An heuristic cloud based segmentation technique using edge and texture based two dimensional entropy

Jaganathan, M.; Sabari, A.

doi:10.1007/s10586-018-1757-3

Cited by 6 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gadget changed into positioned to the take a look at for every photograph to peer if it changed into valid. The detection is feasible [11]. D. Deep learning training: The dataset used for education is proven in Table .1.…”

Section: Resultsmentioning

confidence: 99%

An Application of a Deep Learning Algorithm for Detection of Accidents under bad CCTV Monitoring Conditions in Tunnels using ODTS &R-CNN

Kumar¹,

Reddy²,

Vinnie³

et al. 2022

EJASR

View full text Add to dashboard Cite

In this project, an Object Detection and Tracking System (ODTS) can be brought and used together with a famous deep gaining knowledge of community, the Faster Regional Convolution Neural Network (Faster R-CNN), for Object Detection and a Conventional Object Tracking set of rules for computerized detection and tracking of surprising occasions on CCTVs in tunnels, which can be probable to be (1) Wrong-Way Driving (WWD), (2) Stop, (three) Person out of the automobile in ODTS takes a video body in time as enter and makes use of Object Detection to generate Bounding Box (BBox) findings, evaluating the BBoxes of the modern and former video frames to assign a completely unique ID wide variety to every shifting and diagnosed item. This technique lets in you to display a shifting item in real-time, that's hard to do with conventional item detection frameworks. With a group of occasion pix in tunnels, a deep gaining knowledge of version in ODTS changed into educated to Average Precision (AP) values of zero.8479, zero.7161, and zero.9085 for goal items Car, Person, and Fire, respectively. The ODTS-primarily based totally Tunnel CCTV Accident Detection System changed into then examined the use of 4 twist of fate recordings, one for every twist of fate, the use of a educated deep gaining knowledge of version. As a consequence, inside 10 seconds, the gadget can locate all injuries. The maximum important truth is that once the education dataset grows larger, the detection functionality of ODTS can be robotically multiplied with none adjustments to the programme codes.

show abstract

Section: Resultsmentioning

confidence: 99%

An Application of a Deep Learning Algorithm for Detection of Accidents under bad CCTV Monitoring Conditions in Tunnels using ODTS &R-CNN

Kumar¹,

Reddy²,

Vinnie³

et al. 2022

EJASR

View full text Add to dashboard Cite

show abstract

“…Roads, buildings and bridges are the main structural features obtained from satellite images. Detection of clouds and shadows supports the extraction of these features [12,26]. Different algorithms are available for the extraction of these features, depending on the availability of remotely sensed data.…”

Section: Related Researchmentioning

confidence: 99%

ANFIS Classification based Vegetation Area Detection and Classification using Texture Features

R¹,

N²

2022

Preprint

View full text Add to dashboard Cite

The main objective of this paper is to classify the satellite image into vegetation and nonvegetation area. Satellite image, taken from National Satellite Meteorological Center has been preprocessed with the colour conversion and histogram equalization process, Color conversion technique helps to determine the accurate representation of the area presented in image with less amount of information in the satellite image. Whereas, histogram equalization helps in increasing the intensity level to visualize the different area details of satellite image clearly. Preprocessed images have been processed by feature extraction technique where five different features have been extracted with Gray level coherence matrix (GLCM) and Local Derivative Pattern (LDP) techniques. In this proposed methodology, Adaptive Neuro Fuzzy Inference System (ANFIS) classifier has been used to category the satellite image areas into vegetation and Non-vegetation. Analysis was done based on the parameters such as sensitivity, specificity and accuracy. The results obtained with sensitivity of 96.03%, 94.65 of specificity and 96.08% of accuracy shows that better performance as compared to the existing methodologies available. It will help to maintain climate conditions for crop cultivation, overcoming global warming. Ecological cycle will be balanced and life span of human will be extended based on the vegetation area availability

show abstract

“…Similar sort of paintings is finished in [12] however in comparison different algorithms like SVM alongside the RF. Lakshmi and Kavila [13] proposed a method for CCFD the usage of gadget studying algorithms like logistic regression, selection timber, random wooded area, neural community and Naïve Bayes and [21] Jaganathan, M used a segmentation technique to categorise statistics. The effects found out that RF ought to offer higher overall performance.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Based Solution for an Effective Credit Card Fraud Detection

Kumar¹

2022

EJASR

View full text Add to dashboard Cite

Credit card utilization has been growing with the emergence of e-trade and different programs that permit bills to be made on-line. However, whilst credit score card is stolen or any fraudulent interest takes place, it effects in monetary issues to the cardboard holders. It additionally reasons problems to the provider of playing cards. Therefore, it's far crucial to have a mechanism to stumble on fraudulent on-line transactions. In this regard, there exists many answers as located withinside the literature. One such technique is to have ancient transactions divided into fraudulent and non-fraudulent transactions. This ought to assist educate classifiers to stumble on or suspect fraud transactions. These answers focused spending conduct of clients so that you can stumble on opportunity of fraud. In the present device, statistics mining method is accompanied with random forests to version the conduct of ordinary and fraudulent transactions for credit score card fraud detection. The trouble with the version is that it really works best with dataset this is best tuned. If dataset isn't always good, its overall performance is deteriorated. To conquer this trouble, on this project, a characteristic choice set of rules is proposed to beautify the overall performance of classifier. The proposed device additionally could have comparative have a look at with more than one classifiers like Random Forests and SVM to assess the characteristic choice technique

show abstract

An heuristic cloud based segmentation technique using edge and texture based two dimensional entropy

Cited by 6 publications

References 16 publications

An Application of a Deep Learning Algorithm for Detection of Accidents under bad CCTV Monitoring Conditions in Tunnels using ODTS &R-CNN

An Application of a Deep Learning Algorithm for Detection of Accidents under bad CCTV Monitoring Conditions in Tunnels using ODTS &R-CNN

ANFIS Classification based Vegetation Area Detection and Classification using Texture Features

Machine Learning Based Solution for an Effective Credit Card Fraud Detection

Contact Info

Product

Resources

About