Movie genre classification with deep neural network using poster images

Nayeem Hossain; Md Martuza Ahamad; Sakifa Aktar; Mohammad Ali Moni

doi:10.1109/ICICT4SD50815.2021.9396778

Movie genre classification with deep neural network using poster images

Nayeem Hossain
, Md Martuza Ahamad
, Sakifa Aktar
, Mohammad Ali Moni

Artificial Intelligence and Cyber Futures Institute

Bangabandhu Sheikh Mujibur Rahman Science and Technology University
University of New South Wales

Research output: Book chapter/Published conference paper › Conference paper › peer-review

7 Citations (Scopus)

Abstract

The utility of the deep learning model on poster images to classify their corresponding movie genre is an incredible challenge in computer vision. The objective of this study is to make a computerized framework that works with pictures, both low-level and high-level highlights (such as object detection and form) to classify movie genres. Categorizing motion pictures makes it easier for the watcher to choose a movie they would like to watch. The method of categorizing movies is known as a genre. Many people started to work with low-level features (colour, edge) utilizing deep neural networks for movie genre classification. In this work, a convolutional neural network has been applied to classify the movie genre using their corresponding poster images. At first, this study extracted features from the movie's poster images and then classified the movie genres. A multilayered convolutional neural network is outlined which is trained over a large number of poster images. This study reached an accuracy of 91.15%, f1 score of 0.22, precision 0.67, hamming loss 0.1 and zero one loss 0.75 for the classification of the movie genre.

Original language	English
Title of host publication	2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD)
Subtitle of host publication	Conference Proceedings
Editors	Brig Gen Golam Faruque, Kazi Abu Taher, M. Shamim Kaiser, Mohammed Nasir Uddin
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	195-199
Number of pages	5
ISBN (Electronic)	9781665414609, 9781665414593 (USB)
ISBN (Print)	9781665447522 (Print on demand), Dhaka, Bangladesh
DOIs	https://doi.org/10.1109/ICICT4SD50815.2021.9396778
Publication status	Published - 27 Feb 2021
Event	2021 International Conference on Information and Communication Technology for Sustainable Development: ICICT4SD 2021 - Bangladesh University of Professionals, Dhaka, Bangladesh Duration: 27 Feb 2021 → 28 Feb 2021 http://icict4sd.bup.edu.bd/ (Conference website) https://easychair.org/cfp/icict4sd2021#:~:text=BUP%20will%20host%20the%20International,the%20vision%20of%20Digital%20Bangladesh. (Call for papers) https://ieeexplore.ieee.org/xpl/conhome/9396769/proceeding (Proceedings)

Publication series

Name	2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings

Conference

Conference	2021 International Conference on Information and Communication Technology for Sustainable Development
Abbreviated title	Shaping a sustainable future through advancement in information and communication technology for smart Bangladesh
Country/Territory	Bangladesh
City	Dhaka
Period	27/02/21 → 28/02/21
Other	Bangladesh University of Professionals (BUP) is a unique public university administered by the Armed Forces upholding the motto "Excellence Through Knowledge". BUP will host the International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD) at Bangladesh University of Professionals, Dhaka to attain the vision of Digital Bangladesh. In order to fulfill the aspiration of the Bangladesh Government of achieving Sustainable Development Goals, the theme of the conference is "Shaping a Sustainable Future through Advancement in Information and Communication Technology". This conference will be a platform for creating and sharing ideas among engineers, researchers, scientists, industrialists, and students.
Internet address	http://icict4sd.bup.edu.bd/ (Conference website) https://easychair.org/cfp/icict4sd2021#:~:text=BUP%20will%20host%20the%20International,the%20vision%20of%20Digital%20Bangladesh. (Call for papers) https://ieeexplore.ieee.org/xpl/conhome/9396769/proceeding (Proceedings)

Access to Document

10.1109/ICICT4SD50815.2021.9396778

Cite this

Hossain, N., Ahamad, M. M., Aktar, S., & Moni, M. A. (2021). Movie genre classification with deep neural network using poster images. In B. G. G. Faruque, K. A. Taher, M. S. Kaiser, & M. N. Uddin (Eds.), 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings (pp. 195-199). Article 9396778 (2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICICT4SD50815.2021.9396778

Hossain, Nayeem ; Ahamad, Md Martuza ; Aktar, Sakifa et al. / Movie genre classification with deep neural network using poster images. 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings. editor / Brig Gen Golam Faruque ; Kazi Abu Taher ; M. Shamim Kaiser ; Mohammed Nasir Uddin. IEEE, Institute of Electrical and Electronics Engineers, 2021. pp. 195-199 (2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings).

@inproceedings{53754bd404a74d728184f12f747c87a6,

title = "Movie genre classification with deep neural network using poster images",

abstract = "The utility of the deep learning model on poster images to classify their corresponding movie genre is an incredible challenge in computer vision. The objective of this study is to make a computerized framework that works with pictures, both low-level and high-level highlights (such as object detection and form) to classify movie genres. Categorizing motion pictures makes it easier for the watcher to choose a movie they would like to watch. The method of categorizing movies is known as a genre. Many people started to work with low-level features (colour, edge) utilizing deep neural networks for movie genre classification. In this work, a convolutional neural network has been applied to classify the movie genre using their corresponding poster images. At first, this study extracted features from the movie's poster images and then classified the movie genres. A multilayered convolutional neural network is outlined which is trained over a large number of poster images. This study reached an accuracy of 91.15\%, f1 score of 0.22, precision 0.67, hamming loss 0.1 and zero one loss 0.75 for the classification of the movie genre.",

keywords = "CNN, Deep Learning, Feature Extraction, Multi-label classification",

author = "Nayeem Hossain and Ahamad, \{Md Martuza\} and Sakifa Aktar and Moni, \{Mohammad Ali\}",

year = "2021",

month = feb,

day = "27",

doi = "10.1109/ICICT4SD50815.2021.9396778",

language = "English",

isbn = "9781665447522 (Print on demand)",

series = "2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "195--199",

editor = "Faruque, \{Brig Gen Golam\} and Taher, \{Kazi Abu\} and Kaiser, \{M. Shamim\} and Uddin, \{Mohammed Nasir\}",

booktitle = "2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD)",

address = "United States",

note = "2021 International Conference on Information and Communication Technology for Sustainable Development : ICICT4SD 2021, Shaping a sustainable future through advancement in information and communication technology for smart Bangladesh ; Conference date: 27-02-2021 Through 28-02-2021",

url = "http://icict4sd.bup.edu.bd/, https://easychair.org/cfp/icict4sd2021\#:\textasciitilde{}:text=BUP\%20will\%20host\%20the\%20International,the\%20vision\%20of\%20Digital\%20Bangladesh., https://ieeexplore.ieee.org/xpl/conhome/9396769/proceeding",

}

Hossain, N, Ahamad, MM, Aktar, S & Moni, MA 2021, Movie genre classification with deep neural network using poster images. in BGG Faruque, KA Taher, MS Kaiser & MN Uddin (eds), 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings., 9396778, 2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings, IEEE, Institute of Electrical and Electronics Engineers, pp. 195-199, 2021 International Conference on Information and Communication Technology for Sustainable Development, Dhaka, Bangladesh, 27/02/21. https://doi.org/10.1109/ICICT4SD50815.2021.9396778

Movie genre classification with deep neural network using poster images. / Hossain, Nayeem; Ahamad, Md Martuza; Aktar, Sakifa et al.
2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings. ed. / Brig Gen Golam Faruque; Kazi Abu Taher; M. Shamim Kaiser; Mohammed Nasir Uddin. IEEE, Institute of Electrical and Electronics Engineers, 2021. p. 195-199 9396778 (2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Movie genre classification with deep neural network using poster images

AU - Hossain, Nayeem

AU - Ahamad, Md Martuza

AU - Aktar, Sakifa

AU - Moni, Mohammad Ali

PY - 2021/2/27

Y1 - 2021/2/27

N2 - The utility of the deep learning model on poster images to classify their corresponding movie genre is an incredible challenge in computer vision. The objective of this study is to make a computerized framework that works with pictures, both low-level and high-level highlights (such as object detection and form) to classify movie genres. Categorizing motion pictures makes it easier for the watcher to choose a movie they would like to watch. The method of categorizing movies is known as a genre. Many people started to work with low-level features (colour, edge) utilizing deep neural networks for movie genre classification. In this work, a convolutional neural network has been applied to classify the movie genre using their corresponding poster images. At first, this study extracted features from the movie's poster images and then classified the movie genres. A multilayered convolutional neural network is outlined which is trained over a large number of poster images. This study reached an accuracy of 91.15%, f1 score of 0.22, precision 0.67, hamming loss 0.1 and zero one loss 0.75 for the classification of the movie genre.

AB - The utility of the deep learning model on poster images to classify their corresponding movie genre is an incredible challenge in computer vision. The objective of this study is to make a computerized framework that works with pictures, both low-level and high-level highlights (such as object detection and form) to classify movie genres. Categorizing motion pictures makes it easier for the watcher to choose a movie they would like to watch. The method of categorizing movies is known as a genre. Many people started to work with low-level features (colour, edge) utilizing deep neural networks for movie genre classification. In this work, a convolutional neural network has been applied to classify the movie genre using their corresponding poster images. At first, this study extracted features from the movie's poster images and then classified the movie genres. A multilayered convolutional neural network is outlined which is trained over a large number of poster images. This study reached an accuracy of 91.15%, f1 score of 0.22, precision 0.67, hamming loss 0.1 and zero one loss 0.75 for the classification of the movie genre.

KW - CNN

KW - Deep Learning

KW - Feature Extraction

KW - Multi-label classification

UR - https://www.scopus.com/pages/publications/85104604487

UR - https://www.scopus.com/pages/publications/85104604487#tab=citedBy

U2 - 10.1109/ICICT4SD50815.2021.9396778

DO - 10.1109/ICICT4SD50815.2021.9396778

M3 - Conference paper

AN - SCOPUS:85104604487

SN - 9781665447522 (Print on demand)

SN - Dhaka, Bangladesh

T3 - 2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings

SP - 195

EP - 199

BT - 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD)

A2 - Faruque, Brig Gen Golam

A2 - Taher, Kazi Abu

A2 - Kaiser, M. Shamim

A2 - Uddin, Mohammed Nasir

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 2021 International Conference on Information and Communication Technology for Sustainable Development

Y2 - 27 February 2021 through 28 February 2021

ER -

Hossain N, Ahamad MM, Aktar S, Moni MA. Movie genre classification with deep neural network using poster images. In Faruque BGG, Taher KA, Kaiser MS, Uddin MN, editors, 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings. IEEE, Institute of Electrical and Electronics Engineers. 2021. p. 195-199. 9396778. (2021 International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2021 - Proceedings). doi: 10.1109/ICICT4SD50815.2021.9396778

Movie genre classification with deep neural network using poster images

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this