1. DRSR@DA-IICT
  2. Theses and dissertations
  3. M Tech Dissertations
Please use this identifier to cite or link to this item: http://drsr.daiict.ac.in//handle/123456789/954
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorKhare, Manish
dc.contributor.authorMaulvi, Mohammed Nadeem G.
dc.date.accessioned2020-09-22T04:58:25Z
dc.date.available2023-02-17T04:58:25Z
dc.date.issued2020
dc.identifier.citationMaulvi, Mohammed Nadeem G. (2020). Image captioning using xception. Dhirubhai Ambani Institute of Information and Communication Technology. vi, 12 p. (Acc.No: T00876)
dc.identifier.urihttp://drsr.daiict.ac.in//handle/123456789/954
dc.description.abstractThe main aim of the project was to create a model that generates the captions. The captions must be syntactically correct and semantically true. Also the goal was to create a new model that can achieve outstanding results compared to other models. The data set used was Flickr8k and was trained over pre-trained Xception model. The outcomes were compared against the ResNet50 and InceptionV3 results. The evaluation metric used was BLEU (Bilingual Evaluation Understudy) Score. The BLEU Score graphs shows that Xception has outperformed the ResNet50 and InceptionV3 models.
dc.publisherDhirubhai Ambani Institute of Information and Communication Technology
dc.subjectImage Captioning
dc.subjectXception model
dc.subjectFlickr8k data set
dc.subjectBLEU Score
dc.classification.ddc621.367 MAU
dc.titleImage captioning using xception
dc.typeDissertation
dc.degreeM. Tech
dc.student.id201811048
dc.accession.numberT00876
Appears in Collections:M Tech Dissertations

Files in This Item:
File Description SizeFormat 
201811048.pdf
  Restricted Access		680.96 kBAdobe PDFView/Open Request a copy
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.