Adaptative Context Normalization: A Boost for Deep Learning in Image Processing

IntroductionWith the rapid development of artificial intelligence and machine learning technology, image processing technology based on artificial intelligence and machine learning has been applied in various fields, which effectively solves the multi-classification problem of similar targets in traditional image processing technology.MethodsThis paper summarizes the various algorithms of artificial intelligence and machine learning in image processing, the development process of neural network model, the principle of model and the advantages and disadvantages of different algorithms, and introduces the specific application of image processing technology based on these algorithms in different scientific research fields.Results And DiscussionThe application of artificial intelligence and machine learning in image processing is summarized and prospected, in order to provide some reference for researchers who used artificial intelligence and machine learning for image processing in different fields.

In recent years, with the deepening of deep learning reform and the rapid development of reeling neural network technology, the model applied by deep learning has been greatly different from the traditional, the original learning program and learning model need to be developed and changed with the progress of the times. Therefore, the purpose of this paper is to rely on the network model derived from the deep learning of reel neural networks to solve the problems in the field of image processing. Based on the technical safety code and data security protection of reticulation neural network, this paper learns in depth the computing power of reel neural network while taking into account the deep learning corresponding to the refragstortic neural network model, and then collects, organizes and analyzes the information related to image processing, uses sandbox simulation operation, modeling, and a variety of intelligent algorithms to get the final result. This paper mainly uses the target detection algorithm to experiment. The experimental results show that the application of co product neural network model deep learning in image processing can be improved more effectively by using suitable algorithms.

Artificial Intelligence has accelerated research on autonomous vehicles in the past few years. However, it is not easy to achieve full autonomy on account of the essence of a complex and dynamic driving environment. Fortunately, the rapid development of deep learning has made great progress, which can be used to solve problems about image processing in the autonomous vehicles field. This paper offers a comprehensive review of the recent deep-learning-based image processing methods that leverage data detected. The paper gives a brief overview of deep learning, discussing basic concepts and principles. We also discuss the common models and architectures of deep learning and introduce typical deep learning techniques: convolutional neural networks (CNN). Furthermore, we divided the application of deep learning in the autonomous vehicles into three parts and discuss them respectively. Finally, we review the disadvantages of the application of deep learning in image processing for autonomous vehicles. On this basis, we put forward our insights and point out promising research directions.

The rapid development of Internet technology has made the whole society enter the era of big data. In recent years, the development trend of artificial intelligence and machine learning has also risen sharply. Informatization has become an important feature of the current era. As an indispensable common information carrier, images not only facilitate people’s communication, but also promote the development of deep learning processing image technology. Based on this, this paper analyzes the application of computer deep learning in image processing. Firstly, the deep learning is summarized, its concept and origin are briefly introduced, and then the technical classification, development process and processing purpose of image processing are expounded. Finally, the application of computer deep learning in four aspects is analyzed in detail in image recognition, image denoising, image classification and image enhancement, and it has certain significance for promoting the research and application of deep learning.

During the past decade, deep learning is one of the essential breakthroughs made in artificial intelligence. In particular, it has achieved great success in image processing. Correspondingly, various applications related to image processing are also promoting the rapid development of deep learning in all aspects of network structure, layer designing, and training tricks. However, the deeper structure makes the back-propagation algorithm more difficult. At the same time, the scale of training images without labels is also rapidly increasing, and class imbalance severely affects the performance of deep learning, these urgently require more novelty deep models and new parallel computing system to more effectively interpret the content of the image and form a suitable analysis mechanism. In this context, this survey provides four deep learning model series, which includes CNN series, GAN series, ELM-RVFL series, and other series, for comprehensive understanding towards the analytical techniques of image processing field, clarify the most important advancements and shed some light on future studies. By further studying the relationship between deep learning and image processing tasks, which can not only help us understand the reasons for the success of deep learning but also inspires new deep models and training methods. More importantly, this survey aims to improve or arouse other researchers to catch a glimpse of the state-of-the-art deep learning methods in the field of image processing and facilitate the applications of these deep learning technologies in their research tasks. Besides, we discuss the open issues and the promising directions of future research in image processing using the new generation of deep learning.

The modern-day society is increasingly dependent on computer-aided tools and techniques. Digital imaging techniques have a tremendous impact on our day-to-day lives. Image processing is a vital component in the field of biological sciences and has the potential to drastically change the computer-human interface. Image processing refers to the conversion of an image into a digital form followed by enhancement of the image in order to extract useful information from it that are indiscernible by human ocular perceivers. Rapid advances in image processing, computerized reconstruction of an image and allied advancements in image analysis algorithms and the application of artificial intelligence has spurred a revolution in the field of medical and diagnostic imaging. Deep learning, a type of Artificial Neural Network (Machine Learning), is resurfacing as a powerful tool for its utilization in big healthcare data. The integration of deep learning techniques to image processing has the potential to add momentum to the dermatological imaging and promote early and accurate diagnosis of skin lesions. This review attempts to discuss the fundamentals of image processing, its importance, various clinical imaging modalities in use in the field of dermatology and application of deep learning algorithms in dermatological imaging, accentuating the inadequacies and future research prospects.

Food is the paramount necessity of the people. With the progress of society and the improvement of social welfare system, the living standards of people all over the world are constantly improving. The development of medical industry improves people's health level constantly, and the world population is constantly climbing to a new peak. With the continuous development of deep learning in recent years, its advantages are constantly displayed, especially in the aspect of image recognition and processing, it drives into the distance. Thanks to the superiority of deep learning in image processing, the combination of remote sensing images and deep learning has attracted more attention. To simulate the four key factors of rice yield, this article tries a regression model with a combination of various characteristic independent variables. In this article, the selection of the best linear and nonlinear regression models is discussed, the prediction performance and significance of each regression model are analyzed, and some thoughts are given on estimation of actual rice yield.

This book chapter provides a comprehensive exploration of deep learning architectures and their transformative impact on image processing, emphasizing the pivotal roles of Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). The chapter begins with a historical context, tracing the evolution of image processing techniques from traditional algorithms to cutting-edge deep learning approaches. It delves into fundamental concepts, highlighting advancements in CNNs and emerging trends such as self-supervised learning. Additionally, the chapter examines the practical applications of these models, showcasing case studies that illustrate their effectiveness in image classification, object detection, and data augmentation. Challenges and limitations associated with generative models are also addressed, underscoring the need for ongoing research and development. The synthesis of these topics positions the chapter as a significant contribution to the field, offering insights into the future directions of deep learning in image processing.

A user-friendly deep learning application for accurate lung cancer diagnosis.

With deep learning techniques, a revolution has taken place in the field of image processing and computer vision. The survey paper emphasizes the importance of representation learning methods for machine learning tasks. Deep learning, the modern machine learning is commonly used in the vision tasks—semantic segmentation, image captioning, object detection, recognition, and image classification. The paper focuses on the recent developments in the domain of remote sensing, retinal image understanding, and scene understanding based on newly proposed deep architectures. The author finds it quite intriguing of the classical building blocks of image segmentation (Gabor, K-means), shifting gear, and contributing to image recognition tasks based on deep learning (Gabor convolutional network, K-means dictionary learning). The survey makes an attempt to serve as a concise guide in providing latest works in computer vision applications based on deep learning and giving futuristic insights.

Highlights A broiler mortality removal robot was successfully developed. The broiler shank was the target anatomical part for detection and mortality pickup. Higher light intensities improved the performance of detection and pickup performance. The final success rate for picking up dead birds was 90.0% at the 1000-lux light intensity. Abstract. Manual collection of broiler mortality is time-consuming, unpleasant, and laborious. The objectives of this research were: (1) to design and fabricate a broiler mortality removal robot from commercially available components to automatically collect dead birds; (2) to compare and evaluate deep learning models and image processing algorithms for detecting and locating dead birds; and (3) to examine detection and mortality pickup performance of the robot under different light intensities. The robot consisted of a two-finger gripper, a robot arm, a camera mounted on the robot’s arm, and a computer controller. The robot arm was mounted on a table, and 64 Ross 708 broilers between 7 and 14 days of age were used for the robot development and evaluation. The broiler shank was the target anatomical part for detection and mortality pickup. Deep learning models and image processing algorithms were embedded into the vision system and provided location and orientation of the shank of interest, so that the gripper could approach and position itself for precise pickup. Light intensities of 10, 20, 30, 40, 50, 60, 70, and 1000 lux were evaluated. Results indicated that the deep learning model “You Only Look Once (YOLO)” V4 was able to detect and locate shanks more accurately and efficiently than YOLO V3. Higher light intensities improved the performance of the deep learning model detection, image processing orientation identification, and final pickup performance. The final success rate for picking up dead birds was 90.0% at the 1000-lux light intensity. In conclusion, the developed system is a helpful tool towards automating broiler mortality removal from commercial housing, and contributes to further development of an integrated autonomous set of solutions to improve production and resource use efficiency in commercial broiler production, as well as to improve well-being of workers. Keywords: Automation, Broiler, Deep learning, Image processing, Mortality, Robot arm.

In this work we introduce GrapheNet, a deep learning framework based on an Inception-Resnet architecture using image-like encoding of structural features for the prediction of the properties of nanographenes. The model is validated on datasets of computed structure/property data on graphene oxide and defected graphene nanoflakes. By exploiting the planarity of quasi-bidimensional systems and through encoding structures into images, and leveraging the flexibility and power of deep learning in image processing, Graphenet achieves significant accuracy in predicting the physicochemical properties of nanographenes. This approach is able to efficiently encode structures composed of hundreds of atoms, scaling efficiently with the size of the model and enabling the prediction of the properties of large systems, which contrasts with the limitations of current atomistic-level representations for deep learning applications. The approach proposed based on image encoding exhibit a significant numerical accuracy and outperforms the computational efficiency of current representations of materials at the atomistic level, with significant advantages especially in the representation of nanostructures and large planar systems.

Deep learning is a subfield of machine learning. Computer vision is one of the technological advances that utilizes deep learning in image processing, object classification, and object detection. In the Object Detection, there have been various models that can detect objects with different characteristics, and with so many models that have been developed, it takes longer to determine which model is suitable for the needs of a project because it requires comparisons between each model. In this study, an analysis was conducted by comparing three models that utilize Deep Learning to detect car and bus objects, namely Faster-RCNN with ResNet50, SSD with MobileNet, and EfficientDet with D0. Each model is run using TensorFlow Object Detection. The models will be trained using a custom dataset containing of 52 images and will be trained in 3000 steps. Based on experiments, it is known that from the comparison of mAP, Faster-RCNN ResNet50 has the highest score of 0.453, and the lowest is EfficientDet D0 with 0.274; for the comparison of Average Recall, Faster-RCNN ResNet50 has the highest score with 0.337, and the lowest is EfficientDet D0 with 0.190, as well as for model size comparison, EfficientDet D0 has the smallest size with 290 MB, and the largest is Faster-RCNN ResNet50 with 1280 MB.

Image feature matching is an integral task for many computer vision applications such as object tracking, image retrieval, etc. The images can be matched no matter how the image changes owing into the geometric transformation (such as rotation and translation), illumination, etc. Also due to the successful application of the deep learning in image processing, the deep learning method has an advantage in feature extraction of images. In this paper, we adopt a deep Convolutional neural network (CNN) model, which attention on image patch, in image feature points matching. CNN obtains the feature by convolution kernel which parameters are achieved by learning. So it has strong ability to express feature. Compared with other methods, experimental results indicate the proposed method has higher accuracy and completed efficiently.

This study presents the development of a mobile identification system that detects biological butterfly characteristics through deep learning by capturing images. The challenge identified is that butterfly identification and recognition are difficult tasks because there are too many species, and it is hard to classify the types of butterfly species. Butterflies are also difficult to differentiate from each other, and limited studies are done using computer database referrals for butterflies’ characterization. This study aims to develop an automated computer program to easily identify the species of butterflies. Deep learning in image processing is programmed, which can control the qualification, segmentation, and classification of images and automatically detect butterfly characterization. The design system consists of three stages: capture, feature extraction, and butterfly recognition. Then, multiple recognition clues such as shape, color, texture, and size are extracted and analyzed to analyze and recognize the butterfly. This approach is faster and less complex than the previous approach. The result successfully presents a convolutional neural network (CNN) to classify images after training and characterization. The graphics processing unit (GPU) that trains the image dataset presents 86% image accuracy in the allocated time. This research is significant in such a way that new butterfly species will be automatically collected and stored on the online server. The information could be treasured as a valuable butterfly database.