000			02170cam a2200337 a 4500
003			EG-GiCUC
005			20250223032808.0
008			210830s2021 ua dh f m 000 0 eng d
040			_aEG-GiCUC _beng _cEG-GiCUC
041	0		_aeng
049			_aDeposite
097			_aM.Sc
099			_aCai01.13.06.M.Sc.2021.Ma.N
100	0		_aMariam Abdelmohsen Mohamed Ramadan Mohamed Hafez
245	1	2	_aA novel hybrid model for automatic image captioning / _cMariam Abdelmohsen Mohamed Ramadan Mohamed Hafez ; Supervised Magda B. Fayek , Mayada M. Hadhoud
246	1	5	_aنموذج هجين جديد للتوضيح التلقائى للصور
260			_aCairo : _bMariam Abdelmohsen Mohamed Ramadan Mohamed Hafez , _c2021
300			_a65 P. : _bcharts , facsimiles ; _c30cm
502			_aThesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering
520			_aA 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
530			_aIssued also as CD
653		4	_aFeature Extraction
653		4	_aImage Captioning
653		4	_aLSTM
700	0		_aMagda B. Fayek , _eSupervisor
700	0		_aMayada M. Hadhoud , _eSupervisor
856			_uhttp://172.23.153.220/th.pdf
905			_aNazla _eRevisor
905			_aShimaa _eCataloger
942			_2ddc _cTH
999			_c81923 _d81923