Explore chapters and articles related to this topic
Deep Learning for Analyzing the Data on Object Detection and Recognition
Published in R. Sujatha, S. L. Aarthy, R. Vettriselvan, Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics, 2021
Considering Computer Vision, object detection deals with the detection in a visual image or video of instances of objects from a given class (Zhao et al., 2019). This specifies that the location object is displayed in the picture and scales one or more of the objects (Liu et al., 2020). Object detection is used to identify every object introduced to an image regardless of position, height, rendering, or other factors. Once the object is correctly identified, additional knowledge such as object class, object identification, and object detection is retrieved. Object detection consists primarily of two tasks: localization of objects and object classification. Object localization, by drawing a bounding box around it, specifies the position and size of one or more instances of an object. Object classification refers to the mechanism by which the label of a class is applied to the object. In order to detect, systems of object detection create a model from the training dataset, and, for generalization, a broad set of training data is required (Liu et al., 2017).
Computer Vision Concepts and Applications
Published in S. Kanimozhi Suguna, M. Dhivya, Sara Paiva, Artificial Intelligence (AI), 2021
The incorporation of deep learning and artificial neural networks in almost all fields of computer vision has made it possible to replicate human vision. Computer vision works basically with images and includes techniques such as image analysis, scene analysis, and image understanding. Computer vision without artificial intelligence works well but including deep learning methods achieves accurate results. Researchers have identified that computer vision is more effective in identifying image patterns than human cognitive systems. This chapter includes the most important aspects of computer vision like feature extraction, object detection, and image segmentation. The applications of computer vision have been growing exponentially, especially in terms of control systems, detecting events, modelling environments, target detection, automatic inspection, navigation, etc.
Intelligent Transport Systems and Traffic Management
Published in Rajshree Srivastava, Sandeep Kautish, Rajeev Tiwari, Green Information and Communication Systems for a Sustainable Future, 2020
Pranav Arora, Deepak Kumar Sharma
Computer vision is defined as the study that aims to develop ways to help computers with the ability to visualize and understand digital images in the form of photographs and videos. In terms of engineering, computer vision is the ability to automate tasks that a living visualizing system is able to perform. The main aim of a computer vision system is to be able to extract information from images. Computer vision is basically a subset of artificial intelligence, where we apply various kinds of machine learning algorithms to classify images in order to maximize the accuracy of our output in the form of a prediction. We see many examples of computer vision in our daily commuting lives, from the automated cruise control system in cars to automated parking and entry systems. Indeed, the field of computer science has revolutionized our ways to commute and will continue to do so in the future as well. Figure 3.7 shows us how computer vision is related to better-known terms like machine learning and artificial intelligence.
Dance Video Motion Recognition Based on Computer Vision and Image Processing
Published in Applied Artificial Intelligence, 2023
The key to video human motion recognition is to reasonably preprocess the original video image, and then extract the features of the video image and describe and classify it (Bao, Liu, and Yu 2022; Rao, Lu, and Jie 2019). There are many limitations in the acquisition of information by the human visual system, which is not conducive to the understanding and processing of information (Tao, Guo, and Li). Computer vision is an auxiliary means that can help people accurately obtain information. It can simulate, expand and even extend human intelligence by letting machines “see,” and can solve large-scale and complex visual tasks (Alam, Ofli, and Imran 2018). At present, computer vision is widely used in image generation, vehicle monitoring, target tracking and so on. It has broad application prospects in various fields such as medical treatment, agriculture and transportation. In recent years, the ability of computer image processing has been continuously improved, and the development of computer vision has become increasingly mature (Glancova, Do, and Sanghavi 1053).
A review of advances in image inpainting research
Published in The Imaging Science Journal, 2023
Hong-an Li, Liuqing Hu, Jun Liu, Jing Zhang, Tian Ma
In recent years, as the core technology of artificial intelligence, deep learning has been highly valued because of its powerful learning algorithms and rich application scenarios, and has achieved remarkable success in the field of computer vision. Inpainting technology based on deep learning has been well developed [22–25], and the development of deep learning technology has promoted the significant improvement of inpainting performance. Since the concept of Auto-Encoder [26] was proposed, the evolving and advancing neural networks have been applied to image inpainting, and researchers have tried to use the encoding and decoding structure in Auto-Encoder networks to image inpainting tasks. By capturing the contextual information around the missing regions of an image and encoding it through an encoder to extract the potential feature representation of the image, and a decoder to restore the original image data to generate content of the missing region, while continuously optimizing the inpainting result by adding various constraints. Subsequently, LeNet [27], ResNet [28], and VGG [29] has constantly been proposed, which have performed well in image inpainting. 2014 Goodfellow et al. [30] proposed Generative Adversarial Network (GAN), which computer image inpainting development went further [31–43]. In the training process, the goal of the generator is to try to generate real images to deceive the discriminator, while the goal of the discriminator is to try to distinguish the images generated by the generator from the real ones.
The role of artificial intelligence in shaping the future of Agile fashion industry
Published in Production Planning & Control, 2022
Mujahid Mohiuddin Babu, Shahriar Akter, Mahfuzur Rahman, Md Morsaline Billah, Dieu Hack-Polay
In AI, computer vision is regarded as a scientific area, which provides training to a machine to accomplish high-level interpretation of the images or videos. Computer vision algorithms perform several tasks which include extraction, pre-processing, exploration of the high dimensional data and generation of supervised or unsupervised models. For proper understanding of images and extraction of useful information, models utilize the concept and knowledge of geometry, statistics, physics, and machine learning theory (Forsyth and Ponce 2003). Computer vision also includes object recognition, video tracking, motion estimation etc. Machine vision is used in textile manufacturing to conduct automation of many industrial applications, such as inspection and process control (Steger, Ulrich, and Wiedemann 2018). Other popular applications of image recognition and vision are content-based image retrieval systems, virtual try-on and augmented reality, which are now frequently used in this industry (Yuan et al. 2013; Cushen and Nixon 2011).