Supporting Image-to-Text (Image Captioning) in Apache Tika for Image MIME Types

Supporting Image-to-Text (Image Captioning) in Apache Tika for Image MIME Types

Thejan Wijesinghe

Thejan Wijesinghe

Colombo, Western Province

The project was done as my Google Summer of Code'17 project. Primary objective of this project was to implement an image captioning parser.

Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

    Follow

Description

Image captions are a small piece of text, usually of one line, added to the metadata of images to provide a brief summary of the scenery in the image. It helps text based Information Retrieval(IR) systems to "understand" the scenery in images. It is a very useful feature, yet a challenging and interesting problem in the domain of computer vision.

The objective of this project is providing Apache Tika (https://github.com/apache/tika), image captioning capabilities and a scalable architecture to deal with deep learning models in the future.

Links

GSoC archive

Wiki Link

Medium pic2

Thejan W. created project Supporting Image-to-Text (Image Captioning) in Apache Tika for Image MIME Types

Medium 26a2c836 f3c1 4cd2 a7e5 a55a061634a6

Supporting Image-to-Text (Image Captioning) in Apache Tika for Image MIME Types

Image captions are a small piece of text, usually of one line, added to the metadata of images to provide a brief summary of the scenery in the image. It helps text based Information Retrieval(IR) systems to "understand" the scenery in images. It is a very useful feature, yet a challenging and interesting problem in the domain of computer vision.

The objective of this project is providing Apache Tika (https://github.com/apache/tika), image captioning capabilities and a scalable architecture to deal with deep learning models in the future.

No users to show at the moment.

No users to show at the moment.