China
Africa
Explore chapters and articles related to this topic
Role of Image Processing in Artificial Intelligence and Internet of Things
Published in Lavanya Sharma, Mukesh Carpenter, Computer Vision and Internet of Things, 2022
An important open-source library for image processing and computer vision application is the Open Source Computer Vision Library or OpenCV. OpenCV was created to give general architecture for computer vision packages. OpenCV is a Berkeley Software Distribution-certified product and it is easier to use in different areas or programs. It’s a free prescient library which allows users to carry out different methods of image processing such as: InputCompression and decompressionEnhancement and recoveryDenoisingSegmentationData extraction.
A Hybrid-DE for Automatic Retinal Image-based Blood Vessel Segmentation
Published in Richard Jiang, Li Zhang, Hua-Liang Wei, Danny Crookes, Paul Chazot, Recent Advances in AI-enabled Automated Medical Diagnosis, 2022
Colin Paul Joy, Kamlesh Mistry, Gobind Pillai, Li Zhang
The proposed system is implemented from scratch using C++ and OpenCV library under Ubuntu operating system. The learning algorithms, such as NN, SVM, NN- and SVM-based ensemble are imported from OpenCV and LibSVM library. The ground truth of the matching image is used to evaluate the performance of the proposed methodology on segmenting vessels from a fundus image. In order to measure the performance of the proposed system, we use accuracy, sensitivity, and specificity value. To calculate the accuracy, sensitivity, and specificity, we have to consider four measures, i.e. true positives, false positives, false negatives, and true negatives. The correctly categorized vessel pixels as vessels are denoted as true positive (TP) and correctly categorized non-vessel pixels as non-vessels are denoted as true negative (TN). Wrongly categorized non-vessels pixels as vessels are denoted as false positive (FP) and wrongly categorized vessels pixels as non-vessels are denoted as false negative (FN). The equations used to calculate accuracy, sensitivity, and specificity value are as follows: Accuracy = (TP + TN)/(TP + TN + FP + FN)Sensitivity = TP/(TP + FN)Specificity = TN/(TN + FP)
Object Detection System with Image and Speech Recognition
Published in Brojo Kishore Mishra, Sanjay Kumar Kuanar, Sheng-Lung Peng, Daniel D. Dasig, Handbook of IoT and Blockchain, 2020
Chung Van Le, Vikram Puri, Sandeep Singh Jagdev
Open-Source Computer Vision (OpenCV) is a real-time library program developed by Gary Bradsky in 1999 [4]. It is an open-source library for both educational and commercial purposes. It supports C, C++ and Python interfaces and optimizes nearly 2,500 algorithms [5]. OpenCV plays a supportive role in the development of Computer Vision into a new futuristic world and enables millions of people to enhance their limits in productive work.
A Prolog application for reasoning on maths puzzles with diagrams
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2022
Riccardo Buscaroli, Federico Chesani, Giulia Giuliani, Daniela Loreti, Paola Mello
At the lowest level, the primitives module is composed of functions written in C++, making use of the OpenCV6 library to identify points, segments, shapes, and text/numbers. The choice of OpenCV is motivated by the fact that it is one of the most famous open source libraries for computer vision. Originally written in C++, this library was progressively applied in several fields, from video surveillance to autonomous driving. Thanks to its portability on different operating systems, its interfaces towards various programming languages, and the integration with CUDA and OpenCL to take advantage of graphical hardware, the current implementation has reached outstanding levels of efficiency and performance. OpenCV offers over 2,500 computer vision algorithms for automated learning, and a series of additional modules which can be compiled from source to provide advanced or experimental features – e.g. object recognition from images, action recognition or object tracing from video streams, etc.
Visual detection and tracking with UAVs, following a mobile object
Published in Advanced Robotics, 2019
Diego A. Mercado-Ravell, Pedro Castillo, Rogelio Lozano
Object detection is accomplished through the Haar classifier on OpenCV [19]. It consists in a Machine Learning technique first developed in [20] which uses Haar-like features in cascade through different levels of the image to determine whether or not a pre-specified rigid object, for which it was trained a priori, is present on the image. The Haar classifier is a supervised classifier that uses a form of AdaBoost organized as a rejection cascade and designed to have high detection rate at the cost of low rejection rate, producing many false positives. One of the main advantages of this method is the computational speed achieved in real-time detection, once the classifier was trained off-line for the desired object, in this case a face. It is important to notice that this method can be trained for almost any mostly rigid object with distinguishing views.
Catalysing assistive solutions by deploying light-weight deep learning model on edge devices
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2023
Kanak Manjari, Madhushi Verma, Gaurav Singal, Vinay Chamola
OpenCV (Open-Source Computer Vision Library) is an open-source computer vision and machine learning software library that helps to accelerate the adoption of machine learning in commercial products by providing a standard infrastructure for computer vision applications. This library contains over 2500 efficient algorithms for detecting and recognising faces, identifying objects, classifying human activities in films, and tracking moving things. This library is widely utilised by businesses, research organisations, and government agencies.