Image Processing, Image Scaling, OpenCV Research Papers (original) (raw)

A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two problems arise: identify when two articulated objects in different stances are in the same class of objects, and differentiate the distinct positions of the same object. In both cases, it is necessary to know how correspond the different points or regions of such objects standing in different attitudes. This article presents the Contour-Point Signature; a point descriptor that allows to establish a method to achieve the better matching of points between two figures, and to thus obtain a transformation which relates them. With this descriptor, we can achieve more accurate shape features and implement more efficient retrieval under multi-resolution. In addition, CPS is robust to rigid translation, scaling, rotation and independent of the origin point. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also presented.

Face recognition systems are used in practically every industry in this digital age. One of the most widely utilized biometrics is face recognition. It can be used for security, authentication, and identity, among other things. Despite its low accuracy relative to iris and fingerprint identification, it is extensively utilized because it is a contactless and non-invasive technique. Face recognition systems can also be used to track attendance in schools, colleges, and companies. Because the existing manual attendance system is time consuming and difficult to maintain, this system intends to create a class attendance system that employs the concept of face recognition. There's also the possibility of proxy attendance. As a result, the demand for this system grows. Database development, face detection, face recognition, and attendance updating are the four steps of this system. The photos of the kids in class are used to generate the database. Faces are discovered and recognized from the classroom's live streaming footage. At the end of the session, the attendance will be mailed to the appropriate faculty.

MÉTODOS DE SUAVIZADO Y REDUCCIÓN DE RUIDO EN IMÁGENES DIGITALES EN PYTHON, CON "opencv". El objetivo del presente trabajo es el de analizar algunos de los procedimientos de filtrado y suavizado de imágenes que nos ofrece la librería "opencv" en Python, y de como podemos usarlos para eliminar el ruido (consistente en la perturbaciones en la señal que se produce en el proceso de digitalización, el cual, se traduce en la presencia de pixeles cuyo color no se corresponde con el de la imagen original) que puede haber en las mismas. Los primeros algoritmos y funciones de "opencv" que vamos a probar, están orientados a suavizar imágenes digitales afectadas por ruido de tipo "gaussiano", del que es ejemplo el presente en la siguiente imagen, que tomaremos como ejemplo: "Image_noise-example.jpg": El procedimiento que usarán nuestros algoritmos, consiste, a grandes rasgos, en el uso de una "ventana" o "caja" (a la que llamamos comunmente, "kernel") que desplazándose sobre la imagen, irá posicionando encima de cada pixel (de modo que este quede en el centro de la misma) asignándole a

- by Antonio Alfonso Martinez
- •
- Computer Vision, Python, Programming, OpenCv or Computer Vision

Nowadays, Covid-19 is a serious issue, which is outspread all over the world. As, this is a contagious illness, so people maintaining social distance to prevent it. Government of every country announced lockdown to the respective countries to stop its rapid spread. For this reason, most of the sectors especially the education sector is going through a crisis. Students cannot go to their institution because of this pandemic. Therefore, Government of every country decided to start online class in this pandemic situation. It is very much tough to continue study through online rather than intuitional class. Not only students but also the teachers also faced many problems to do the online class properly because this is a new process for both of them. In online class, teachers have to identify that the students are present or not. If the students turn on their webcam, then the teachers can take their attendance easily. In this research, researchers tried to develop a prototype using R programming language and machine learning tools that can detect and recognize students' face easily that might help teachers to take attendance without any hassle. Researchers took help of Artificial Intelligence as well as used Machine Learning tools to complete this research. People using artificial intelligence because people do mistake but machine cannot do mistake so the in here the error rate is low. Machine learning is also important because it is time consuming, this machine have to trained up so that it is act as human and solve all the problems easily. That is why various types of programming language are needed to train up the machine. In here, Researchers mainly used OpenCV that is a built-in package of R programming language, which is used for real time face detection and so on.

A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two problems arise: identify when two articulated objects in different stances are in the same class of objects, and differentiate the distinct positions of the same object. In both cases, it is necessary to know how correspond the different points or regions of such objects standing in different attitudes. This article presents the Contour-Point Signature; a point descriptor that allows to establish a method to achieve the better matching of points between two figures, and to thus obtain a transformation which relates them. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also defined.

- by Waldemar Villamayor-Venialbo and +1
- •
- Computer Vision, Robot Vision, Object Recognition (Computer Vision), Image Recognition (Computer Vision)

The crowd counting problem aims to estimate the number of people within an image or a video-frame from surveillance cameras. Accurate crowd counting is a challenging problem due to scale variations and the lack of a big dataset of images labelled with the exact number of people depicted. This problem is usually solved by estimating the density map generated from the people's location annotations or by leveraging deep convolutional networks. In this paper, we propose an alternative model that combines relevant features of other models [1, 16] recently introduced in the literature. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on 2 public crowd counting datasets. Through extensive experiments, we were able to get 92.8 and 16.9 as MAE, 148.2 and 28.1 as MSE in two difficult datasets: ShanghaiTech part A and B respectively.

We have developed a system for automatic facial expression recognition, which runs on Google Glass and delivers real-time social cues to the wearer. We evaluate the system as a behavioral aid for children with Autism Spectrum Disorder (ASD), who can greatly benefit from real-time non-invasive emotional cues and are more sensitive to sensory input than neurotypically developing children. In addition, we present a mobile application that enables users of the wearable aid to review their videos along with auto-curated emotional information on the video playback bar. This integrates our learning aid into the context of behavioral therapy. Expanding on our previous work describing in-lab trials, this paper presents our system and application-level design decisions in depth as well as the interface learnings gathered during the use of the system by multiple children with ASD in an at-home iterative trial.

- by Titas De and +1
- •
- Artificial Intelligence, Human Computer Interaction, Pediatrics, Computer Vision

Image scaling is a very important technique and has been widely used in many image processing applications. An adaptive edge-enhanced image scalar adopted in this paper is a low complexity image scaling algorithm. It consists of linear space variant edge detector, a low complexity sharpening spatial filter, and a simplifed bilinear interpolation. The proposed image scaling algorithm uses hardware sharing technique in order to reduce the computational complexity and to minimize the computing resources needed. Furthermore, Error Tolerant Adder(ETA) Unit is used to overcome redundant calculation performed in Reconfigurable Calculation Unit (RCU), which reduce the computational resources and hardware cost required, which further results in reduction of gate count. Error tolerant adder (SPST) adder results in reduction in power consumption and filter out the unused switching power and also increases speed.