Embedded Files
Head of AI, Hong Kong Industrial Artificial Intelligence & Robotics Centre (FLAIR)
B.Sc., M.Phil. (HKU), M.S., Ph.D. (UCLA)
Ivy received her B.Sc. and M.Phil. degrees in Mathematics from the University of Hong Kong and her Ph.D. degree in Computer Science from the University of California, Los Angeles. She is Head of AI in FLAIR. Her currently work involving artificial intelligence and computer vision for robotics and industrial automation. Previously, she was a Principal Architect/Assistant Director of the Robotics & Control team in LSCM, where she worked on developing and deployment of artificial intelligence and computer vision algorithms for robotics and automation. Previously, she held a Senior Engineer position with ASTRI, where she worked on developing image processing and data mining techniques in forwarding the research in bioimaging form drug target discovery to medical diagnostics. Before returning to Hong Kong in 2014, Ivy was an Assistant Principal Investigator of the Imaging Informatics Division in the Bioinformatics Institute, Singapore, where she joined as a Postdoctoral Research Fellow. She was also an Adjunct Assistant Professor in Department of Computer Science in National University of Singapore (NUS), where she has been teaching since fall 2013.
Ivy’s research interests focus on developing image processing and data mining techniques for various applications. Her works cover in a broad range of topics in computer vision, artificial intelligence and robotics
· Research
· Teaching
Research
The following is a brief summary of some selected research works. An in-depth exposition on these works and some other projects can be found in the relevant (cited) papers in the Publication List.
Artificial intelligent and robotic vision –
(1) Service Robots:
Deliverbot
Snow white
Follow me platooning
(2) Collaborative Robots for Manufacturing:
Sample extraction
Capacitor Installation
Control unit for greeting card
(3) Human Activity Understanding:
Golf training
Work safety
Imaging in translational research –
(1) Cellular-level molecular imaging:
In [3-4, 18], a series of level set based cell tracking methods using learned dynamic shape priors is presented. These methods can successfully track individual cells from HeLa cell population in many realistic scenarios. They are very generic and can be applied for a variety of cell images.
In [12], a computational framework is presented for the automatic detection of changes in images of in vitro cultured keratinocytos when phosphatase genes are silenced using RNAi technology. The method can successfully filter out many wild type images therefore making inference of gene silencing much easier for wound healing study.
In [13], an effective optimization method for solving the widely-studied Mumford-Shah segmentation model is presented. It is demonstrated how the method substantially improves the quality of segmentation of breast cancer cells expressing p53 and mdm2.
Gradient descent
Stochastic level set
(2) Whole mount imaging:
In [5], two semi-automated mammary gland quantification tools are developed for studying the changes of mammary gland morphologies in the developmental aspects under gene mutation. An online application is also developed for community use.
Diagnostic imaging –
(1) Cancer grading:
In [7, 10-11, 20], a variant of the Mumford-Shah model and a series of its improved versions are presented for tissue texture segmentation. The method performs well in diagnosing premalignant endometrial disease and is very practical for segmenting images sharing similar properties.
Original
Subspace M-S
In [17], an automated breast tissue density assessment method is presented. The work demonstrates that the use of high-order regional texture descriptors can increase the discriminative power of a classifier. In [1], an automated method for measuring change in mammographic density over a time series of mammograms is presented. The work demonstrates that the predictive power can be further improved by considering the mammographic density change obtained by the proposed framework.
Original
Dense tissue
(2) Retinal imaging for diabetes and other eye diseases:
In [6], a general-purpose segmentation algorithm for large collections of images is presented. The method can effectively segment various collections of biological images including retinal images obtained from a diabetic retinopathy screening program and retinal layer images for a study of cellular changes of a retina in response to disease or injury.
Original
Interactive
(3) X-ray and MRA imaging:
In [8], a variant of the Mumford-Shah model is presented for semi-transparent biomedical image segmentation. The method can successfully segment X-ray and MRA images for aiding the diagnosis of bone fracture and for surgery planning.
Elbow joint
Right hip joint
MRA
Database management –
In [21-24], a relational language and several quality control approaches to overcoming the problem of overloading for processing high-throughput streaming data are presented. In [9, 14], more promising results are presented. They started with Ivy’s thesis work but have been substantially extended since then.
Publications
Journal papers:
1. Y. N. Law, H. Jian, N. Lo, M. Ip, M. Chan, K. M. Kam and X. Wu. Low cost automated whole smear microscopy screening system for detection of acid fast bacilli. PLOS ONE. January 2018.
2. A. Khoo, J. Li, K. Czene, P. Hall, K. Humphreys, Y. N. Law. A combined segmentation and registration framework for bilateral and temporal mammogram analysis. Journal of Medical Imaging and Health Informatics, 6(2), pp. 380-386. April 2016.
3. C. K. Yap, E. M. Kalaw, M. Singh, K. T. Chong, D. Giron, C. H. Huang, L. Cheng, Y. N. Law, H. K. Lee. Automated image based prominent nucleoli detection. Journal of Pathology Informatics, 6, pp. 39. June 2015.
4. Y. N. Law. Cell tracking using phase-adaptive shape prior. Journal of Microscopy, 252(2), pp. 149-158. November 2013.
5. Y. N. Law, H.K. Lee and A.M. Yip. Learning dynamical shape prior for level set based cell tracking. Annals of the BMVA, 2013(1), pp.1-14. 2013.
6. Y. N. Law, V. Racine, P. L. Ang, H. Mohamed, P. C. Soo, J. M. Veltmaat and H. K. Lee. Development of MammoQuant: an automated quantitative tool for standardized image analysis of murine mammary gland morphogenesis. Journal of Medical Imaging and Health Informatics, 2(4), pp.352-365. Dec 2012.
7. Y. N. Law, H.K. Lee, M.K. Ng and A.M. Yip. A semi-supervised segmentation model for collections of images. IEEE Transactions on Image Processing, 21(6), pp. 2955-2968. June 2012.
8. Y. N. Law, H. K. Lee and A. M. Yip. Subspace Learning for Mumford-Shah Model Based Texture Segmentation through Texture Patches. Applied Optics, 50(21), pp. 3947-3957. July 2011.
9. Y. N. Law, H. K. Lee, C. Liu and A. M. Yip (2010). A Variational Model for Segmentation of Overlapping Objects with Additive Intensity Value. IEEE. Transactions on Image Processing, 20(6), pp. 1495-1503. June 2011.
10. Y. N. Law, H. Wang, C. Zaniolo. Relational languages and data models for continuous queries on sequences and data streams. ACM Transactions on Database Systems, 36(2), Article 8. May 2011.
11. Y. N. Law, A. M. Yip and H. K. Lee. Automatic Measurement of Volume Percentage Stroma in Endometrial Images using Texture Segmentation. Journal of Microscopy, 241(2), pp. 171-178. February 2011.
12. Y. N. Law, H. K. Lee and A. M. Yip. Semi-Supervised Subspace Learning for Mumford-Shah Model Based Texture Segmentation. Optics Express, 18(5), pp. 4434-4448. 2010.
13. Y. N. Law, S. Ogg, J. Common, D. Tan, E. B. Lane, A. M. Yip and H. K. Lee. Automated protein distribution detection in high-throughput image-based siRNA library screens. Journal of Signal Processing Systems, Vol. 55, No. 1-3, pp. 1 - 13. April 2009.
14. Y. N. Law, H. K. Lee and A. M. Yip. A multiresolution stochastic level set method for Mumford-Shah image segmentation. IEEE Transactions on Image Processing, 17(12), pp. 2289 - 2300, December 2008.
15. Y. N. Law and C. Zaniolo. Improving the accuracy of continuous aggregates and mining queries on data streams under load shedding. International Journal of Business Intelligence and Data Mining, 3(1), pp.99 - 117. April 2008.
Selected conference papers:
16. Y. N. Law, H. Jian, N. Lo, M. Ip, M. Chan, K.M. Kam, C. Tse and X. Wu. Low-cost automated tuberculosis whole smear screening system. Proceedings of the 47th Union World Conference on Lung Health. October 2016.
17. S. Y. Yeo, X. Yang, Y. N. Law, T. Gong, Y. Su and L. Cheng. Robust Modelling and Analysis of Vascular Geometries from Biomedical Images. Proceedings of the IASTED International Conference in Biomedical Engineering (BioMed) 2016, 832-024. February 2016.
18. Y. N. Law, M.K. Lieng, J. Li and A. Khoo. Automated breast tissue density assessment using high order regional texture descriptors in mammography. Proc. SPIE 9035,Medical Imaging 2014: Computer-Aided Diagnosis, 90351Q. March 2014.
19. Y. N. Law and H. K. Lee. Level set based tracking for cell cycle analysis using dynamical shape prior. Proceeding of the 16th Conference on Medical Image Understanding and Analysis (MIUA 2012), pp 137-142. July 2012.
20. V. A. Ngo, Y. N. Law, H. K. Lee, S. Hariharan and S. Ahmed. Accurate single-molecule localization of super-resolution microscopy images using multiscale products. Proc. SPIE 8228, Single Molecule Spectroscopy and Superresolution Imaging V, 822813. February 2012.
21. Y.N. Law, H.K. Lee, A.M. Yip. A stochastic level set method for subspace Mumford-Shah based image segmentation. Proceedings of the 2011 International Conference on Image Processing, Computer Vision, & Pattern Recognition (IPCV’11). July 2011.
22. Y. N. Law and C. Zaniolo. Load shedding for window joins on multiple data streams. Proceedings of the IEEE 23rd International Conference on Data Engineering Workshops (IEEE ICDEW 2007). pp. 674 – 683, April 2007.
23. Y. N. Law, C. Zaniolo: An adaptive nearest neighbor classification algorithm for data streams. Knowledge Discovery in Databases: 9th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2005), Porto, Portugal, October 3-7, 2005, Proceedings. Lecture Notes in Computer Science 3721 Springer 2005.
24. Y. N. Law, H. Wang, C. Zaniolo: Query languages and data models for database sequences and data streams. Proceedings of the Thirtieth International Conference on Very Large Data Bases (VLDB 2004), Toronto, Canada, August 31 - September 3 2004.
25. C. Zaniolo, C.R. Luo, Y. N. Law, and H. Wang: Incompleteness of database languages for data streams and data mining. Proceedings of the Eleventh Italian Symposium on Advanced Database Systems (SEBD 2003), Cetraro (CS), Italy, June 2003.
Book Chapter:
26. H. K. Lee, Y. N. Law, C. H. Huang and C. K. Yap. Analyzing cell and tissue morphologies using pattern recognition algorithms. In Biomedical Image Understanding, Methods and Applications. February 2015.
Patents:
27. K.L.Fan, Y.N. Law, K. Wong and C. Leung, Reinforcement bar joint recognition using artificial intelligence vision, US Patent 10,864,638B, 2020; HK Patent 1250872, 01-2019.
28. 樊家伦, 罗恩妮, 黄敬修, 梁颂恒, 使用人工智能视觉的钢筋接点识别, CN Patent 110956230A, 2020
29. X Wu and Y.N. Law, “Anomaly detection for medical samples under multiple settings, US Patent 10,108,845B2, 2018.
30. 吴晓华, 罗恩妮, 在多种设置下用于医学样品的异常检测, CN Patent 107735838A, 2018.
Teaching
Fall 2013-14 National University of Singapore, CS1010E Programming Methodology
Spring 2013-14 National University of Singapore, CS6101 Exploration of Computer Science Research
Contact
Email: ivyllaw [at] gmail [dot] com
Page updated
Google Sites
Report abuse