東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

On Designing Deep Learning Approache...

Matta, Rohitha Reddy.

FindBook

Google Book

Amazon

博客來

On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild./
作者:	Matta, Rohitha Reddy.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	88 p.
附註:	Source: Masters Abstracts International, Volume: 79-04.
Contained By:	Masters Abstracts International79-04.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10607896
ISBN:	9780355153514

On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild.
Matta, Rohitha Reddy.

On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 88 p.

Source: Masters Abstracts International, Volume: 79-04.

Thesis (M.S.)--West Virginia University, 2017.

This item is not available from ProQuest Dissertations & Theses.

Internet shopping has spread wide and into social networking. Someone may want to buy a shirt, accessories, etc., in a random picture or a streaming video. In this thesis, the problem of automatic classification was taken upon, constraining the target to jerseys in the wild, assuming the object is detected. A dataset of 7,840 jersey images, namely the JerseyXIV is created, containing images of 14 categories of various football jersey types (Home and Alternate) belonging to 10 teams of 2015 Big 12 Conference football season. The quality of images varies in terms of pose, standoff distance, level of occlusion and illumination. Due to copyright restrictions on certain images, unaltered original images with appropriate credits can be provided upon request. While various conventional and deep learning based classification approaches were empirically designed, optimized and tested, a solution that resulted in the highest accuracy in terms of classification was achieved by a train-time fused Convolutional Neural Network (CNN) architecture, namely CNN-F, with 92.61% accuracy. The final solution combines three different CNNs through score level average fusion achieving 96.90% test accuracy. To test these trained CNN models on a larger, application oriented scale, a video dataset is created, which may present an addition of higher rate of occlusion and elements of transmission noise. It consists of 14 videos, one for each class, totaling to 3,584 frames, with 2,188 frames containing the object of interest. With manual detection, the score level average fusion has achieved the highest classification accuracy of 81.31%. In addition, three Image Quality Assessment techniques were tested to assess the drop in accuracy of the average-fusion method on the video dataset. The Natural Image Quality Evaluator (NIQE) index by Bovik et al. with a threshold of 0.40 on input images improved the test accuracy of the average fusion model on the video dataset to 86.36% by removing the low quality input images before it reaches the CNN. The thesis concludes that the recommended solution for the classification is composed of data augmentation and fusion of networks, while for application of trained models on videos, an image quality metric would aid in performance increase with a trade-off in loss of input data.

ISBN: 9780355153514Subjects--Topical Terms:

1567821
Computer Engineering.

On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild.
LDR:03587nmm a2200361 4500 001 2207498
005 20190920131240.5
008 201008s2017 ||||||||||||||||| ||eng d
020 $a 9780355153514
035 $a (MiAaPQ)AAI10607896
035 $a (MiAaPQ)wvumasters:10398
035 $a AAI10607896
040 $a MiAaPQ $c MiAaPQ
100 1 $a Matta, Rohitha Reddy. $3 3434487
245 1 0 $a On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 88 p.
500 $a Source: Masters Abstracts International, Volume: 79-04.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Bourlai, Thirimachos.
502 $a Thesis (M.S.)--West Virginia University, 2017.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a Internet shopping has spread wide and into social networking. Someone may want to buy a shirt, accessories, etc., in a random picture or a streaming video. In this thesis, the problem of automatic classification was taken upon, constraining the target to jerseys in the wild, assuming the object is detected. A dataset of 7,840 jersey images, namely the JerseyXIV is created, containing images of 14 categories of various football jersey types (Home and Alternate) belonging to 10 teams of 2015 Big 12 Conference football season. The quality of images varies in terms of pose, standoff distance, level of occlusion and illumination. Due to copyright restrictions on certain images, unaltered original images with appropriate credits can be provided upon request. While various conventional and deep learning based classification approaches were empirically designed, optimized and tested, a solution that resulted in the highest accuracy in terms of classification was achieved by a train-time fused Convolutional Neural Network (CNN) architecture, namely CNN-F, with 92.61% accuracy. The final solution combines three different CNNs through score level average fusion achieving 96.90% test accuracy. To test these trained CNN models on a larger, application oriented scale, a video dataset is created, which may present an addition of higher rate of occlusion and elements of transmission noise. It consists of 14 videos, one for each class, totaling to 3,584 frames, with 2,188 frames containing the object of interest. With manual detection, the score level average fusion has achieved the highest classification accuracy of 81.31%. In addition, three Image Quality Assessment techniques were tested to assess the drop in accuracy of the average-fusion method on the video dataset. The Natural Image Quality Evaluator (NIQE) index by Bovik et al. with a threshold of 0.40 on input images improved the test accuracy of the average fusion model on the video dataset to 86.36% by removing the low quality input images before it reaches the CNN. The thesis concludes that the recommended solution for the classification is composed of data augmentation and fusion of networks, while for application of trained models on videos, an image quality metric would aid in performance increase with a trade-off in loss of input data.
590 $a School code: 0256.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer science. $3 523869
690 $a 0464
690 $a 0544
690 $a 0984
710 2 $a West Virginia University. $b Statler College of Engineering & Mineral Resources. $3 3170720
773 0 $t Masters Abstracts International $g 79-04.
790 $a 0256
791 $a M.S.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10607896