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

Praveena, Hirald Dwaraka; Guptha, Nirmala S; Kazemzadeh, Afsaneh; Parameshachari, B. D.; Hemalatha, K.

doi:10.1155/2022/3297316

Cited by 34 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

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%

Automatic recognition of lung tumor using convolutional neural networks

Praveena¹,

Pavan²,

Rajani³

et al. 2023

View full text Add to dashboard Cite

The unchecked proliferation of abnormal cells in the lung is known as lung cancer, and it is one of the major causes of death globally. The most accurate way for finding malignant lung nodules is a thorax Computed Tomography (CT) scan. A spherical lesion called a lung nodule can either be malignant or not. Lung cancer appears as rounded, white shadow nodules on the CT scan. The candidate ROIs are calculated using existing method and some blood vessels are removed using rule-based methods based on the candidate ROIs' shape features. Next, the candidate ROIs' remaining grey and texture features are calculated, and are given to the classifier to categorize the candidates. The rule-based technique has no omissions, according to experimental results, however the misclassification probability is too high. Therefore, in the proposed method, by computing the texture features from the Grey Level Co-occurrence Matrix (GLCM) in the wavelet domain, the nodules were identified and CT images were categorized using Convolutional Neural Networks (CNN) into two groups: those with and those without malignant lung nodules. In this work, two classifiers Support Vector Machine (SVM) and CNN are used for the recognized lung cancer image to determine the severity of the condition. Comparisons between SVM and CNN classifiers are done with regard to quality parameters including accuracy and sensitivity.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic recognition of lung tumor using convolutional neural networks

Praveena¹,

Pavan²,

Rajani³

et al. 2023

View full text Add to dashboard Cite

show abstract

“…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%

An Image Classification and Retrieval Hybrid Model for Larger Healthcare Datasets using Deep Learning

Vasudeva,

Chandrashekara

2023

IJST

View full text Add to dashboard Cite

Objectives:The objective of this work is to obtain an efficient medical image retrieval and classification from a larger healthcare datasets using Novel approach. Methods: In this study five different classes of Medical images are taken for input, features are extracted using GLCM (Grey Level Co-occurrence Matrix) by image attributes such as dissimilarity, correlation, homogeneity, contrast, ASM, and energy. The photos are examined at several angles (0, 45, 90, and 135) to extract the characteristics using the layers. The received feature vectors are input into the most often used deep learning models Artificial Neural Networks (ANN) and Convolution Neural Networks (CNN) for image classification. Then CNN model is integrated with a deep learning model based on Long-Short Term Memory (LSTM), which incorporates additional layers into its structure and works on large datasets. Further the retrieval performance is improved by Euclidean Distance Technique. Findings: Performance evaluation is performed by comparing and analyzing the experimental findings of proposed methods, ANN, CNN and CNN-LSTM yields the retrieval accuracy of 97.79%, 98.78% and 99.4%. The Precision, Recall and F1-Score are also compared, and they are more accurate when picture classification is performed on larger healthcare datasets. Novelty: The additional feature extraction using GLCM and the proposed hybrid model can extract better medical image features, and achieve higher classification accuracy compared with earlier image classification models.

show abstract

“…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%

Medical Image Forgery Detection By A Novel Segmentation Method With KPCA

V.¹,

Jayalakshmi²,

Kishore³

2022

View full text Add to dashboard Cite

One of the most challenging tasks of recent days is detecting digital image forgery. Effective image processing tools are developed with excellent technology enhancement, making an easy and comfortable process for image forgery. Because of these systems’ misusage, the verification of picture is too difficult. Therefore, image forgery detection uses different techniques according to the requirements of detection, efficiency, and type of forgery. This study proposes an efficient novel segmentation method with Kernel Principal Component Analysis (KPCA) for the detection of image forgery. The Normalized cut (NCut) segmentation technique is used initially to segment the forged image. Then, the KPCA method is used to extract the image’s features. Finally, image authenticity is decided by comparison of clustering regions according to the threshold. In typical conditions of the image, as changes in brightness, shading diminishment, and limited rotation angles, the copied areas are detected accurately by using the described planned strategy. The performance of the proposed system is analyzed using different medical imaging modalities such as computed tomography, magnetic resonance imaging, x-ray and ultra-sonograms. From the comparative results, it is clear that better performance of image forgery detection is achieved by the described algorithm in terms of accuracy, precision, recall, and specificity than other algorithms.

show abstract

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

Cited by 34 publications

References 36 publications

Automatic recognition of lung tumor using convolutional neural networks

Automatic recognition of lung tumor using convolutional neural networks

An Image Classification and Retrieval Hybrid Model for Larger Healthcare Datasets using Deep Learning

Medical Image Forgery Detection By A Novel Segmentation Method With KPCA

Contact Info

Product

Resources

About