2022
DOI: 10.1155/2022/3297316
|View full text |Cite|
|
Sign up to set email alerts
|

Effective CBMIR System Using Hybrid Features-Based Independent Condensed Nearest Neighbor Model

Abstract: In recent times, a large number of medical images are generated, due to the evolution of digital imaging modalities and computer vision application. Due to variation in the shape and size of the images, the retrieval task becomes more tedious in the large medical databases. So, it is essential in designing an effective automated system for medical image retrieval. In this research study, the input medical images are acquired from new Pap smear dataset, and then, the visible quality of acquired medical images i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 34 publications
(9 citation statements)
references
References 36 publications
0
9
0
Order By: Relevance
“…The CT scan images are categorized as normal and abnormal during the classification step. The SVM [9][10][11][12] algorithm was employed to identify cancer in different places of lung CT images. Supervised learning SVM classifiers analyze the input data and classify it in accordance with a pattern.…”
Section: Methodsmentioning
confidence: 99%
“…The CT scan images are categorized as normal and abnormal during the classification step. The SVM [9][10][11][12] algorithm was employed to identify cancer in different places of lung CT images. Supervised learning SVM classifiers analyze the input data and classify it in accordance with a pattern.…”
Section: Methodsmentioning
confidence: 99%
“…Hirald Dwaraka Praveena et al (9) In this study, new Pap smear dataset is used as the source for the input medical images, and image normalization technique is used to enhance the visible quality of the obtained medical images, by extracting the Color and Texture feature vectors using a Modified Local Binary Pattern (MLBP) and a Histogram of directed Gradients (HOG), the semantic gap between the feature vectors is greatly reduced. Then the obtained feature vectors are fed to the Hybrid feature based Independent Condensed Nearest Neighbor classifier (ICNN) to classify model almost achieved 98.88% of retrieval accuracy.…”
Section: Literature Surveymentioning
confidence: 99%
“…The study of medical images is easy now to identify these images properly and accurately (8) . Due to variation in the shape and size of the images, the retrieval task becomes more monotonous in the large medical databases (9) . A difficult task for people needed in various sectors, especially the healthcare industry is the accuracy and latency of the CBIR technology on cloud storage servers.…”
Section: Introductionmentioning
confidence: 99%
“…Image segmentation is highly referred technique for exact separation of image for the accurate diagnosis [18]. The hybrid feature-based ICNN model was proposed and obtained significant performance in CBMIR by means of recall, precision, accuracy, f-score, and specificity compared to other classifiers such as LSTM, DNN, and CNN [19]. Wavelet transform has been used in an attempt has to generate the ECG signal wave forms using MATLAB software then QRS complex were detected and then each complex are used to find the individual peaks like P and Daubechies wavelet has preferred since the scaling functions are similar to the shape of the ECG signal [20].…”
Section: Literature Surveymentioning
confidence: 99%