Arjun Narang

A humanoid robot is a robot which has anatomy similar to the human body. They are becoming increasingly popular as research platforms, and are well suited for real world applications due to the ease with which humans perform arbitrary tasks in versatile environments. Progress of humanoid robotics is, however, inhibited due to a shortage of affordable platforms with diverse capabilities. In this work, we present a prototype of GATIK-II, a KidSize humanoid robot. This robot prototype is the… Show more

A humanoid robot is a robot which has anatomy similar to the human body. They are becoming increasingly popular as research platforms, and are well suited for real world applications due to the ease with which humans perform arbitrary tasks in versatile environments. Progress of humanoid robotics is, however, inhibited due to a shortage of affordable platforms with diverse capabilities. In this work, we present a prototype of GATIK-II, a KidSize humanoid robot. This robot prototype is the second in the GATIK series of humanoid robots, and has been developed with sufficient power and capabilities so as to be employed for various applications. It has autonomous capabilities and can effectively function in a foreign environment by employing a HaViMo vision module and inertial measurement units. Alternatively, it can also be controlled in real time and via an android based mobile phone, thus exhibiting semi-autonomous mode of operation. Show less

WABIAN-2R is a bipedal humanoid robot which is capable of stretched knee walking with heel-contact and toe-off motions due to the presence of a 2-DoF waist and a passive joint for bending toe motion, and can thus mimic human-like walking. This paper aims to determine the similarity between the walking gait of WABIAN-2R to the natural walking gait of a human of comparable size and stature, on the factors (i) pelvic tilt, (ii) pelvic rotation, (iii) swing and stance percentage, and (iv) double… Show more

WABIAN-2R is a bipedal humanoid robot which is capable of stretched knee walking with heel-contact and toe-off motions due to the presence of a 2-DoF waist and a passive joint for bending toe motion, and can thus mimic human-like walking. This paper aims to determine the similarity between the walking gait of WABIAN-2R to the natural walking gait of a human of comparable size and stature, on the factors (i) pelvic tilt, (ii) pelvic rotation, (iii) swing and stance percentage, and (iv) double limb support and single limb support percentage using inertial measurement units and force-torque sensors. Show less

Diabetic Retinopathy (DR) is a disorder which alters the blood vessels in the retina, and is a common cause of blindness and vision defects in the world today. Hard exudates are associated with diabetic retinopathy, and have been found to be one of the most prevalent clinical signs of retinopathy. One of the research areas which is currently drawing intense interest of scientists and physicians is medical image analysis to aid in clinical diagnosis. Special efforts have been made to develop… Show more

Diabetic Retinopathy (DR) is a disorder which alters the blood vessels in the retina, and is a common cause of blindness and vision defects in the world today. Hard exudates are associated with diabetic retinopathy, and have been found to be one of the most prevalent clinical signs of retinopathy. One of the research areas which is currently drawing intense interest of scientists and physicians is medical image analysis to aid in clinical diagnosis. Special efforts have been made to develop algorithms related to retinal image analysis, providing fundus images enhancement and detecting visual signs of DR. In this paper, we propose a system to analyze the fundus images for the detection of hard exudates using image enhancement, based on Lifting Wavelet Transform (LWT) and an image classifier based on Support Vector Machine (SVM). We prospectively assessed the algorithm performance using a database of 60 retinal images of diabetic subjects with variable color, brightness, and quality. Show less

Face recognition from image or video is a popular topic in biometrics research. It has many important practical applications, like surveillance and access control. It is concerned with the problem of correctly identifying facial images and assigning them to persons in a database. This paper proposes an efficient face recognition method based on Scale Invariant Feature Transform (SIFT) for feature extraction and using Levenberg-Marquardt Backpropagation (LMBP) neural network for classification… Show more

Face recognition from image or video is a popular topic in biometrics research. It has many important practical applications, like surveillance and access control. It is concerned with the problem of correctly identifying facial images and assigning them to persons in a database. This paper proposes an efficient face recognition method based on Scale Invariant Feature Transform (SIFT) for feature extraction and using Levenberg-Marquardt Backpropagation (LMBP) neural network for classification. In this proposed method, we assign the extracted SIFT features of the face images as input vectors to our neural network instead of using just the raw data as the input. Experiments performed on the Yale face database show that the facial images can be recognized by the proposed face identification method efficiently. Also, the traditional face recognition algorithms are compared with the proposed algorithm to show its effectiveness. Show less

Stroke is one of the leading causes of long-term disability worldwide. Present techniques employed for rehabilitation of victims suffering from partial paralysis or loss of function, such as mirror therapy, require substantial amount of resources, which may not be readily available. In traditional mirror therapy, patients place a mirror beside the functional limb, blocking their view of the affected limb, creating the illusion that both the limbs are working properly, which enhances recovery by… Show more

Stroke is one of the leading causes of long-term disability worldwide. Present techniques employed for rehabilitation of victims suffering from partial paralysis or loss of function, such as mirror therapy, require substantial amount of resources, which may not be readily available. In traditional mirror therapy, patients place a mirror beside the functional limb, blocking their view of the affected limb, creating the illusion that both the limbs are working properly, which enhances recovery by enlisting direct simulation. This paper proposes an alternate robot based concept, named Wear-A-BAN, where the rehabilitative task will be carried out by a normal articulated industrial robot. During the proposed rehabilitative procedure, the patients are made to wear a smart sleeve on the functional limb. Movement of this limb is monitored in real-time, by wireless Body-Area Network (BAN) sensors placed inside the sleeve, and copied over the sagittal plane to the affected limb. This procedure results in considerable savings in terms of money and personnel, as even though this procedure does not make the rehabilitation process autonomous, but one therapist can monitor various patients at a time. The industrial robot used is suitable for this purpose due to safety aspects naturally existing in the robot, is relatively cheap in price, and allows comprehensive 3-D motions of the limb. Also, unlike traditional therapy, this procedure allows actual movement of the affected limb. The sensors can also be used for other applications, such as gaming and daily life personal activity monitoring. Show less