Object localization by optimizing convolutional neural network detection score using generic edge features

Etemad, Elham; Gao, Qigang

doi:10.1109/icip.2017.8296366

“…There are other algorithms for background subtraction as well. In order to improve the effectiveness of current object recognition algorithms, the research [6] presents an object localization method that makes use of image edge information as a cue to pinpoint the locations of the objects. The perceptual organisation components of human vision are used to extract the Generic Edge Tokens (GETs) of the image.…”

Section: B Unsupervised Learningmentioning

confidence: 99%

Literature Review of Moving Object Detection Using Machine Learning

Kumar¹,

Sinha²,

Kumar³

2022

IJRASET

1

0

View full text Add to dashboard Cite

In order to answer three different research questions, this paper conducts a literature review on the subject of machine learning in object detection security. The work done covers more than 34 research papers that are relevant to this topic. Charts, tables, and statistics are used to summarize the data and provide the reader with an easily readable summary of the papers that are relevant to this topic.

show abstract

“…Edge detection [63] is the most prominent image processing operation performed to analyse and process images and also among the very first steps to perform visual recognition, this uses a filter of some dimension, a filter can also be called as a kernel because its properties are much similar to a kernel function used in calculation of transformations. This filter is convolving the input images through the use of convolution operation/function of your choice which must belong to the set of functions which are differentiable.…”

Section: ) Hyper-parametersmentioning

confidence: 99%

A Comprehensive Literature Review on Convolutional Neural Networks

Mohammed¹,

Reddy²,

Waseem³

2022

Preprint

0

View full text Add to dashboard Cite

<p>From their initial days, the fields of computer vision and image processing have been dealing with visual recognition problems. Convolutional Neural Networks (CNNs) in machine learning are deep architectures built as feed-forward neural networks or perceptrons, which are inspired by the research done in fields of visual analysis by the visual cortex of mammals like cats. This work analyzes CNNs for computer vision tasks, natural language processing, fundamental sciences and engineering problems, and other miscellaneous tasks. The general CNN structure, along with its mathematical intuition and working, a brief critical commentary on the advantages and disadvantages, which leads researchers to search for alternatives to CNN, is also mentioned. The paper also serves as an appreciation of the brain-child of past researchers for the existence of such a prolific architecture for handling multidimensional data and approaches to improve their performance further. </p>

show abstract

“…Edge detection [63] is the most prominent image processing operation performed to analyse and process images and also among the very first steps to perform visual recognition, this uses a filter of some dimension, a filter can also be called as a kernel because its properties are much similar to a kernel function used in calculation of transformations. This filter is convolving the input images through the use of convolution operation/function of your choice which must belong to the set of functions which are differentiable.…”

Section: ) Hyper-parametersmentioning

confidence: 99%

A Comprehensive Literature Review on Convolutional Neural Networks

Mohammed¹,

Reddy²,

Waseem³

2022

Preprint

0

View full text Add to dashboard Cite

<p>From their initial days, the fields of computer vision and image processing have been dealing with visual recognition problems. Convolutional Neural Networks (CNNs) in machine learning are deep architectures built as feed-forward neural networks or perceptrons, which are inspired by the research done in fields of visual analysis by the visual cortex of mammals like cats. This work analyzes CNNs for computer vision tasks, natural language processing, fundamental sciences and engineering problems, and other miscellaneous tasks. The general CNN structure, along with its mathematical intuition and working, a brief critical commentary on the advantages and disadvantages, which leads researchers to search for alternatives to CNN, is also mentioned. The paper also serves as an appreciation of the brain-child of past researchers for the existence of such a prolific architecture for handling multidimensional data and approaches to improve their performance further. </p>

show abstract

Object localization by optimizing convolutional neural network detection score using generic edge features

Cited by 5 publications

References 14 publications

Literature Review of Moving Object Detection Using Machine Learning

Literature Review of Moving Object Detection Using Machine Learning

A Comprehensive Literature Review on Convolutional Neural Networks

A Comprehensive Literature Review on Convolutional Neural Networks

Contact Info

Product

Resources

About