Deep Learning vs. Traditional Computer Vision (original) (raw)
Related papers
Advances in intelligent systems and computing, 2020
Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised.
Deep Learning Applied in Computer Vision
Multidisciplinary International Journal of Research and Development (MIJRD), 2021
Computer vision is a multidisciplinary field in computational intelligence and artificial intelligence that guide intelligent systems and machines towards understanding the content of images or video. It has come under the spotlight in recent times due to the remarkable advancement and breakthroughs day-by-day such as autonomous driving, intelligent systems, pedestrian system, robotics, medical imaging, remote sensing, object detection, security, speech sequence, image registration, biometric technologies, image retrieval and video processing to mention just a few. The aim of this work is to provide a systematic review in the application of deep learning in various aspects of computer vision that is object detection, object classification, scene classification, image segmentation, image retrieval, image registration, object recognition, feature extraction, image fusion and anomaly detection by providing detail description in a systematic way of all the deep learning techniques; Convolutional Neural Network (CNN), Deep Boltzmann Machine (DBM) and Deep Belief Network (DBN) that are applied in solving this problem of computer vision. This work also explored all the review and survey researches that applied deep learning techniques in computer vision in a systematic format and identify the countries that the researches were conducted which is one of the unique attributes of this paper that makes it exceptional in a state-of-art review and surveys. In addition to datasets that were used in the recent research of computer vision with the software and toolboxes used for the implementation of deep learning techniques in computer vision. We have also identified all the top journals (ISPRS Journal of Photogrammetry and Remote sensing, IEEE Geoscience and Remote Sensing Letter, IEE Transaction of Geoscience and Remote sensing etc.) and conferences proceedings (IEEE Conference of Computer vision and Pattern recognition) for advanced publication of computer vision researches in the world. This work would serve as a roadmap for any researcher that wants to use deep learning algorithms in computer vision.
Deep Learning For Computer Vision Tasks: A review
ArXiv, 2018
Deep learning has recently become one of the most popular sub-fields of machine learning owing to its distributed data representation with multiple levels of abstraction. A diverse range of deep learning algorithms are being employed to solve conventional artificial intelligence problems. This paper gives an overview of some of the most widely used deep learning algorithms applied in the field of computer vision. It first inspects the various approaches of deep learning algorithms, followed by a description of their applications in image classification, object identification, image extraction and semantic segmentation in the presence of noise. The paper concludes with the discussion of the future scope and challenges for construction and training of deep neural networks.
The upsurge of deep learning for computer vision applications
International Journal of Electrical and Computer Engineering (IJECE), 2020
Artificial intelligence (AI) is additionally serving to a brand new breed of corporations disrupt industries from restorative examination to horticulture. Computers can’t nevertheless replace humans, however, they will work superbly taking care of the everyday tangle of our lives. The era is reconstructing big business and has been on the rise in recent years which has grounded with the success of deep learning (DL). Cyber-security, Auto and health industry are three industries innovating with AI and DL technologies and also Banking, retail, finance, robotics, manufacturing. The healthcare industry is one of the earliest adopters of AI and DL. DL accomplishing exceptional dimensions levels of accurateness to the point where DL algorithms can outperform humans at classifying videos & images. The major drivers that caused the breakthrough of deep neural networks are the provision of giant amounts of coaching information, powerful machine infrastructure, and advances in academia. DL is...
A taxonomy of Deep Convolutional Neural Nets for Computer Vision
Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative – that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e., deep-networks) exist, a survey specific to computer vision is missing. We specifically consider one form of deep networks widely used in computer vision – convolutional neural networks (CNNs). We start with “AlexNet” as our base CNN and then examine the broad variations proposed over time to suit different applications. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.
Deep Learning based Computer Vision: A Review
Computer vision tasks include methods for acquiring, processing, analyzing and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information. It may be in the forms of decisions. The feature extraction is strongly carried out by the deep learning with promising benefits, it has been broadly utilized as a part of the field of computer vision and among others, and step by step supplante d conventional machine learning algorithms. This work first presents state of the art of deep learning in connection with computer vision. Later it introduces deep learning concept and methods of deep learning. It then focuses some of the computer vision applications including face recognition, object recognition and activity recognition.
Deep Learning Networks for New Computer Vision Technologies
International Journal of Computer Science and Information Technology Research, 2017
Deep Learning can is a machine learning subject in Artificial Intelligence with networks that have the ability of learning without supervision from unlabeled or unstructured data. It is also referred to as Deep Neural Learning. Deep learning networks have proved to be effective in solving various problems. They have also been effective in various applications in computer technology and thus they have greatly helped in moving the computer technology to another level. Deep learning networks have the ability that is remarkable in deriving meaning from data that is complicated. They also help in detecting complex trends. A network that is trained can be considered to be an expert in analyzing data. The essay examines various ways in which the deep learning networks have been applied and used.
Comprehensive Study on Image Using Deep Learning Techniques
IRJCS:: AM Publications,India, 2024
In recent years, the field of computer vision has witnessed significant advancements, particularly in image classification, owing to the remarkable progress in deep learning techniques. This research paper presents a study on image classification using architectures, challenges, and potential applications. The primary objective is to analyse the effectiveness of deep lear image classification tasks and provide insights into the current trends and future directions in this rapidly evolving domain
A Comprehensive Review of Deep Learning Architectures for Computer Vision Applications
American Academic Scientific Research Journal for Engineering, Technology, and Sciences, 2021
The emergence of machine learning in the artificial intelligence field led the world of technology to make great strides. Today"s advanced systems with the ability of being designed just like human brain functions has given practitioners the ability to train systems so that they could process, analyze, classify, and predict different data classes. Therefore, the machine learning field has become a hot topic for scientists and researchers to introduce the best network with the highest performance for such mentioned purposes. In this article, computer vision science, image classification implementation, and deep neural networks are presented. This article discusses how models have been designed based on the concept of the human brain. The development of a Convolutional Neural Network (CNN) and its various architectures, which have shown great efficiency and evaluation in object detection, face recognition, image classification, and localization, are also introduced. Furthermore, the utilization and application of CNNs, including voice recognition, image processing, video processing, and text recognition, are examined closely. A literature review is conducted to illustrate the significance and the details of Convolutional Neural Networks in various applications.
Deep Learning Techniques for Image Recognition (Machine Learning)
Path of Science, 2024
Deep learning (DL), a sophisticated subset of machine learning (ML), has emerged as a transformative force within the broader realm of artificial intelligence (AI). By leveraging architectures such as convolutional neural networks (CNNs), DL has significantly advanced image recognition capabilities, enabling systems to identify and classify visual data with remarkable precision accurately. This technology is not only applicable to image recognition. Still, it has also made strides in diverse areas, such as speech recognition, language translation, automated gameplay, healthcare diagnostics, and the development of self-driving vehicles. The success of DL in this domain can be attributed to its ability to learn hierarchical representations of data, allowing for improved feature extraction and pattern recognition. Despite its impressive performance, deep learning is not without its limitations. Key challenges include its reliance on vast amounts of labelled data, which can be difficult and expensive to obtain, its lack of common sense reasoning and difficulties in addressing complex, multifaceted problems.