Alexander Loui Headshot

Alexander Loui

Lecturer
Department of Computer Engineering
Kate Gleason College of Engineering

585-475-5799
Office Location

Alexander Loui

Lecturer
Department of Computer Engineering
Kate Gleason College of Engineering

Education

BS, MS, Ph.D., University of Toronto (Canada)

Bio

Alexander C. Loui received his B.A.Sc. (Honors), M.A.Sc, and Ph.D. all in Electrical Engineering from the University of Toronto, Canada. He joined the Dept. of Computer Engineering at Rochester Institute of Technology in 2018. Prior to that, he spent over 28 years in a number of technical and research leadership positions with Kodak Alaris (2013-18), Kodak Research Labs (1996-13), and Bell Communications Research (1990-96). Dr. Loui has been directing research and development on computer vision and machine learning systems for a broad range of applications including image classification, video summarization, image/video retrieval, image management and curation, event detection, image quality assessment, and visual communications. His research interests also include data mining and deep learning algorithms for machine intelligence and AI applications. He has published over 100 refereed journal and conference papers in these areas. He is an Adjunct Professor of the ECE Department at Ryerson University in Toronto.

Dr. Loui is a Senior Area Editor of the IEEE Transactions on Image Processing. He has also served as an associate editor of the IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Multimedia, and SPIE Journal of Electronic Imaging. He has been an elected member of the IEEE ICME Steering Committee, IVMSP, MMSP, and MSA Technical Committees. He was Chair of the IEEE Rochester Section (2010-11), and Chair of the Rochester Chapter of IEEE Signal Processing Society (2005). Dr. Loui was a Kodak Distinguished Inventor with over 80 granted US patents. He is a recipient of the IEEE Region 1 Technological Innovation Award and a Fellow of IEEE and SPIE.

Recent Publications:

  • M. Kucer, A. Loui, and D. Messinger, "Leveraging expert feature knowledge for predicting image aesthetics," IEEE Trans. on Image Processing, Vol. 27, Issue 10, Oct. 2018.
  • C. Zhang, S. Sah, T. Nguyen, D. Peri, A. Loui, C. Salvaggio, and R. Ptucha, “Semantic sentence embeddings for paraphrasing and text summarization,” Proc. IEEE GlobalSIP, Montreal, Canada, Nov. 2017.
  • C. Zhang and A. Loui, "A coarse-to-fine framework for video object segmentation," Proc. Visual Information Processing and Communication Conference, IS&T Electronic Imaging, San Francisco, CA, Jan. 2017.
  • M. Wood, M. Das, P. Stubler, and A. Loui, “Event-enabled intelligent asset selection and grouping for photobook creation,” Image and Vision Computing – Special Issue on Event-based Media Processing and Analysis, Vol. 53, Elsevier, Sept. 2016.
  • W. Jiang, and A. Loui, “Video concept detection by audio-visual grouplets,” International Journal of Multimedia Information Retrieval (IJMIR), Vol. 1, Issue 4, pp. 223-238, Springer, Dec. 2012.
  • M. Das, A. Loui, and A. Blose, “Visual feature localization for detecting unique objects in images,” book chapter on Multimedia Information Extraction: Advances in Video, Audio, and Imagery Analysis for Search, Data Mining, Surveillance and Authoring, Wiley/IEEE Computer Society Press, Oct. 2012.
  • M. Park, M. Kumar, and A. Loui, “Saliency detection using region-based incremental center-surround distance,” Proc. IEEE Intern. Symposium on Multimedia, Dana Point, CA, Dec. 2011.
  • Y.-G. Jiang, G. Ye, S.-F. Chang, D. Ellis, and A. Loui, "Consumer Video Understanding: A Benchmark Database and an Evaluation of Human and Machine Performance,” Proc. ACM Intern. Conf. on Multimedia Retrieval, Trento, Italy, April 2011.
585-475-5799

Currently Teaching

CMPE-497
3 Credits
This is the first half of a two-semester design course oriented to the solution of engineering problems. The mission is to enhance engineering education through a capstone design experience that integrates engineering theory, principles and processes within a collaborative environment. Working in multidisciplinary teams and following an engineering design process, students will assess customer needs and engineering specifications, evaluate concepts, resolve major technical hurdles, and employ rigorous engineering principles to design a prototype which is fully tested and documented. Students may propose their own projects, which may have a primarily computer engineering focus and team, and which may begin with an entrepreneurial experience to establish the scope of the project for potential market and realistic prototype.
CMPE-480
3 Credits
This course introduces the basic elements of continuous and discrete time signals and systems and fundamental signal processing techniques, such as FIR and IIR Filtering, the Fourier transform, the Discrete Fourier transform and the z transform. Theory is strengthened through MATLAB-based projects and exercises.
CMPE-498
3 Credits
This is the second half of a two-semester design course oriented to the solution of engineering problems. The mission is to enhance engineering education through a capstone design experience that integrates engineering theory, principles and processes within a collaborative environment. Working in multidisciplinary teams and following an engineering design process, students will assess customer needs and engineering specifications, evaluate concepts, resolve major technical hurdles, and employ rigorous engineering principles to design a prototype which is fully tested and documented.
CMPE-677
3 Credits
Machine intelligence teaches devices how to learn a task without explicitly programming them how to do it. Example applications include voice recognition, automatic route planning, recommender systems, medical diagnosis, robot control, and even Web searches. This course covers an overview of machine learning topics with a computer engineering influence. Includes Matlab programming. Course topics include unsupervised and supervised methods, regression vs. classification, principal component analysis vs. manifold learning, feature selection and normalization, and multiple classification methods (logistic regression, regression trees, Bayes nets, support vector machines, artificial neutral networks, sparse representations, and deep learning).