سیستم خودکار زیرنویس تصویر
ترجمه نشده

سیستم خودکار زیرنویس تصویر

عنوان فارسی مقاله: Chittron: یک سیستم خودکار زیرنویس تصویر بنگلادشی
عنوان انگلیسی مقاله: Chittron: An Automatic Bangla Image Captioning System
مجله/کنفرانس: علوم کامپیوتر پروسیدیا – Procedia Computer Science
رشته های تحصیلی مرتبط: مهندسی کامپیوتر
گرایش های تحصیلی مرتبط: هوش مصنوعی
کلمات کلیدی فارسی: مجموعه داده زیرنویس عکس BanglaLekha، حاشیه نویسی تصویر، ایجاد زیرنویس خودکار، حافظه کوتاه مدت طولانی (LSTM)، یادگیری عمیق، شبکه های عصبی، یادگیری ماشین، بنگلادشی، پردازش زبان طبیعی
کلمات کلیدی انگلیسی: BanglaLekha-Image-Caption dataset ; Image Annotation ; Automatic Caption Generation ; LSTM ; Deep Learning ; Neural Networks ; Machine Learning; Bangla; Natural Language Processing
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
شناسه دیجیتال (DOI): https://doi.org/10.1016/j.procs.2019.06.100
دانشگاه: University of Liberal Arts Bangladesh, Dhanmondi, Dhaka, Bangladesh
صفحات مقاله انگلیسی: 7
ناشر: الزویر - Elsevier
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2019
ایمپکت فاکتور: 1.257 در سال 2018
شاخص H_index: 47 در سال 2019
شاخص SJR: 0.281 در سال 2018
شناسه ISSN: 1877-0509
فرمت مقاله انگلیسی: PDF
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: خیر
آیا این مقاله مدل مفهومی دارد: ندارد
آیا این مقاله پرسشنامه دارد: ندارد
آیا این مقاله متغیر دارد: ندارد
کد محصول: E12361
رفرنس: دارای رفرنس در داخل متن و انتهای مقاله
فهرست مطالب (انگلیسی)

Abstract

1-Introduction

2-Relevant Work

3-BanglaLekha-Image Captions: The Data Set

4-Model and Training Details

5-Results and Discussion

6-Conclusion

7-References

بخشی از مقاله (انگلیسی)

Abstract

Automatic image caption generation aims to produce an accurate description of an image in natural language automatically. How- ever, Bangla, the fifth most widely spoken language in the world, is lagging considerably in the research and development of such domain. Besides, while there are many established data sets related to image annotation in English, no such resource exists for Bangla yet. Hence, this paper outlines the development of “Chittron”, an automatic image captioning system in Bangla. To address the data set availability issue, a collection of 16, 000 Bangladeshi contextual images has been accumulated and manually annotated in Bangla. This data set is then used to train a model that integrates a pre-trained VGG16 image embedding model with stacked LSTM layers. The model is trained to predict the caption when the input is an image, one word at a time. The results show that the model has successfully been able to learn a working language model and to generate captions of images quite accurately in many cases. The results are evaluated mainly qualitatively. However, BLEU scores are also reported. It is expected that a better result can be obtained with a bigger and more varied data set.

Introduction

The stark reality is that most of the works in image captioning have concentrated almost exclusively on English language [1, 2, 3]. Additionally, the relevant data-sets, e.g. the MSCOCO [4], have a prominent western preference which leads to a two-pronged problem: (1) the language in which captions are generated is English only, and (2)the data set is not representative of the cultural peculiarities of non-western countries. These very problems exist for generating image captions in Bangla, particularly for images which have a decidedly Bangla geocultural flavor. A simple example of this can be seen in Figure 1, where a web service is used to generate captions. The service uses the im2txt model trained on the MSCOCO data set and quite clearly the model fails to recognize the image in Figure 1a as a boy wearing a lungi, a very common male garb in Bangladesh. In fact, it incorrectly identifies the subject as a female since the attire is identified as women gown.