Analisis Algoritma Shi-Tomasi Dalam Pengujian Citra Senyum Pada Wajah Manusia

Problems in image processing to obtain the best smile are strongly influenced by the quality, background, position, and lighting, so it is very necessary to have an analysis by utilizing existing image processing algorithms to get a system that can make the best smile selection, then the Shi-Tomasi Algorithm is used. the algorithm that is commonly used to detect the corners of the smile region in facial images. The Shi-Tomasi angle calculation processes the image effectively from a target image in the edge detection ballistic test, then a corner point check is carried out on the estimation of translational parameters with a recreation test on the translational component to identify the cause of damage to the image, it is necessary to find the edge points to identify objects with remove noise in the image. The results of the test with the shi-Tomasi algorithm were used to detect a good smile from 20 samples of human facial images with each sample having 5 different smile images, with test data totaling 100 smile images, the success of the Shi-Tomasi Algorithm in detecting a good smile reached an accuracy value of 95% using the Confusion Matrix, Precision, Recall and Accuracy Methods.

Automated determination of interfacial tension and contact angle using computer vision for oil field applications

Contact angle and surface tension are the two most widely used surface analysis approaches for reservoir fluid characterization in petroleum industries. The pendant drop method has among the most widely used techniques for the estimation of surface tension. The present work utilizes a python-based computer program to automatically determine interfacial tension (IFT) and contact angle from the pendant drop image acquired from a typical pendant drop apparatus. The proposed program uses python-based image processing libraries for the analysis of the pendant drop image. Also, the program is tested on images acquired from the standard solutions for the IFT and contact angle calculation showing promising results with a standard deviation of less than 1.7 mN/m.

Deep Neural Networks for Human Action Recognition

In deep neural networks, human action detection is one of the most demanding and complex tasks. Human gesture recognition is the same as human action recognition. Gesture is defined as a series of bodily motions that communicate a message. Gestures are a more natural and preferable way for humans to engage with computers, thereby bridging the gap between humans and robots. The finest communication platform for the deaf and dumb is human action recognition. We propose in this work to create a system for hand gesture identification that recognizes hand movements, hand characteristics such as peak calculation and angle calculation, and then converts gesture photos into text. Index Terms: Human action recognition, Deaf and dumb, CNN.

Simulation of the movement of the supporting leg of an exoskeleton with two links of variable length in 3D

A two-link model of exoskeleton with variable-length links for supporting the lower limbs of the human musculoskeletal system is proposed in the article. The researched model differs from the existing ones by the variable-length links, and by the angle calculation method. While in the existing models, the angles are calculated from the regular direction – from vertical, or from horizontal, – in the proposed research they are calculated between the links. As for practical exoskeleton implementation, the proposed method of angle calculation is appropriate to the actual working conditions of the electrical motors with the reduction gears installed in the hinges, which change the angles between the links. The construction of a variable-length exoskeleton link consists of two absolutely solid weighty sections located at both ends of the link and one weightless section between them in the center of the link. In the weightless section, there is a drive that creates a control longitudinal force, which realizes the increase or decrease in the length of the link in the required manner and provides the necessary maintenance of the length of the link when the person moves in the exoskeleton. The links are connected to each other using spherical hinges. Drives are installed in each hinge, creating control torques, which provide a relative rotational movement of the links. The jointly controlling longitudinal forces and moments realize the maintenance of the posture or the movement of the link in the required manner and, in relation to the exoskeleton, the repetition of the basic biomechanical properties of the human musculoskeletal system. The mathematical model in the form of the system of Lagrange differential equations of the second kind is obtained. The obtained mathematical model is examined for existence and uniqueness of the Cauchy solution. The kinematic trajectory of the link motion has been synthesized, which simulates the anthropomorphic movement of the supporting leg during the single-support phase of movement, and the control actions required for its implementation has been found. The significance of the results obtained in the process of modeling lies in the ability to create active exoskeletons, prostheses in medicine, anthropomorphic robots, and spacesuits that take into account the biomechanical features of the functioning of the human musculoskeletal system.

HOLBP: Remote Sensing Image Registration Based on Histogram of Oriented Local Binary Pattern Descriptor

Image registration has always been an important research topic. This paper proposes a novel method of constructing descriptors called the histogram of oriented local binary pattern descriptor (HOLBP) for fast and robust matching. There are three new components in our algorithm. First, we redefined the gradient and angle calculation template to make it more sensitive to edge information. Second, we proposed a new construction method of the HOLBP descriptor and improved the traditional local binary pattern (LBP) computation template. Third, the principle of uniform rotation-invariant LBP was applied to add 10-dimensional gradient direction information to form a 138-dimension HOLBP descriptor vector. The experimental results showed that our method is very stable in terms of accuracy and computational time for different test images.