Amir Akramin Shafie

Vascular intersection detection in retina fundus images using a new hybrid approach

The use of vascular intersection aberration as one of the signs when monitoring and diagnosing diabetic retinopathy from retina fundus images (FIs) has been widely reported in the literature. In this paper, a new hybrid approach called the combined cross-point number (CCN) method able to detect the vascular bifurcation and intersection points in FIs is proposed. The CCN method makes use of two vascular intersection detection techniques, namely the modified cross-point number (MCN) method and the simple cross-point number (SCN) method. Our proposed approach was tested on images obtained from two different and publicly available fundus image databases. The results show a very high precision, accuracy, sensitivity and low false rate in detecting both bifurcation and crossover points compared with both the MCN and the SCN methods.

Hidden Markov model for human to computer interaction: a study on human hand gesture recognition

Human hand recognition plays an important role in a wide range of applications ranging from sign language translators, gesture recognition, augmented reality, surveillance and medical image processing to various Human Computer Interaction (HCI) domains. Human hand is a complex articulated object consisting of many connected parts and joints. Therefore, for applications that involve HCI one can find many challenges to establish a system with high detection and recognition accuracy for hand posture and/or gesture. Hand posture is defined as a static hand configuration without any movement involved. Meanwhile, hand gesture is a sequence of hand postures connected by continuous motions. During the past decades, many approaches have been presented for hand posture and/or gesture recognition. In this paper, we provide a survey on approaches which are based on Hidden Markov Models (HMM) for hand posture and gesture recognition for HCI applications.

Modeling and control of a rotary inverted pendulum using various methods, comparative assessment and result analysis

Inverted pendulum control is one of the fundamental but interesting problems in the field of control theory. This paper describes the steps to design various controllers for a rotary motion inverted pendulum which is operated by a rotary servo plant, SRV 02 Series. In this paper some classical and modern control techniques are analyzed to design the control systems. Firstly, the most popular Single Input Single Output (SISO) system, is applied including 2DOF Proportional-Integral-Derivative (PID) compensator design. Here the common Root Locus Method is described step by step to design the two compensators of PID controller. Designing the control system using 2DOF PID is quiet challenging task for the rotary inverted pendulum because of its highly nonlinear and open-loop unstable characteristics. Secondly, the paper describes the two Modern Control techniques that include Full State Feedback (FSF) and Linear Quadratic Regulator (LQR). Here FSF and LQR control systems are tested both for the Upright and Swing-Up mode of the Pendulum. Finally, experimental and MATLAB based simulation results are described and compared based on the three control systems which are designed to control the Rotary Inverted Pendulum.

Vision-based hand posture detection and recognition for Sign Language — A study

Unlike general gestures, Sign Languages (SLs) are highly structured so that it provides an appealing test bed for understanding more general principles for hand shape, location and motion trajectory. Hand posture shape in other words static gestures detection and recognition is crucial in SLs and plays an important role within the duration of the motion trajectory. Vision-based hand shape recognition can be accomplished using three approaches 3D hand modelling, appearance-based methods and hand shape analysis. In this survey paper, we show that extracting features from hand shape is so essential during recognition stage for applications such as SL translators.

A hybrid method using haar-like and skin-color algorithm for hand posture detection, recognition and tracking

Human hand posture detection and recognition is a challenging problem in computer vision. We introduce an algorithm that is capable to recognize hand posture in a sophisticated background. The system combines two algorithms to achieve better detection rate for hand. Recently Viola et al. in [10] have introduced a rapid object detection scheme; we use this approach to detect the hand posture in the first set of consecutive frames. The chromatic color distribution of skin can be found within this cluster. As the shape of hand posture keep changing in the subsequent frames, the skin regions updated dynamically. The classification of hand posture makes use of static feature for locating and counting hand fingers. Kalman Filter is used to track the face and hand blobs based on their position. In the experiments, we have tested our system in various environments, and results showed effectiveness of the approach.

Evolution of Humanoid Robot and contribution of various countries in advancing the research and development of the platform

A human like autonomous robot which is capable to adapt itself with the changing of its environment and continue to reach its goal is considered as Humanoid Robot. These characteristics differs the Android from the other kind of robots. In recent years there has been much progress in the development of Humanoid and still there are a lot of scopes in this field. A number of research groups are interested in this area and trying to design and develop a various platforms of Humanoid based on mechanical and biological concept. Many researchers focus on the designing of lower torso to make the Robot navigating as like as a normal human being do. Designing the lower torso which includes west, hip, knee, ankle and toe, is the more complex and more challenging task. Upper torso design is another complex but interesting task that includes the design of arms and neck. Analysis of walking gait, optimal control of multiple motors or other actuators, controlling the Degree of Freedom (DOF), adaptability control and intelligence are also the challenging tasks to make a Humanoid to behave like a human. Basically research on this field combines a variety of disciplines which make it more thought-provoking area in Mechatronics Engineering. In this paper a various platforms for Humanoid Robot development are identified and described based on the evolutionary research on robotics. The paper also depicts a virtual map of humanoid platform development from the ancient time to present time. It is very important and effective to analyze the development phases of androids because of its Business, Educational and Research value. Basic comparisons between the different designs of Humanoid Structures are also analyzed in this paper.

Dynamic approach for real-time skin detection

Human face and hand detection, recognition and tracking are important research areas for many computer interaction applications. Face and hand are considered as human skin blobs, which fall in a compact region of colour spaces. Limitations arise from the fact that human skin has common properties and can be defined in various colour spaces after applying colour normalization. The model therefore, has to accept a wide range of colours, making it more susceptible to noise. We have addressed this problem and propose that the skin colour could be defined separately for every person. This is expected to reduce the errors. To detect human skin colour pixels and to decrease the number of false alarms, a prior face or hand detection model has been developed using Haar-like and AdaBoost technique. To decrease the cost of computational time, a fast search algorithm for skin detection is proposed. The level of performance reached in terms of detection accuracy and processing time allows this approach to be an adequate choice for real-time skin blob tracking.

Geometrical analysis on BIOLOID humanoid system standing on single leg

In near future humanoid robots will not only be able to socialize with the human being but will also be able to replace him even in the irksome and dangerous tasks, ranging from rescuing situations to interplanetary exploration. Nowadays many researchers are engaged on this field to make the humanoid more adaptable, intelligent and representable to the dynamic environment. Designing a suitable and efficient gait for the Biped Intelligent Machine (BIM) is a complex task. In this paper a geometrical analysis is presented to identify the movements and positions of the Center of Gravity (CoG) of a humanoid system while it balancing itself in the Single Support (SS) mode. SS mode while standing on single leg is a very critical job for a bipedal system. The paper also exemplifies the results based on the proposed Geometrical Analysis Technique (GAT) which is applied on the BIOLOID humanoid system.

Artificial neural network based autoregressive modeling technique with application in voice activity detection

A new method of estimating the coefficients of an autoregressive (AR) model using real-valued neural network (RVNN) technique is presented in this paper. The coefficients of the AR model are obtained from the synaptic weights and adaptive coefficients of the activation function of a two layer RVNN while the number of neurons in the hidden layer is estimated from over-constrained system of equations. The performance of the proposed technique has been evaluated using sinusoidal data and recorded speech so as to examine the spectral resolution and line splitting as well as its ability to detect voiced and unvoiced data section from a recorded speech. Results obtained show that the method can accurately resolve closely related frequencies without experiencing spectral line splitting as well as identify the voice and unvoiced segments in a recorded speech.

An attempt to develop a Biped Intelligent Machine BIM-UIA

Human like sovereign system that is capable to adapt itself with the changes of its environment and continue to reach its goal is considered as Humanoid Robot. In recent years much progress has been done in the design and development of humanoid and still there have a lot of opportunities in this field. Strategies of lower torso are concern for many researchers to make the system navigating as like as a normal human being do. Designing the toe, ankle, knee, hip and west for lower torso is the complicated and challenging task. Analyzing the walking gait, optimal control of multiple actuators, designing the Degree of Freedom (DoF), adaptability control and intelligence are also the ambitious tasks to make a humanoid to act like a human. This paper exemplifies the initiatives to design and development of a Biped Intelligent Machine (BIM) for Universiti Islam Antarabangsa (UIA) called BIM-UIA, in order to meet the demand of a research platform for humanoid robot navigation system. The paper represents the basic prototype design of the system as the outcomes of the study, mechanical design of a single leg having 6 DoF, component selection schemes, design of the control architecture and hip joint strategy based on three different models. This work is basically a small part of the main project but have a great inspiration for the researchers with the aim to design and construct the future BIM-UIA with lower cost and limited time constraints.