Abstract
Computer vision is becoming an increasingly trendy word in the area of image processing. With the emergence of computer vision applications, there is a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited the computer vision community by producing excellent results in video processing, object recognition, picture classification and segmentation, natural language processing, speech recognition, and many other fields. Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. Several inspirational concepts for the progress of CNN have been investigated, including alternative activation functions, regularization, parameter optimization, and architectural advances. Furthermore, achieving innovations in architecture results in a tremendous enhancement in the capacity of the deep CNN. Significant emphasis has been given to leveraging channel and spatial information, with a depth of architecture and information processing via multi-path. This survey paper focuses mainly on the primary taxonomy and newly released deep CNN architectures, and it divides numerous recent developments in CNN architectures into eight groups. Spatial exploitation, multi-path, depth, breadth, dimension, channel boosting, feature-map exploitation, and attention-based CNN are the eight categories. The main contribution of this manuscript is in comparing various architectural evolutions in CNN by its architectural change, strengths, and weaknesses. Besides, it also includes an explanation of the CNN’s components, the strengths and weaknesses of various CNN variants, research gap or open challenges, CNN applications, and the future research direction.
Highlights
Artificial intelligence is bridging the gap between machine and human talents at a breakneck pace
A convolutional neural network is a method of deep learning that takes an input image and assigns importance to various objects in the image, distinguishing one from the other [1]
In 2015, Ren proposed a rapid region-based CNN (R-CNN) for object detection as an enhancement over R-CNN, which is employed in their research for feature extraction and is able to recognize the boundary and score of objects at various positions concurrently
Summary
Artificial intelligence is bridging the gap between machine and human talents at a breakneck pace. It represents a wide range of CNN architectures, from their conception to their most current advancements and achievements This survey will assist readers in developing architectural novelties in convolutional neural networks by providing a more profound theoretical knowledge of CNN design concepts. This survey will assist readers in learning more about CNN and CNN variants, which helps to improve the field The contributions of this survey paper are summarized below: This is the first review that almost provides each detail about CNN for computer vision, its history, CNN architecture designs, its merits and demerits, application, and the future work to take upon in a single paper. It provides a clear listing of future research trends in the area of CNN for computer vision The organization of this survey paper includes the first section, which presents a methodical comprehension of CNN.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
