Comparative Analysis of Fractional Order Calculus in Image Processing

Heena, Ayesha; Biradar, Nagashettappa; Maroof, Najmuddin M.

doi:10.1109/icait47043.2019.8987396

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…K-nearest neighbors on the other hand, is efficient and can be implemented easily as per the user needs, [17] but the limiting factor of this algorithm is the computational speed is very less when the number of data sets increases, which also interprets the computational speed, is quite high for the fewest amount of data for the processing. This KNN algorithm operates with the basic principle of the amount of weights or the calculated distance among the query and the selective examples in the data set by the specific number which is variable defined as 'k', and this 'k' is the closest among the query, [9,19,20] then the selection will be done on the relevant frequency label of the data for the classification of pixel in the image data or it identifies the average labels for the regression operations, [21,22] in the regression based operation it can be quoted that the selection of the suitable 'k' for the required data serve for the best of the 'k' states which will be the best one for the exchange and selection of pixel data [6,7]. Whereas the KNN algorithm is the best for the less amount of the data pixels for the query and processing [8,13].…”

Section: Methodsmentioning

confidence: 99%

Machine learning based biomedical image processing for echocardiographic images

Heena¹,

Biradar²,

Maroof

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

The popularity of Artificial intelligence and machine learning have prompted researchers to use it in the recent researches. The proposed method uses K-Nearest Neighbor (KNN) algorithm for segmentation of medical images, extracting of image features for analysis by classifying the data based on the neural networks. Classification of the images in medical imaging is very important, KNN is one suitable algorithm which is simple, conceptual and computational, which provides very good accuracy in results. KNN algorithm is a unique user-friendly approach with wide range of applications in machine learning algorithms which are majorly used for the various image processing applications including classification, segmentation and regression issues of the image processing. The proposed system uses gray level co-occurrence matrix features. The trained neural network has been tested successfully on a group of echocardiographic images, errors were compared using regression plot. The results of the algorithm are tested using various quantitative as well as qualitative metrics and proven to exhibit better performance in terms of both quantitative and qualitative metrics in terms of current state -of-the-art methods in the related area. To compare the performance of trained neural network the regression analysis performed showed a good correlation.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine learning based biomedical image processing for echocardiographic images

Heena¹,

Biradar²,

Maroof

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Fractional calculus is widely used in research foundation in different domains such as engineering, computer science and others [1]. It is a well-known fact, that Fractional calculus is a method that results from the function to a non-integer order.…”

Section: Introductionmentioning

confidence: 99%

Image Enhancement Using Adaptive Fractional Order Filter

Heena¹,

Biradar²,

Maroof³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Image enhancement is an important preprocessing task as the contrast is low in most of the medical images, Therefore, enhancement becomes the mandatory process before actual image processing should start. This research article proposes an enhancement of the model-based differential operator for the images in general and Echocardiographic images, the proposed operators are based on Grunwald-Letnikov (G-L), Riemann-Liouville (R-L) and Caputo (Li & Xie), which are the definitions of fractional order calculus. In this fractional-order, differentiation is well focused on the enhancement of echocardiographic images. This provoked for developing a non-linear filter mask for image enhancement. The designed filter is simple and effective in terms of improving the contrast of the input low contrast images and preserving the textural features, particularly in smooth areas. The novelty of the proposed method involves a procedure of partitioning the image into homogenous regions, details, and edges. Thereafter, a fractional differential mask is appropriately chosen adaptively for enhancing the partitioned pixels present in the image. It is also incorporated into the Hessian matrix with is a second-order derivative for every pixel and the parameters such as average gradient and entropy are used for qualitative analysis. The wide range of existing state-of-the-art techniques such as fixed order fractional differential filter for enhancement, histogram equalization, integer-order differential methods have been used. The proposed algorithm resulted in the enhancement of the input images with an increased value of average gradient as well as entropy in comparison to the previous methods. The values obtained are very close (almost equal to 99.9%) to the original values of the average gradient and entropy of the images. The results of the simulation validate the effectiveness of the proposed algorithm.

show abstract