Chee Seng Chan

A Fusion Approach for Efficient Human Skin Detection

A reliable human skin detection method that is adaptable to different human skin colors and illumination conditions is essential for better human skin segmentation. Even though different human skin-color detection solutions have been successfully applied, they are prone to false skin detection and are not able to cope with the variety of human skin colors across different ethnic. Moreover, existing methods require high computational cost. In this paper, we propose a novel human skin detection approach that combines a smoothed 2-D histogram and Gaussian model, for automatic human skin detection in color image(s). In our approach, an eye detector is used to refine the skin model for a specific person. The proposed approach reduces computational costs as no training is required, and it improves the accuracy of skin detection despite wide variation in ethnicity and illumination. To the best of our knowledge, this is the first method to employ fusion strategy for this purpose. Qualitative and quantitative results on three standard public datasets and a comparison with state-of-the-art methods have shown the effectiveness and robustness of the proposed approach.

Fuzzy Qualitative Human Motion Analysis

This paper proposes a fuzzy qualitative approach to vision-based human motion analysis with an emphasis on human motion recognition. It achieves feasible computational cost for human motion recognition by combining fuzzy qualitative robot kinematics with human motion tracking and recognition algorithms. First, a data-quantization process is proposed to relax the computational complexity suffered from visual tracking algorithms. Second, a novel human motion representation, i.e., qualitative normalized template, is developed in terms of the fuzzy qualitative robot kinematics framework to effectively represent human motion. The human skeleton is modeled as a complex kinematic chain, and its motion is represented by a series of such models in terms of time. Finally, experiment results are provided to demonstrate the effectiveness of the proposed method. An empirical comparison with conventional hidden Markov model (HMM) and fuzzy HMM (FHMM) shows that the proposed approach consistently outperforms both HMMs in human motion recognition.

A robust arbitrary text detection system for natural scene images

Abstract Text detection in the real world images captured in unconstrained environment is an important yet challenging computer vision problem due to a great variety of appearances, cluttered background, and character orientations. In this paper, we present a robust system based on the concepts of Mutual Direction Symmetry (MDS), Mutual Magnitude Symmetry (MMS) and Gradient Vector Symmetry (GVS) properties to identify text pixel candidates regardless of any orientations including curves (e.g. circles, arc shaped) from natural scene images. The method works based on the fact that the text patterns in both Sobel and Canny edge maps of the input images exhibit a similar behavior. For each text pixel candidate, the method proposes to explore SIFT features to refine the text pixel candidates, which results in text representatives. Next an ellipse growing process is introduced based on a nearest neighbor criterion to extract the text components. The text is verified and restored based on text direction and spatial study of pixel distribution of components to filter out non-text components. The proposed method is evaluated on three benchmark datasets, namely, ICDAR2005 and ICDAR2011 for horizontal text evaluation, MSRA-TD500 for non-horizontal straight text evaluation and on our own dataset (CUTE80) that consists of 80 images for curved text evaluation to show its effectiveness and superiority over existing methods.

Fuzzy human motion analysis

Human Motion Analysis (HMA) is currently one of the most popularly active research domains as such significant research interests are motivated by a number of real world applications such as video surveillance, sports analysis, healthcare monitoring and so on. However, most of these real world applications face high levels of uncertainties that can affect the operations of such applications. Hence, the fuzzy set theory has been applied and showed great success in the recent past. In this paper, we aim at reviewing the fuzzy set oriented approaches for HMA, individuating how the fuzzy set may improve the HMA, envisaging and delineating the future perspectives. To the best of our knowledge, there is not found a single survey in the current literature that has discussed and reviewed fuzzy approaches towards the HMA. For ease of understanding, we conceptually classify the human motion into three broad levels: Low-Level (LoL), Mid-Level (MiL), and High-Level (HiL) HMA. HighlightsA survey of fuzzy set oriented methods for human motion analysis is presented.This is the first time such a survey is presented in the fuzzy set literature.Categorization of existing approaches into three broad levels is performed.Insights and suggestions for future research are discussed.

Recognition of Human Motion From Qualitative Normalised Templates

This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classification methods which usually include a human model, prior knowledge on human motion and a matching algorithm, we replace the matching algorithm (e.g. template matching) with the proposed QNTs. The human motion is modelled by the time-varying joint angles and link lengths of an articulated human model. The ability to manage the trade-offs between model complexity and computational cost plays a crucial role in the performance of human motion classification. The QNTs is developed to categorise complex human motion into sets of fuzzy qualitative angles and positions in quantity space. Classification of the human motion is done by comparing the QNTs to the parameters learned from numerical motion tracking. Experimental results have demonstrated the effectiveness of our proposed method when classifying simple human motions, e.g. running and walking.

A novel multimodal communication framework using robot partner for aging population

It is expected that the population of elderly in the world will double in 2050.This paper proposes a human-friendly robot partner to assist the elderly.A new communication framework between the human and robot partner is developed.Informationally structured space was proposed to realize natural communication.Experiments using three case studies show the strength of the proposed framework. In developed country such as Japan, aging has become a serious issue, as there is a disproportionate increasing of elderly population who are no longer able to look after themselves. In order to tackle this issue, we introduce human-friendly robot partner to support the elderly people in their daily life. However, to realize this, it is essential for the robot partner to be able to have a natural communication with the human. This paper proposes a new communication framework between the human and robot partner based on relevance theory as the basis knowledge. The relevance theory is implemented to build mutual cognitive environment between the human and the robot partner, namely as the informationally structured space (ISS). Inside the ISS, robot partner employs both verbal as well as non-verbal communication to understand human. For the verbal communication, Rasmussens behavior model is implemented as the basis for the conversational system. While for the non-verbal communication, environmental and human state data along with gesture recognition are utilized. These data are used as the perceptual input to compute the robot partners emotion. Experimental results have shown the effectiveness of our proposed communication framework in establishing natural communication between the human and the robot partner.

Crowd behavior analysis

Although the traits emerged in a mass gathering are often non-deliberative, the act of mass impulse may lead to irrevocable crowd disasters. The two-fold increase of carnage in crowd since the past two decades has spurred significant advances in the field of computer vision, towards effective and proactive crowd surveillance. Computer vision studies related to crowd are observed to resonate with the understanding of the emergent behavior in physics (complex systems) and biology (animal swarm). These studies, which are inspired by biology and physics, share surprisingly common insights, and interesting contradictions. However, this aspect of discussion has not been fully explored. Therefore, this survey provides the readers with a review of the state-of-the-art methods in crowd behavior analysis from the physics and biologically inspired perspectives. We provide insights and comprehensive discussions for a broader understanding of the underlying prospect of blending physics and biology studies in computer vision. HighlightsReview crowd behavior studies in computer vision from physics and biology outlooks.Overview of the key attributes of crowd from the perspectives of the two sciences.General attributes of crowd: decentralized, collective motion, emergent behavior.Contradicting attributes of crowd: thinking/non-thinking, bias/non-bias.Discuss sample applications of crowd based on attributes and benchmarked datasets.

iSurveillance: Intelligent framework for multiple events detection in surveillance videos

Abstract Research in the video surveillance is gaining more popularity due to its widespread applications as well as social impact. In this paper, we present an intelligent framework for detection of multiple events in surveillance videos. Based on the principle of compositionality, we modularize the surveillance problems into a set of variables comprising regions-of-interest, classes (i.e. human, vehicle), attributes (i.e. speed, locality) and a set of notions (i.e. rules) associated to each of the attributes to construct a knowledge-based understanding of the environment. The final output from the reasoning process, which combines the definition domains of the various variables, allows a broader and integrated understanding of complex pattern of activities in the scene. This is in contrast to the state-of-the-art solutions that are only able to perform only a singular task, at a time. Experimental results on both the public and real-time datasets have demonstrated the effectiveness and robustness of the proposed framework in detecting multiple events in surveillance videos.

How deep learning extracts and learns leaf features for plant classification

Abstract Plant identification systems developed by computer vision researchers have helped botanists to recognize and identify unknown plant species more rapidly. Hitherto, numerous studies have focused on procedures or algorithms that maximize the use of leaf databases for plant predictive modeling, but this results in leaf features which are liable to change with different leaf data and feature extraction techniques. In this paper, we learn useful leaf features directly from the raw representations of input data using Convolutional Neural Networks (CNN), and gain intuition of the chosen features based on a Deconvolutional Network (DN) approach. We report somewhat unexpected results: (1) different orders of venation are the best representative features compared to those of outline shape, and (2) we observe multi-level representation in leaf data, demonstrating the hierarchical transformation of features from lower-level to higher-level abstraction, corresponding to species classes. We show that these findings fit with the hierarchical botanical definitions of leaf characters. Through these findings, we gained insights into the design of new hybrid feature extraction models which are able to further improve the discriminative power of plant classification systems. The source code and models are available at: https://github.com/cs-chan/Deep-Plant .

A weighted inference engine based on interval-valued fuzzy relational theory

Extend the BK subproduct from Type-1 fuzzy sets to interval-valued fuzzy sets.Weight parameter is introduced to the BK subproduct.Develop a novel method that automatically constructs knowledge base from examples.The proposed method outperforms state-of-the-art solutions in medical data. The study of fuzzy relations forms an important fundamental of fuzzy reasoning. Among all, the research on compositional fuzzy relations by Bandler and Kohout, or the Bandler-Kohout (BK) subproduct gained remarkable success in developing inference engines for numerous applications. Despite of its successfulness, we notice that there are limitations associated in the current implementations of the BK subproduct. In this paper, the BK subproduct, which originally based on the ordinary fuzzy set theory, is extended to the interval-valued fuzzy sets. This is because studies had claimed that ordinary fuzzy set theory has its limitation in addressing uncertainties using the crisp membership functions. Secondly, with the understanding that some features might have higher influence compare to the others, a weight parameter is introduced in the BK subproduct-based inference engines. Finally, a fuzzification method that able to fuzzify the input data and also train the inference engines is also developed. So, the BK subproduct-based inference systems can be built without human intervention, which are cumbersome and time consuming. Experiments on three public datasets and a comparison with state-of-art solutions have shown the efficiency and robustness of the proposed method.