Performance comparison of ORB, SURF and SIFT using Intracranial Haemorrhage CTScan Brain images
Keywords:
scale-invariant feature transform (SIFT), speed up robust feature (SURF), oriented FAST, rotated BRIEF (ORB), Image matching.
Abstract
Medical images are crucial for both the doctor's accurate diagnosis and the patient's subsequent therapy. It is feasible to swiftly identify lesions in medical photos by using clever algorithms, and it is crucial to extract information from images. Feature extraction is an important step in image classification. It allows the representation of the content of images as perfectly as possible. The intention of this study is to certain overall performance assessment among the feature detector and the descriptor method, especially while there are numerous combos for assessment. Three techniques were decided on for the feature descriptors: ORB (Oriented FAST and Rotated BRIEF), SIFT (Scale Invariant Feature Transformation), and SURF (Accelerated Robust Feature) and to calculate matching evaluation parameters, for example, the number of key points in the image, Execution time required for each algorithm and to find the best match. The dataset was taken from Kaggle, which contained 170 CTScan images of the brain with intracranial hemorrhage masks. The brute force method is used to achieve feature matching. Performance analysis shows the discriminative power of various combinations of detector and descriptor methods. SURF algorithm is the best and most robust in CTScan imaging to help medical diagnosis.
References
[1] Aimin Yang 1, Xiaolei Yang1, Wenrui Wu 2, Huixiang Liu1, and Yunxi Zhuansun1. Research on Feature Extraction of Tumor Image Based on Convolutional Neural Network. Digital Object Identifier 10.1109/ACCESS.2019.2897131. (2019).
[2] Hang Zhu and Zihao Wang. Feature matching in Ultrasound images 23 Oct 2020.
[3] Wamidh K. Mutlag1, Shaker K. Ali2, Zahoor M. Aydam3 and Bahaa H.Taher4. Feature Extraction Methods: A Review. 2020.
[4] Mr. Anil K. Bharodiya and Prof. Dr. Atul M. Gonsai. Research Review on Feature Extraction Methods of Human Being’s X-Ray Image Analysis ISSN: 0974-3308, VOL. 11, NO. 1 JUNE 2018 @ SRIMCA.
[5] K.Baskar1 and D.Seshathiri2. A Survey on Feature Selection Techniques in Medical Image Processing (IJERT) IJERTIJERT ISSN: 2278-0181 www.ijert.org NCICCT' 14 Conference Proceedings.
[6] Ebtsam Adel, Mohammed Elmogy and Hazem Elbakr, Image Stitching System Based on ORB Feature. Egypt (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 9, 2015.
[7] Hemamalini G E and Dr. J Prakash. Medical Image Analysis of Image Segmentation and Registration Techniques (IJET).
[8] Yong Chen. Robust Image Matching Algorithm Using SIFT on Multiple Layered Strategies Volume 2013 | Article ID 452604 | https://doi.org/10.1155/2013/452604.
[9] Ebrahim Karami, Siva Prasad, and Mohamed Shehata. Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images.
[10] Gustavo Magalhães Moura and Rodrigo Luis De Souza Da Silva. Analysis And Evaluation Of Feature Detection And Tracking Techniques Using Opencv With Focus On Markerless Augmented Reality Applications. Journal of Mobile Multimedia 12(3&4):291-302 DOI:10.26421/JMM12.3-4. April 2017.
[11] Surbhi Gupta, Kutub Thakur and Munish Kumar. 2D-human face recognition using SIFT and SURF descriptors of face’s feature regions The Visual Computer (2021) 37:447–456 https://doi.org/10.1007/s00371-020-01814-8
[12] N. Sasikala, V. Swathipriya, M. Ashwini, V. Preethi, A. Pranavi, and M. Ranjith. Feature Extraction of Real-Time Image Using SIFT Algorithm EJECE, European Journal of Electrical Engineering and Computer Science Vol. 4, No. 3, May 2020
[13] Manyi Wu. Research on optimization of image fast feature point matching algorithm. Wu EURASIP Journal on Image and Video Processing (2018) 2018:106 https://doi.org/10.1186/s13640-018-0354-y
[14] Shaharyar Ahmed Khan Tareen and Zahra Saleem Fatima A Comparative Analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. 2018 International Conference on Computing, Mathematics and Engineering Technologies – iCoMET 2018
[15] Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim. A Speeded up Robust Scale-Invariant Feature Transform Currency Recognition Algorithm World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:12, No:6, 2018.
[16] Ebrahim Karami, Siva Prasad, and Mohamed Shehata. Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images Faculty of Engineering and Applied Sciences, Memorial University, Canada. (Pages 05. 2017).
[17] M. Hanmandlu, A.Q Ansari, Kunal Goyal, Jaspreet Kour and Rutvik Malekar Scale Invariant Feature Transform Based Fingerprint Core point Detection. Defence Science Journal 63(4):37-42 DOI:10.14429/dsj.63.2708. 2013.
[18] Shuvo Kumar Paul, Pourya Hoseini and Mircea Nicolescu. Performance Analysis of Keypoint Detectors and Binary Descriptors Under Varying Degrees of Photometric and Geometric Transformation. arXiv:2012.04135 [cs.CV]
[19] Ertugrul Bayraktar, Pınar Boyraz and Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics. Turkish Journal of Electrical Engineering & Computer Sciences, (2017) 25: 2444 – 2454.
[20] Yin Fei, Xi’, Gao Wei and Song Zongxi. Medical Image Fusion Based on Feature Extraction and Sparse Representation. Hindawi International Journal of Biomedical Imaging Volume 2017, Article ID 3020461, 11 pages https://doi.org/10.1155/2017/3020461.
[21] Shruthishree S.H, and Harshvardhan, A REVIEW PAPER ON MEDICAL IMAGE PROCESSING. India. ISSN- 2350-0530(O), ISSN- 2394-3629(P), April, 2017.
[22] Chaoqun Ma, Xiaoguang Hu, Jin Xiao, and Guofeng Zhang, Homogenized ORB Algorithm Using Dynamic Threshold and Improved Quadtree. China. Hindawi Mathematical Problems in Engineering Volume 2021, Article ID 6693627, 19 pages https://doi.org/10.1155/2021/6693627.
[23] Gustavo Magalhães Moura and RODRIGO LUIS DE SOUZA DA SILVA. Analysis And Evaluation Of Feature Detection And Tracking Techniques Using Opencv With Focus On Markerless Augmented Reality Applications. Journal of Mobile Multimedia, Vol. 12, No. 3&4 (2017) 291–302
[2] Hang Zhu and Zihao Wang. Feature matching in Ultrasound images 23 Oct 2020.
[3] Wamidh K. Mutlag1, Shaker K. Ali2, Zahoor M. Aydam3 and Bahaa H.Taher4. Feature Extraction Methods: A Review. 2020.
[4] Mr. Anil K. Bharodiya and Prof. Dr. Atul M. Gonsai. Research Review on Feature Extraction Methods of Human Being’s X-Ray Image Analysis ISSN: 0974-3308, VOL. 11, NO. 1 JUNE 2018 @ SRIMCA.
[5] K.Baskar1 and D.Seshathiri2. A Survey on Feature Selection Techniques in Medical Image Processing (IJERT) IJERTIJERT ISSN: 2278-0181 www.ijert.org NCICCT' 14 Conference Proceedings.
[6] Ebtsam Adel, Mohammed Elmogy and Hazem Elbakr, Image Stitching System Based on ORB Feature. Egypt (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 9, 2015.
[7] Hemamalini G E and Dr. J Prakash. Medical Image Analysis of Image Segmentation and Registration Techniques (IJET).
[8] Yong Chen. Robust Image Matching Algorithm Using SIFT on Multiple Layered Strategies Volume 2013 | Article ID 452604 | https://doi.org/10.1155/2013/452604.
[9] Ebrahim Karami, Siva Prasad, and Mohamed Shehata. Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images.
[10] Gustavo Magalhães Moura and Rodrigo Luis De Souza Da Silva. Analysis And Evaluation Of Feature Detection And Tracking Techniques Using Opencv With Focus On Markerless Augmented Reality Applications. Journal of Mobile Multimedia 12(3&4):291-302 DOI:10.26421/JMM12.3-4. April 2017.
[11] Surbhi Gupta, Kutub Thakur and Munish Kumar. 2D-human face recognition using SIFT and SURF descriptors of face’s feature regions The Visual Computer (2021) 37:447–456 https://doi.org/10.1007/s00371-020-01814-8
[12] N. Sasikala, V. Swathipriya, M. Ashwini, V. Preethi, A. Pranavi, and M. Ranjith. Feature Extraction of Real-Time Image Using SIFT Algorithm EJECE, European Journal of Electrical Engineering and Computer Science Vol. 4, No. 3, May 2020
[13] Manyi Wu. Research on optimization of image fast feature point matching algorithm. Wu EURASIP Journal on Image and Video Processing (2018) 2018:106 https://doi.org/10.1186/s13640-018-0354-y
[14] Shaharyar Ahmed Khan Tareen and Zahra Saleem Fatima A Comparative Analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. 2018 International Conference on Computing, Mathematics and Engineering Technologies – iCoMET 2018
[15] Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim. A Speeded up Robust Scale-Invariant Feature Transform Currency Recognition Algorithm World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:12, No:6, 2018.
[16] Ebrahim Karami, Siva Prasad, and Mohamed Shehata. Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images Faculty of Engineering and Applied Sciences, Memorial University, Canada. (Pages 05. 2017).
[17] M. Hanmandlu, A.Q Ansari, Kunal Goyal, Jaspreet Kour and Rutvik Malekar Scale Invariant Feature Transform Based Fingerprint Core point Detection. Defence Science Journal 63(4):37-42 DOI:10.14429/dsj.63.2708. 2013.
[18] Shuvo Kumar Paul, Pourya Hoseini and Mircea Nicolescu. Performance Analysis of Keypoint Detectors and Binary Descriptors Under Varying Degrees of Photometric and Geometric Transformation. arXiv:2012.04135 [cs.CV]
[19] Ertugrul Bayraktar, Pınar Boyraz and Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics. Turkish Journal of Electrical Engineering & Computer Sciences, (2017) 25: 2444 – 2454.
[20] Yin Fei, Xi’, Gao Wei and Song Zongxi. Medical Image Fusion Based on Feature Extraction and Sparse Representation. Hindawi International Journal of Biomedical Imaging Volume 2017, Article ID 3020461, 11 pages https://doi.org/10.1155/2017/3020461.
[21] Shruthishree S.H, and Harshvardhan, A REVIEW PAPER ON MEDICAL IMAGE PROCESSING. India. ISSN- 2350-0530(O), ISSN- 2394-3629(P), April, 2017.
[22] Chaoqun Ma, Xiaoguang Hu, Jin Xiao, and Guofeng Zhang, Homogenized ORB Algorithm Using Dynamic Threshold and Improved Quadtree. China. Hindawi Mathematical Problems in Engineering Volume 2021, Article ID 6693627, 19 pages https://doi.org/10.1155/2021/6693627.
[23] Gustavo Magalhães Moura and RODRIGO LUIS DE SOUZA DA SILVA. Analysis And Evaluation Of Feature Detection And Tracking Techniques Using Opencv With Focus On Markerless Augmented Reality Applications. Journal of Mobile Multimedia, Vol. 12, No. 3&4 (2017) 291–302
Published
2023-01-31
How to Cite
Oad, A., Kumari, K., Hussain, I., Dong, F., Hammad, B., & Oad, R. (2023). Performance comparison of ORB, SURF and SIFT using Intracranial Haemorrhage CTScan Brain images. International Journal of Artificial Intelligence & Mathematical Sciences, 1(2), 26-34. https://doi.org/10.58921/ijaims.v1i2.41
