Performance Analysis of Texture Image Retrieval in Curvelet, Contourlet, and Local Ternary Pattern Using DNN and ELM Classifiers for MRI Brain Tumor Images

Pandian, A. Anbarasa; Raman, Balasubramanian

doi:10.1007/978-981-10-2104-6_22

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique should be practical in combination with map reduce function for its effectual and precise process. In the present context, as suggested by Pandian and Balasubramanian (2017) [13] the field of digital image gathering have been amplified due to the fast development. In this development, Images are generated in gigabytes levels which are used most particularly generated by using the apparatus of both civilian and military.…”

Section: State Of the Art In Big Data Analytics From Image Dataa Reviewmentioning

confidence: 81%

State of the art in image processing & big data analytics: issues and challenges

Ezhilraman¹,

Srinivasan²

2018

IJET

View full text Add to dashboard Cite

Image processing, in the contemporary domain, is now emerging as a novel and an innovative space in computing research and applications. Today, the discipline of “computer science” may be termed as “image science”, why because in every aspect of computer application, either science or humanities or management, image processing plays a vital role in varied ways. It is broadly now used in all the industries, organizations, administrative divisions; various social organizations, economic/business institutions, healthcare, defense and so on. Image processing takes images as input and image processing techniques are used to process the images and the output is modified images, video, or collection of text, or features of the images. The resultant output by most image processing techniques creates a huge amount of data which is categorized as Big-data. In this technique, bulky information is processed and stored as either structured or unstructured data as a result of processing images through computing techniques. In turn, Big Data analytics for mining knowledge from data created through image processing techniques has a huge potential in sectors like education, government organizations, healthcare institutions, manufacturing units, finance and banking, centers of retail business. This paper focuses on highlighting the recent innovations made in the field of image processing and Big Data analytics. The integration and interaction of the two broad fields of image processing and Big Data have great potential in various areas. Research challenges identified in the integration and interaction of these two broad fields are discussed and some possible research directions are suggested.

show abstract

Section: State Of the Art In Big Data Analytics From Image Dataa Reviewmentioning

confidence: 81%

State of the art in image processing & big data analytics: issues and challenges

Ezhilraman¹,

Srinivasan²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…Table 6 shows that the proposed transfer learning method based on the pretrained EfficientNet‐B5 outperforms other deep models using a DNN [41] or kernel‐based ELM [28] in terms of the best‐case accuracy for fivefold cross‐validation on real MR images. In addition, our method outperforms other models used in transfer learning, such as GoogLeNet [42], VGG19 [44], and ResNet with a randomized neural network [31].…”

Section: Discussionmentioning

confidence: 99%

Transfer‐learning‐based classification of pathological brain magnetic resonance images

Savaş,

Damar

2023

ETRI Journal

View full text Add to dashboard Cite

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state‐of‐art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet‐B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross‐validation and a two‐tier cross‐test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

show abstract

“…For the second stage, the K‐nearest neighbor was used. Pandian & Balasubramanian 13 suggested a method that utilizes local ternary pattern (LTP), contourlet transform, as well as curvelet transform, for extracting features and classifiers like deep neural network (DNN) along with extreme learning machine (ELM). The contourlet transform achieved better results compared to others.…”

Section: Literature Surveymentioning

confidence: 99%

Fractional wavelet transform based diagnostic system for brain tumor detection in MR imaging

Kaushal¹,

Patil²,

Birajdar

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The brain tumor detection is a highly complicated but significant task. The early detection of a brain tumor can increase the survival rate of an individual by providing proper treatment. This work proposes a computer‐aided diagnostic method for brain tumor detection using fractional wavelet transform (FrDWT) with different values of alpha (α) ranging from (0.1‐1), histogram‐based various local feature descriptors, feature selectors, and two classification methods, that is, support vector machine (SVM) as well as artificial neural network (ANN). The brain MR images dataset is taken from BraTS 2015, e‐health laboratory, and Harvard Medical School. The FrDWT and the local feature descriptors used are combined to extract features. Some of the features are selected using Eigenvector centrality and Laplacian Score techniques. The selected features are trained and classified by the two classifiers, SVM and ANN. It is a type of binary classification, so the labels provided to the classifier are named “normal” and “abnormal.” The performance is estimated using parameters like accuracy, sensitivity, precision, specificity, and F1 score. The results of FrDWT are compared with conventional discrete wavelet transform (DWT), and it is observed that FrDWT outperforms DWT at alpha (α) values lower than 0.5.

show abstract

Performance Analysis of Texture Image Retrieval in Curvelet, Contourlet, and Local Ternary Pattern Using DNN and ELM Classifiers for MRI Brain Tumor Images

Cited by 6 publications

References 10 publications

State of the art in image processing & big data analytics: issues and challenges

State of the art in image processing & big data analytics: issues and challenges

Transfer‐learning‐based classification of pathological brain magnetic resonance images

Fractional wavelet transform based diagnostic system for brain tumor detection in MR imaging

Contact Info

Product

Resources

About