Performance Analysis of Deep Neural Networks Using Computer Vision

INTRODUCTION: In recent years, deep learning techniques have been made to outperform the earlier state-of-the-art machine learning techniques in many areas, with one of the most notable cases being computer vision. Deep learning is also employed to train the neural networks with...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nidhi Sindhwani, Rohit Anand, Meivel S., Rati Shukla, Mahendra Yadav, Vikash Yadav
Formato:	article
Lenguaje:	EN
Publicado:	European Alliance for Innovation (EAI) 2021
Materias:	computer vision object detection deep learning deep neural network image classification artificial intelligence machine learning convolutional neural network accuracy Computer engineering. Computer hardware TK7885-7895 Systems engineering TA168
Acceso en línea:	https://doaj.org/article/b6138f8763064cb09e6223614725a70f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b6138f8763064cb09e6223614725a70f
record_format	dspace
spelling	oai:doaj.org-article:b6138f8763064cb09e6223614725a70f2021-11-30T11:07:41ZPerformance Analysis of Deep Neural Networks Using Computer Vision2410-021810.4108/eai.13-10-2021.171318https://doaj.org/article/b6138f8763064cb09e6223614725a70f2021-11-01T00:00:00Zhttps://eudl.eu/pdf/10.4108/eai.13-10-2021.171318https://doaj.org/toc/2410-0218INTRODUCTION: In recent years, deep learning techniques have been made to outperform the earlier state-of-the-art machine learning techniques in many areas, with one of the most notable cases being computer vision. Deep learning is also employed to train the neural networks with the images and to perform the various tasks such as classification and segmentation using several different models. The size and depth of current deep learning models have increased to solve certain tasks as these models provide better accuracy. As pre-trained weights may be used for further training and prevent costly computing, transfer learning is therefore of vital importance. A brief account is given of their history, structure, benefits, and drawbacks, followed by a description of their applications in the different tasks of computer vision, such as object detection, face recognition etc. OBJECTIVE: The purpose of this paper is to train a deep neural network to properly classify the images that it has never seen before, define techniques to enhance the efficiency of deep learning and deploy deep neural networks in various applications. METHOD: The proposed approach represents that after the reading of images, 256x256 pixel image’s random parts are extracted and noise, distortion, flip, or rotation transforms are applied. Multiple convolution and pooling steps are applied by controlling the stride lengths. RESULT: Data analysis and research findings showed that DNN models have been implemented in three main configurations of deep learning: CNTK, MXNet and TensorFlow. The proposed work outperforms the previous techniques in predicting the dependent variables, learning rate, image count, image mean, performance analysis of loss rate and learning rate during training, performance Analysis of Loss with respect to Epoch for Training, Validation and Accuracy. CONCLUSION: This research encompasses a large variety of computer applications, from image recognition and machine translation to enhanced learning. DNN models have been implemented in three main configurations of deep learning: CNTK, MXNet and TensorFlow. Extensive research has been conducted using the various deep architectures such as AlexNet, InceptionNet, etc. To the best of authors’ knowledge, this is the first work that presents a quantitative analysis of the deep architectures mentioned above.Nidhi SindhwaniRohit AnandMeivel S.Rati ShuklaMahendra YadavVikash YadavEuropean Alliance for Innovation (EAI)articlecomputer vision object detection deep learning deep neural network image classification artificial intelligencemachine learningconvolutional neural networkaccuracyComputer engineering. Computer hardwareTK7885-7895Systems engineeringTA168ENEAI Endorsed Transactions on Industrial Networks and Intelligent Systems, Vol 8, Iss 29 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	computer vision object detection deep learning deep neural network image classification artificial intelligence machine learning convolutional neural network accuracy Computer engineering. Computer hardware TK7885-7895 Systems engineering TA168
spellingShingle	computer vision object detection deep learning deep neural network image classification artificial intelligence machine learning convolutional neural network accuracy Computer engineering. Computer hardware TK7885-7895 Systems engineering TA168 Nidhi Sindhwani Rohit Anand Meivel S. Rati Shukla Mahendra Yadav Vikash Yadav Performance Analysis of Deep Neural Networks Using Computer Vision
description	INTRODUCTION: In recent years, deep learning techniques have been made to outperform the earlier state-of-the-art machine learning techniques in many areas, with one of the most notable cases being computer vision. Deep learning is also employed to train the neural networks with the images and to perform the various tasks such as classification and segmentation using several different models. The size and depth of current deep learning models have increased to solve certain tasks as these models provide better accuracy. As pre-trained weights may be used for further training and prevent costly computing, transfer learning is therefore of vital importance. A brief account is given of their history, structure, benefits, and drawbacks, followed by a description of their applications in the different tasks of computer vision, such as object detection, face recognition etc. OBJECTIVE: The purpose of this paper is to train a deep neural network to properly classify the images that it has never seen before, define techniques to enhance the efficiency of deep learning and deploy deep neural networks in various applications. METHOD: The proposed approach represents that after the reading of images, 256x256 pixel image’s random parts are extracted and noise, distortion, flip, or rotation transforms are applied. Multiple convolution and pooling steps are applied by controlling the stride lengths. RESULT: Data analysis and research findings showed that DNN models have been implemented in three main configurations of deep learning: CNTK, MXNet and TensorFlow. The proposed work outperforms the previous techniques in predicting the dependent variables, learning rate, image count, image mean, performance analysis of loss rate and learning rate during training, performance Analysis of Loss with respect to Epoch for Training, Validation and Accuracy. CONCLUSION: This research encompasses a large variety of computer applications, from image recognition and machine translation to enhanced learning. DNN models have been implemented in three main configurations of deep learning: CNTK, MXNet and TensorFlow. Extensive research has been conducted using the various deep architectures such as AlexNet, InceptionNet, etc. To the best of authors’ knowledge, this is the first work that presents a quantitative analysis of the deep architectures mentioned above.
format	article
author	Nidhi Sindhwani Rohit Anand Meivel S. Rati Shukla Mahendra Yadav Vikash Yadav
author_facet	Nidhi Sindhwani Rohit Anand Meivel S. Rati Shukla Mahendra Yadav Vikash Yadav
author_sort	Nidhi Sindhwani
title	Performance Analysis of Deep Neural Networks Using Computer Vision
title_short	Performance Analysis of Deep Neural Networks Using Computer Vision
title_full	Performance Analysis of Deep Neural Networks Using Computer Vision
title_fullStr	Performance Analysis of Deep Neural Networks Using Computer Vision
title_full_unstemmed	Performance Analysis of Deep Neural Networks Using Computer Vision
title_sort	performance analysis of deep neural networks using computer vision
publisher	European Alliance for Innovation (EAI)
publishDate	2021
url	https://doaj.org/article/b6138f8763064cb09e6223614725a70f
work_keys_str_mv	AT nidhisindhwani performanceanalysisofdeepneuralnetworksusingcomputervision AT rohitanand performanceanalysisofdeepneuralnetworksusingcomputervision AT meivels performanceanalysisofdeepneuralnetworksusingcomputervision AT ratishukla performanceanalysisofdeepneuralnetworksusingcomputervision AT mahendrayadav performanceanalysisofdeepneuralnetworksusingcomputervision AT vikashyadav performanceanalysisofdeepneuralnetworksusingcomputervision
_version_	1718406704854466560

Performance Analysis of Deep Neural Networks Using Computer Vision

Ejemplares similares