2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) 2018
DOI: 10.1109/icmla.2018.00023
|View full text |Cite
|
Sign up to set email alerts
|

ROI Detection in Mammogram Images Using Wavelet-Based Haralick and HOG Features

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
1
1

Relationship

1
8

Authors

Journals

citations
Cited by 14 publications
(6 citation statements)
references
References 21 publications
0
6
0
Order By: Relevance
“…In this paper, we used the DT and SVM classifiers as they are commonly used in ML techniques. In addition, they proved their efficiency over the other classifiers [71] , [72] .…”
Section: Methodology and Limitationsmentioning
confidence: 91%
“…In this paper, we used the DT and SVM classifiers as they are commonly used in ML techniques. In addition, they proved their efficiency over the other classifiers [71] , [72] .…”
Section: Methodology and Limitationsmentioning
confidence: 91%
“…A descriptor is then constructed to form a subset of features. Once key points are selected in the scale space, these key points, being extrema in the scale space, undergo wavelet transformation [22][23][24][25] to separate multiscale features around the key points, achieving effective feature extraction. Rectangular sub-images are established with key points as centers to describe key point information using sub-region image features, enabling mutual matching between key points in two images.…”
Section: Interference Fringe Feature Extraction and Matchingmentioning
confidence: 99%
“…After removing the flat ground effect from the interference fringes, which reflects terrain undulation information with a gradually changing gradient, analyzing local gradient information around feature points can effectively describe the current feature points. Histogram of oriented gradient (HOG) is a technique used for texture-based image analysis [24][25][26], simplifying images by extracting gradient information. HOG extracts features that have a locally distinctive shape based on edges or gradient structures.…”
Section: Interference Fringe Feature Extraction and Matchingmentioning
confidence: 99%
“…The performance of their model on the quin-classi cation task was not satisfactory (achieving an accuracy of 39.04%), so, in their last contribution they showed the fusion of the ROI and classi er outputs for WSI-level diagnosis helped improving accuracy. In more traditional mannerisms of extraction of features from digital mammography imaging, Yengec Tasdemir et al ( 2019) [71] detected abnormal areas in a mammography by features extracted by Histogram of Oriented Gradients (HOG) [72] and Haralick features [73] to detect ROIs for presence of BCa. The mammography was segmented into smaller ROIs of size 73×68 and then converted into a two dimensional Discrete Wavelet Transform (2D-DWT) for multi-resolution decomposition of the ROIs [74].…”
Section: Region Of Interest (Roi)-based Approachesmentioning
confidence: 99%