header
Local cover image
Local cover image
Image from OpenLibrary

A novel hybrid model for automatic image captioning / Mariam Abdelmohsen Mohamed Ramadan Mohamed Hafez ; Supervised Magda B. Fayek , Mayada M. Hadhoud

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Mariam Abdelmohsen Mohamed Ramadan Mohamed Hafez , 2021Description: 65 P. : charts , facsimiles ; 30cmOther title:
  • نموذج هجين جديد للتوضيح التلقائى للصور [Added title page title]
Subject(s): Online resources: Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering Summary: A set of deep learning models and various datasets were tested to solve the problem by finding the link between the image features and the words it represented. The work was divided into two phases: the first was to extract features and determine classes. Various models were tested on different datasets (ImageNet, MS-COCO) to determine the effectiveness of their use. Combination of ALEXNET network, multi-class SVM was the best with accuracy 84.25%.The second was to generate captions, by entering the features and classes from the first stage. Various models were tested, and concluded that LSTM was the best model.The two phases resulted in a hybrid model of ALEXNET network, multi-class SVM and LSTM as the best model with accuracy 88.4%.The model was tested on the complete MS-COCO dataset, reaching an accuracy 90.7%, and was shown to reduce image processing time and high accuracy compared to previous models
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Home library Call number Copy number Status Barcode
Thesis Thesis قاعة الرسائل الجامعية - الدور الاول المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2021.Ma.N (Browse shelf(Opens below)) Not for loan 01010110084052000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2021.Ma.N (Browse shelf(Opens below)) 84052.CD Not for loan 01020110084052000

Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering

A set of deep learning models and various datasets were tested to solve the problem by finding the link between the image features and the words it represented. The work was divided into two phases: the first was to extract features and determine classes. Various models were tested on different datasets (ImageNet, MS-COCO) to determine the effectiveness of their use. Combination of ALEXNET network, multi-class SVM was the best with accuracy 84.25%.The second was to generate captions, by entering the features and classes from the first stage. Various models were tested, and concluded that LSTM was the best model.The two phases resulted in a hybrid model of ALEXNET network, multi-class SVM and LSTM as the best model with accuracy 88.4%.The model was tested on the complete MS-COCO dataset, reaching an accuracy 90.7%, and was shown to reduce image processing time and high accuracy compared to previous models

Issued also as CD

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer

Local cover image