1



associate professor at University of Malaya



[Google Scholar] [Github]

My research interests include computer vision and fuzzy set theory, particularly on image/video content analysis, that enables automatic analyzing of image/video to detect and determine spatial and temporal events. Potential applications include visual surveillance, robots, entertainments etc. I was the founding Chair for the IEEE Computational Intelligence Society (CIS) Malaysia chapter, the organising chair for ACPR in 2015, and general chair for MMSP in 2019 & VCIP in 2013. I am a Senior Member of IEEE, a Chartered Engineer and a Member of IET.

Highlights:
        10/2018: Signal Processing: Image Communication Special Issue on The Deep Learning in Computational Photography.
        08/2018: I will serve as the general chair of MMSP 2019.
        05/2018: One(1) paper to appear in ICIP 2018.
        07/2017: I co-author a book with titled - Human Motion Sensing and Recognition: A Fuzzy Qualitative Approach is now available.


I am always interested to hear from prospective research students. Scholarships are available from time to time, contact me to enquire.


Selected Publications

2

Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork

ArtGAN: A series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis. Extension of ICIP 2017: ArtGAN.

W.R. Tan, C.S. Chan, H. Aguirre and K. Tanaka
IEEE Transactions on Image Processing 2019
[pdf] [supp. material] [code]

2

Anisotropic Partial Differential Equation based Video Saliency Detection

Study video saliency detection using Partial Differential Equation (PDE).

W.L. Hoo and C.S. Chan
ICIP 2018
[pdf] [poster]

2

Multi-Organ Plant Classification based on Convolutional and Recurrent Neural Networks

In this work, we present two deep frameworks (i.e. HGO-CNN & Plant-StructNet) to classify plant. Extension of ICIP 2017: HGO-CNN.

S.H. Lee, C.S. Chan and P. Remagnino
IEEE Transactions on Image Processing 2018
[pdf] [code] [project]

2

Granular-based Dense Crowd Density Estimation

In this work, we study crowd counting using the concept and principles of granular computing.

V.J. Kok and C.S. Chan
Multimedia Tools and Applications 2018
[pdf]

2

Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition

To facilitate a new text detection research, we introduce the Total-Text dataset, which is more comprehensive than the existing text datasets. Total-Text consists of 1555 images with more than 3 different text orientations, one of a kind.

C.K. Ch'ng and C.S. Chan
ICDAR 2017 (Oral, acceptance rate: 52/409 ~ 12.7%.)
[pdf] [arXiv (extended ver.)] [slide] [dataset]

2

How Deep Learning Extracts and Learns Leaf Features for Plant Classification

This paper studies how deep learning can be used in plant classification. Extension of ICIP 2015: Deep-Plant.

S.H. Lee, C.S. Chan, S. Mayo and P. Remagnino
Pattern Recognition 2017
[pdf] [code] [dataset] [webpage]

2

GrCS: Granular Computing Based Crowd Segmentation

This paper studies crowd segmentation using the concept and principles of granular computing.

V.J. Kok and C.S. Chan
IEEE Transactions on Cybernetics 2017
[pdf] [webpage]

2

phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning

This paper builds an image captioning system based on phrase.

Y.H. Tan and C.S. Chan
ACCV 2016
[pdf] [arXiv (extended ver.)] [poster]

2

A Deep Convolutional Network for Fine-art Paintings Classification

This paper preliminary studies on artwork classification using AlexNet.

W.R. Tan, C.S. Chan, H. Aguirre and K. Tanaka
ICIP 2016
[pdf] [supp. material] [poster] [github] [dataset]

2

Early Detection of Human Actions - A Hybrid Approach

This paper studies a classifer that is capable to recognize human action when only partial action sample is seen. Best student paper nomination at FUZZ-IEEE 2015.

E. Vats and C.S. Chan
Applied Soft Computing 2016
[pdf]

2

Fuzzy Qualitative Human Model for Viewpoint Identification

This paper studies a view-invariant human model based on Poisson and fuzzy qualitative reasoning. Extension of FUZZ-IEEE 2013.

C.H. Lim and C.S. Chan
Neural Computing and Applications 2016
[pdf]

2

Crowd Behavior Analysis: A Review where Physics meets Biology

This paper surveys a crowd behavior analysis with 180 references.

V.J. Kok, M.K. Lim and C.S. Chan
Neurocomputing 2016
[pdf] [webpage]

2

Orthogonal Planar Search (OPS) for Coronary Artery Centerline Extraction

This paper investigates orthogonal planar search for coronary artery centerline extraction from computed tomography angiography. Extension of MVA 2013.

S. Tang and C.S. Chan
Signal, Image and Video Processing 2016
[pdf] [poster]

2

Zero-Shot Object Recognition System based on Topic Model

This paper studies zero-shot learning based on topic model. Extension of ICIP 2013.

W.L. Hoo and C.S. Chan
IEEE Transactions on Human-Machine Systems 2015
[pdf] [webpage]

2

An Improved BK Sub-Triangle Product Approach for Scene Classification

This paper studies on scene classification using BK sub-triangle product inference mechanism.

E. Vats, C.K. Lim and C.S. Chan
Journal of Intelligent & Fuzzy Systems 2015
[pdf] [webpage]

2

A Novel Multimodal Communication Framework using Robot Partner for Ageing Population

This paper studies a new multimodal human-robot interaction framework to support elderly people in their daily life.

D. Tang, B. Yusuf, J. Botzheim, N. Kubota and C.S. Chan
Expert Systems with Applications 2015
[pdf]

2

Fuzzy Human Motion Analysis: A Review

First fuzzy review paper in human motion analysis with 252 references.

C.H. Lim*, E. Vats* and C.S. Chan (*indicates equal contribution)
Pattern Recognition 2015
[pdf]

2

A Weighted Inference Engine based on Interval-valued Fuzzy Relational Theory

This paper studies a high reliability inference engine that is rule-free, tolerate to uncertainty with interval-valued fuzzy sets and consider features weight. Extension of FUZZ-IEEE 2013.

C.K. Lim and C.S. Chan
Expert Systems with Applications 2015
[pdf]

2

Scene Image is Non-Mutually Exclusive - A Fuzzy Qualitative Scene Understanding

This paper proposes fuzzy qualitative rank classifier to handle natural scene classification. Extension of FUZZ-IEEE 2012.

C.H. Lim, A. Risnumawan and C.S. Chan
IEEE Transactions on Fuzzy Systems 2014
[pdf]

2

A Robust Arbitrary Text Detection System for Natural Scene Images

Curve text detection. A new dataset (CUTE80) is proposed.

A. Risnumawan, P. Shivakumara, C.S. Chan and C.L. Tan
Expert Systems with Applications 2014
[pdf] [dataset]

2

Refined Particle Swarm Optimisation Method for Abrupt Motion Tracking

This paper studies abrupt motion tracking using PSO. Extension of MVA 2013: SwATrack.

M.K. Lim, C.S. Chan, D. Monekosso and P. Remagnino
Information Sciences 2014
[pdf] [dataset] [webpage]

2

Crowd Saliency Detection via Global Similarity Structure

This paper identifies and localizes salient regions in a crowd scene, by transforming low-level features extracted from the crowd motion field into a global similarity structure.

M.K. Lim*, V.J. Kok*, C.C. Loy and C.S. Chan (*indicates equal contribution)
ICPR 2014 (Oral, acceptance rate: 198/1409 ~ 14%.)
[pdf] [dataset] [webpage]

2

Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding

This paper studies discriminative RF codebook learning and generative classifier learning in image understanding.

W.L. Hoo, T-K. Kim, Y. Pei and C.S. Chan
ICPR 2014 (Oral, acceptance rate: 198/1409 ~ 14%.)
[pdf] [supp. material]

2

A Fusion Approach for Efficient Human Skin Detection

This paper studies a hybrid model to detect human skin. A new skin detection dataset (Pratheepan) is proposed.

W.R. Tan, C.S. Chan, Y. Pratheepan and J. Condell
IEEE Transactions on Industrial Informatics 2012
[pdf] [dataset] [webpage]

2

Fuzzy Qualitative Human Motion Analysis

This paper studies human motion analysis with fuzzy qualitative reasoning. Extension of FUZZ-IEEE 2008.

C.S. Chan and H. Liu
IEEE Transactions on Fuzzy Systems 2009
[pdf]

2

GMM-QNT Hybrid Framework for Vision-based Human Motion Analysis

This paper studies a fusion between GMM-QNT for human motion analysis.

C.S. Chan and H. Liu
FUZZ-IEEE 2009 (Oral)
[pdf]

2

Recognition of Human Motion From Qualitative Normalised Templates

This paper models human upper and lower limbs using qualitative normalised templates. Application in visual surveillance.

C.S. Chan, H. Liu and D.J. Brown
Journal of Intelligent and Robotic Systems 2007
[pdf]


Talks


2

Toward Interpretable Deep Learning via Fuzzy Logic

IJCAI 2018

Our recent findings disclosed an intriguing connection between fuzzy logic and deep learning. This tutorial highlights the main concepts of fuzzy logic and its applicability to deep learning.
[Part 1] [Part 2] [Part 3]

2

Image Captioning using Phrase-based Hierarchical LSTM Model

Invited Talk at Nvidia AI Conference 2018

This invited talk was presented at Nvidia A.I. Conference, Singapore. The talk highlights how image captioning can be used to assist visual impairment society.
[Slides]

2

Computer Vision: A Computational Intelligence Perspective

Tutorial at FUZZ-IEEE/WCCI

How modern computer vision (CV) research and possible directions, tools and novel ideas that the computational intelligence (CI) community may contribute.
[FUZZ2017] [WCCI2016 Part I] [WCCI2016 Part II]

2

A.I. - A Dream or A Nightmare (人工智能,美夢還是噩夢?)

TEDx PetalingStreet [video]



Datasets


2

Total Text Dataset

ICDAR 2017

The Total-Text dataset is a collection of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.


2

Exclusively Dark Dataset

arXiv2017

The Exclusively Dark (ExDARK) dataset is a collection of 7,363 natural low-light images with 12 object classes (similar to PASCAL VOC) annotated on both image class level and local object bounding boxes.


2

WikiArt Dataset

ICIP 2016

In order to replicate or to have a fair comparison to our ICIP2016 paper, we created a "new" Wikiart dataset. All the images were obtained from WikiArt.org.


2

MalayaKew Plant Dataset

ICIP 2015

MalayaKew (MK) Leaf dataset was collected at the Royal Botanic Gardens, Kew, England. It consists of scan-like images of leaves from 44 species classes. This dataset is very challenging as leaves from different species classes have very similar appearance.


2

CUTE80 Dataset

ESWA 2014

We introduce the first curved text dataset to be made public, namely CUTE80 that consists of 80 curved text line images with complex background, perspective distortion effect and poor resolution effect (in circle, S, Z shaped text lines).


2

Pratheepan Human Skin Dataset

T-II 2012

The images in this dataset are downloaded randomly from Google for human skin detection research. These images are captured with a range of different cameras using different colour enhancement and under different illuminations.



Current Team

  • Nor Hamizah Miswan
  • Nicole Tham
  • Yu Quan Lim
  • Nurul Japar
  • Jian Han Lim
  • Chun Chet Ng
  • Jia Huei Tan
  • Chee Kheng Chng
  • Ying Hua Tan
  • Abhishek Jhawar
  • Yang Loong Chang

Alumni

  • Yuen Peng Loh
    Now Assistant Lecturer @ Multimedia Univ.
  • Sue Han Lee - PhD 2018.
    Now Postdoc @ INRA, France.
  • Ven Jyn Kok - PhD 2016.
    Now Senior Lecturer @ National Univ. of Malaysia.
  • Wai Lam Hoo - PhD 2016.
    Now Senior Lecturer @ Univ. of Malaya
  • Ekta Vats - PhD 2016.
    Now Postdoc @ Uppsala Univ., Sweden.
  • Mei Kuan Lim - PhD 2015.
    Now Lecturer @ Monash Univ.
  • Sze Ling Tang - PhD 2015.
    Now R&D Lead @ Manja Technologies.
  • Anhar Risnumawan - MSc. 2014.
    Now Lecturer @ EEPIS, Indonesia.
  • Chee Kau Lim - PhD 2014.
    Now Senior Lecturer @ Univ. of Malaya.
  • Chern Hong Lim - PhD 2014.
    Now Lecturer @ Monash Univ.
  • Wei Ren Tan - MSc. 2012.
    Now Postdoc @ National Tsing Hua Univ., Taiwan.