanan, R Parthiban, K Santhosh Kumar," Secure And Flexible Data Sharing Scheme Based On Hir-Cp-Abe For Mobile Cloud Computing," International Journal of Pure and Applied Mathematics, Volume 119, Issue 14, 2018.

[43] D.Saravanan S. Usharani," Survey on Security-Based Novel Context-Aware Mobile Computing Scheme Via Crowdsourcing," International Journal of Scientific Research in Computer Science, Engineering and Information Technology.

[44] S. Usharani, D.Saravanan," Security Improvement of Dropper Elimination Scheme for IoT Based Wireless Networks," International Journal of Engineering Trends and Technology.

[45] R Parthiban, S Usharani, D Saravanan," Survey of Security Improvement of Dropper Elimination Scheme for IoT Based Wireless Networks," International Journal of Engineering Trends and Technology (IJETT).

(15)

[46] Jayachandran, A., and D. Stalin David. "Textures and Intensity Histogram Based Retinal Image Classification System Using Hybrid Colour Structure Descriptor." Biomedical and Pharmacology Journal, vol. 11, no. 1, 2018, p. 577+. Accessed 12 Feb. 2021.

[47] D. Stalin David, 2019, "Parasagittal Meningioma Brain Tumor Classification System based on MRI Images and Multi-Phase level set Formulation," Biomedical and Pharmacology Journal, Vol.12, issue 2, pp.939-946.

[48] D. S. David and A. Jeyachandran, "A comprehensive survey of security mechanisms in healthcare applications," 2016 International Conference on Communication and Electronics Systems (ICCES), Coimbatore, 2016, pp. 1-6, DOI:

10.1109/CESYS.2016.7889823.

[49] Stalin David, D., Jayachandran, A. A new expert system based on hybrid colour and structure descriptors and machine learning algorithms for early glaucoma diagnosis.

Multimed Tools Appl 79, 5213–5224 (2020). https://doi.org/10.1007/s11042-018-6265-1.

[50] D Stalin David, A Jayachandran, 2018, Robust Classification of Brain Tumor in MRI Images using Salient Structure Descriptor and RBF Kernel-SVM, TAGA Journal of Graphic Technology, Volume 14, Issue 64, pp.718-737.

[51] D Stalin David, 2016, Robust Middleware based Framework for the Classification of Cardiac Arrhythmia Diseases by Analyzing Big Data, International Journal on Recent Researches In Science, Engineering & Technology, 2018, Volume 4, Issue 9, pp.118-127.

[52] David, D.S. and Y. Justin, 2020. A Comprehensive Review on Partition of the Blood Vessel and Optic Disc in Retinal Images. Artech J. Eff. Res. Eng. Technol., 1: 110-117.

[53] D. Stalin David and A.A. Jose, 2020. Retinal image classification system for diagnosis of diabetic retinopathy using SDC Methods. Artech J. Eff. Res. Eng. Technol., 1: 87-93.

[54] D. Stalin David and T. Joseph George, 2020. Identity-based Sybil attack detection and localization. Artech J. Eff. Res. Eng. Technol., 1: 94-98.

[55] David, D.S. and L. Arun, 2020. Classification of brain tumour type and grade using MRI texture and shape in a machine learning scheme. Artech J. Eff. Res. Eng. Technol., 1: 57- 63.

[56] David, D.S., 2020. Retinal image classification system for diagnosis of diabetic retinopathy using morphological edge detection and feature extraction techniques. Artech J. Eff. Res. Eng. Technol., 1: 28-33.

(16)

[57] David, D.S., 2020. A novel specialist system based on hybrid colour and structure descriptors and machine learning algorithms for early diabetic retinopathy diagnosis.

Artech J. Eff. Res. Eng. Technol., 1: 50-56.

[58] David, D.S. and M. Samraj, 2020. A comprehensive survey of emotion recognition system in facial expression. Artech J. Eff. Res. Eng. Technol., 1: 76-81.

[59] David, D.S. and L. Arun, 2020. Multi-view 3D face renovation with deep recurrent neural networks. Artech J. Eff. Res. Eng. Technol., 1: 64-68.

[60] David, D.S. and S. Namboodiri, 2020. Improvement of a framework for the grouping of CA diseases by investigating big data. Artech J. Eng. Appl. Technol., 1: 7-14.

[61] D. Jayakumar; Dr.U. Palani; D. Raghuraman; Dr.D. StalinDavid; D. Saravanan; R.

Parthiban; S. Usharani. "CERTAIN INVESTIGATION ON MONITORING THE LOAD OF SHORT DISTANCE ORIENTEERING SPORTS ON CAMPUS BASED ON EMBEDDED SYSTEM ACCELERATION SENSOR. " European Journal of Molecular

& Clinical Medicine, 7, 9, 2021, 2477-2494.

[62] R. Parthiban; S. Usharani; D. Saravanan; D. Jayakumar; Dr.U. Palani; Dr.D. StalinDavid;

D. Raghuraman. "PROGNOSIS OF CHRONIC KIDNEY DISEASE (CKD) USING HYBRID FILTER WRAPPER EMBEDDED FEATURE SELECTION METHOD. "

European Journal of Molecular & Clinical Medicine, 7, 9, 2021, 2511-2530.

[63] Dr.U. Palani; D. Raghuraman; Dr.D. StalinDavid; R. Parthiban; S. Usharani; D.

Jayakumar; D. Saravanan. "AN ENERGY-EFFICIENT TRUST-BASED SECURE DATA SCHEME IN WIRELESS SENSOR NETWORKS. " European Journal of Molecular & Clinical Medicine, 7, 9, 2021, 2495-2510.

[64] Dr. D. Stalin David; R. Parthiban; D. Jayakumar; S. Usharani; D. RaghuRaman; D.

Saravanan; Dr.U. Palani. "MEDICAL WIRELESS SENSOR NETWORK COVERAGE AND CLINICAL APPLICATION OF MRI LIVER DISEASE DIAGNOSIS. " European Journal of Molecular & Clinical Medicine, 7, 9, 2021, 2559-2571.

[65] Dr.G.Suresh, Dr.A.Senthil Kumar, Dr.S.Lekashri, Dr.R.Manikandan. (2021). Efficient Crop Yield Recommendation System Using Machine Learning For Digital Farming.

International Journal of Modern Agriculture, 10(01), 906 - 914. Retrieved from http://www.modern-journals.com/index.php/ijma/article/view/688

Referințe

DOCUMENTE SIMILARE

Sukavanam, "Human Action Recognition from Motion Trajectory using Fourier Temporal Features of Skeleton Joints," 2018 International Conference on Advances in Computing

Classification and Detection of Brain Tumor through MRI Images Using Various Transfer Learning Techniques.. Amit Thakur 1 , Pawan Kumar

Vijayalakshmi M M, Melanoma Skin Cancer Detection using Image Processing and Machine Learning, International Journal of Trend in Scientific Research and

Viola Jones Algorithm tested with single Person image from Pointing’04 dataset Face detection from the randomly selected images. Randomly 20 images from Pionting’04 dataset were

Feature extraction mainly refers to the geometric measurements of the leaf image obtained. The three features such as colour, texture and shape-based features are

Classification of Plaque in Carotid Artery Using Intravascular Ultrasound Images (IVUS) by Machine Learning

Multi-Level Thresholding for Image Segmentation on Medical Images Using Multi Otsu and Sine Cosine Optimization Algorithm.. Erukala Mahender 1* ,

The projected framework first and foremost individuates inside the blood picture the leucocytes from the others platelets, at that point it chooses the white cell cells