WL Operator: A Robust Quasi High-Pass Filter for Edge Detection in Medical Images

Javad Safiyi; Erfan Molavi; Mahya Divani; Sina Emami

Yazarlar

Javad Safiyi Electrical Engineering and Computer Science Department, Isfahan University of Technology, Iran, Isfahan
Erfan Molavi New Technologies Department, Iran University of Technology and Science, Iran, Tehran
Mahya Divani Biomechanical Engineering Department, Isfahan University of Technology, Iran, Isfahan
Sina Emami New Technologies Department, Iran University of Technology and Science, Iran, Tehran

Anahtar Kelimeler:

Edge Detection, Medical Images, Quasi High-Pass Filter, WL Operator, Kernel-Based Algorithm, Spatial Isotropic Symmetry, Medical Imaging Modalities.

Özet

In this study, we propose a robust edge detection method for medical images using the WL operator (Wang and Lin). The operator is based on a kernel-based algorithm, similar to conventional edge detectors, but with an adaptive and mathematically formulated approach. By expressing the detector as a quadratic form of the Toeplitz matrix, we exploit its highly structured internal architecture and spatial isotropic symmetry. The WL operator addresses common edge detection challenges such as fragmentation, position dislocation, and thinness loss, while being robust to noise and efficient in extracting crucial edge features. Comparative evaluations against other edge detectors, using Pratt's figure of merits and expert visual analog scale scores, demonstrate the superior performance of the WL operator. Furthermore, the operator shows promising results in various medical imaging modalities, including X-ray, CT, and MRI, encouraging further investigation.

Referanslar

Shotton J, Blake A, Cipolla R. Multiscale categorical object recognition using contour fragments. IEEE transactions on pattern analysis and machine intelligence. 2008 Jun 6;30(7):1270-81.

Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K. Sketch-based manga retrieval using manga109 dataset. Multimedia Tools and Applications. 2017 Oct;76:21811-38.

Qian W, Yang X, Peng S, Yan J, Guo Y. Learning modulated loss for rotated object detection. InProceedings of the AAAI conference on artificial intelligence 2021 May 18 (Vol. 35, No. 3, pp. 2458-2466).

Poma XS, Riba E, Sappa A. Dense extreme inception network: Towards a robust cnn model for edge detection. InProceedings of the IEEE/CVF winter conference on applications of computer vision 2020 (pp. 1923-1932).

Zhang X, Yang YH, Han Z, Wang H, Gao C. Object class detection: A survey. ACM Computing Surveys (CSUR). 2013 Jul 11;46(1):1-53.

Izadi S, Jabari K, Izadi M, Hamedani BK, Ghaffari A. Identification and Diagnosis of Dynamic and Static Misalignment in Induction Motor Using Unscented Kalman Filter. In2021 13th Iranian Conference on Electrical Engineering and Computer Science (ICEESC) 2021.

Gall J, Lempitsky V. Class-specific hough forests for object detection. Decision forests for computer vision and medical image analysis. 2013:143-57.

Najari, A., Shabani, F. and Hosseynzadeh, M., 2021. INTEGRATED INTELLIGENT CONTROL SYSTEM DESIGN TO IMPROVE VEHICLE ROTATIONAL STABILITY USING ACTIVE DIFFERENTIAL. Acta Technica Corviniensis-Bulletin of Engineering, 14(1), pp.79-82.

Sharma KU, Thakur NV. A review and an approach for object detection in images. International Journal of Computational Vision and Robotics. 2017;7(1-2):196-237.

Amini M, Hassani Mehraban A, Pashmdarfard M, Cheraghifard M. Reliability and validity of the Children Participation Assessment Scale in Activities Outside of School–Parent version for children with physical disabilities. Australian Occupational Therapy Journal. 2019 Aug;66(4):482-9.

Gall J, Yao A, Razavi N, Van Gool L, Lempitsky V. Hough forests for object detection, tracking, and action recognition. IEEE transactions on pattern analysis and machine intelligence. 2011 Apr 5;33(11):2188-202.

Cheraghifard M, Shafaroodi N, Khalafbeigi M, Yazdani F, Alvandi F. Psychometric properties of the Persian version of Volitional Questionnaire in Patients with Severe Mental Illnesses. Journal of Rehabilitation Sciences & Research. 2019 Jun 1;6(2):86-90.

K. Jabari, M. Izadi, S. Izadi, B. Khadem Hamedani, and A. Ghaffari, "Predictive and Data-Driven Control of Traffic Lights in Urban Road Networks using Linear and Time-Varying Model," in 2022 14th Iranian Conference on Electrical Engineering and Computer Science (ICEESC), 2022.

Gupta RK, Chia AY, Rajan D, Ng ES, Zhiyong H. Image colorization using similar images. InProceedings of the 20th ACM international conference on Multimedia 2012 Oct 29 (pp. 369-378).

Lin G, Tang Y, Zou X, Cheng J, Xiong J. Fruit detection in natural environment using partial shape matching and probabilistic Hough transform. Precision Agriculture. 2020 Feb;21:160-77.

Cao Y, Wang C, Zhang L, Zhang L. Edgel index for large-scale sketch-based image search. InCVPR 2011 2011 Jun 20 (pp. 761-768). IEEE.

Bai J, Liu Z, Lin Y, Li Y, Lian S, Liu D. Wearable travel aid for environment perception and navigation of visually impaired people. Electronics. 2019 Jun 20;8(6):697.

Rueda S, Fathima S, Knight CL, Yaqub M, Papageorghiou AT, Rahmatullah B, Foi A, Maggioni M, Pepe A, Tohka J, Stebbing RV. Evaluation and comparison of current fetal ultrasound image segmentation methods for biometric measurements: a grand challenge. IEEE Transactions on medical imaging. 2013 Aug 6;33(4):797-813.

Floros G, Van Der Zander B, Leibe B. Openstreetslam: Global vehicle localization using openstreetmaps. In2013 IEEE International Conference on Robotics and Automation 2013 May 6 (pp. 1054-1059). IEEE.

Lin L, Wang X, Yang W, Lai JH. Discriminatively trained and-or graph models for object shape detection. IEEE Transactions on pattern analysis and machine intelligence. 2014 Sep 23;37(5):959-72.

Choi C, Trevor AJ, Christensen HI. RGB-D edge detection and edge-based registration. In2013 IEEE/RSJ International Conference on Intelligent Robots and Systems 2013 Nov 3 (pp. 1568-1575). IEEE.

Kontschieder P, Donoser M, Bischof H. Beyond pairwise shape similarity analysis. InComputer Vision–ACCV 2009: 9th Asian Conference on Computer Vision, Xi’an, September 23-27, 2009, Revised Selected Papers, Part III 9 2010 (pp. 655-666). Springer Berlin Heidelberg.

Lysenkov I, Eruhimov V, Bradski G. Recognition and pose estimation of rigid transparent objects with a kinect sensor. Robotics. 2013 Jul 5;273(273-280):2.

Choi C, Christensen HI. 3D textureless object detection and tracking: An edge-based approach. In2012 IEEE/RSJ International Conference on Intelligent Robots and Systems 2012 Oct 7 (pp. 3877-3884). IEEE.