Image Classification Using Convolutional Neural Networks With Multi-stage Feature

Yim, Junho; Ju, Jeongwoo; Jung, Heechul; Kim, Junmo

doi:10.1007/978-3-319-16841-8_52

Cited by 65 publications

(27 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed fusion approach is evaluated according to image classification benchmark data sets, CIFAR-10, NORB, and SVHN. This paper shows that the approach that is proposed improves the reported performances of the existing models by 0.38%, 3,21% and 0.13% respectively [12].…”

Section: A Comparison Of Generic Machine Learning Algorithms For Imagmentioning

confidence: 82%

See 1 more Smart Citation

Analytical Study of Image Classsification Using Deep Learning

yousuf

2018

ijarcs

View full text Add to dashboard Cite

Abstract:The machine learning technology has received increased attention in recent years in several vision tasks such as image classification, image detection, and image recognition. In particular, recent advances of machine learning techniques bring encouragement to image classification with convolutional neural networks. CNN has been established as a powerful class of models for image recognition problems and even in some cases they outperform humans. The main purpose of the work presented in this paper is the rise and development of machine learning, deep learning, CNN and to give an overview on using machine learning for image classification. At the end the comparison of CNN with traditional method is discussed.

show abstract

Section: A Comparison Of Generic Machine Learning Algorithms For Imagmentioning

confidence: 82%

“…As in some cases, the lower layer carries more powerful features than those from the top [12]. Therefore applying features from a particular layer only to categorize seems to be a process that does not require learned CNN's potential discriminant power to its full degree.…”

Section: A Comparison Of Generic Machine Learning Algorithms For Imagmentioning

confidence: 99%

Analytical Study of Image Classsification Using Deep Learning

yousuf

2018

ijarcs

View full text Add to dashboard Cite

show abstract

“…CNN is very effective in the field of image classification and recognition [ 24 ]. This special type of Neural Network was limited due to hardware capacity before 2010, as CNN demands a large amount of memory to process the huge amount of training data.…”

Section: Methodsmentioning

confidence: 99%

An Automatic Car Counting System Using OverFeat Framework

Biswas

Wang

et al. 2017

Sensors

View full text Add to dashboard Cite

Automatic car counting is an important component in the automated traffic system. Car counting is very important to understand the traffic load and optimize the traffic signals. In this paper, we implemented the Gaussian Background Subtraction Method and OverFeat Framework to count cars. OverFeat Framework is a combination of Convolution Neural Network (CNN) and one machine learning classifier (like Support Vector Machines (SVM) or Logistic Regression). With this study, we showed another possible application area for the OverFeat Framework. The advantages and shortcomings of the Background Subtraction Method and OverFeat Framework were analyzed using six individual traffic videos with different perspectives, such as camera angles, weather conditions and time of the day. In addition, we compared the two algorithms above with manual counting and a commercial software called Placemeter. The OverFeat Framework showed significant potential in the field of car counting with the average accuracy of 96.55% in our experiment.

show abstract

“…Sedangkan fokus area perceived intrusion adalah untuk mengetahui apakah penggunaan aplikasi mobile menimbulkan rasa tidak nyaman bagi penggunaya, informasi pribadi pengguna yang lebih mudah tersedia untuk orang lain, dan akibat dari penggunaan aplikasi mobile [8]. Kemudiaan untuk fokus area secondary use of information adalah untuk mengetahui apakah Aplikasi mobile dapat menggunakan informasi pribadi pengguna untuk tujuan lain tanpa izin otoritas dari pengguna, aplikasi dapat menggunakan informasi pribadi pengguna untuk tujuan lain, dan aplikasi mobile dapat berbagi informasi pribadi pengguna dengan entitas lain tanpa otorisasi pengguna.…”

Section: Metode Penelitianunclassified

Uji Tingkat Kesadaran Keamanan Informasi Pengguna Smartphone (Studi Kasus: Amik Labuhan Batu)

Munthe¹,

Purnama

2019

Tekinkom

View full text Add to dashboard Cite

Based on statistical data, it is known that Android is the most popular smartphone with the largest number of users in the world, which is around 1.8 billion users. The high number of users also invites many cases of information security and privacy caused by a lack of awareness from users such as spam, spoofing / phishing, network incidents, malware, uploading something of a personal nature such as photos, telephone numbers, addresses or not having antivirus. This study aims to find out about information security and privacy of Android smartphone users by measuring the problem of the dimension of awareness (attitude, knowledge and behavior) with seven focus areas of information security namely trust in app repositories, misconception about app testing, security and agreement messages, pirated application, adoption of security control, spam sms and report of security incidents and three focus areas on privacy namely perceived surveillance, perceived intrusion, secondary use of information. This research uses analytical hierarchy process (AHP) method to measure the level of information security awareness and privacy of smartphone users. Overall, the results of the study indicate that information security has an average level of awareness (71%). But in the focus area the report for security incidents has a poor level of awareness (37%) this is because users prefer to solve their own information security problems experienced and privacy has an average level of awareness (76%). While the secondary use of information in the attitude dimension has a low level of awareness (66%). Based on these findings, it can be concluded that smartphone users at AMIK Labuhan Batu have a poor level of awareness in maintaining information security and privacy..

show abstract

Image Classification Using Convolutional Neural Networks With Multi-stage Feature

Cited by 65 publications

References 5 publications

Analytical Study of Image Classsification Using Deep Learning

Analytical Study of Image Classsification Using Deep Learning

An Automatic Car Counting System Using OverFeat Framework

Uji Tingkat Kesadaran Keamanan Informasi Pengguna Smartphone (Studi Kasus: Amik Labuhan Batu)

Contact Info

Product

Resources

About