International Journal of Pharma and Bio Sciences
ijpbs.net
editorijpbs@rediffmail.com (or) editorofijpbs@yahoo.com (or) prasmol@rediffmail.com
10.22376/ijpbs.2019.10.1.p1-12
Volume 5 Issue 3
2014 (July- September)
CONVERSION OF DETECTED TEXT AND CAPTION FROM AN IMAGE TO SPEECH
Image retrieval is a process of browsing and searching an image from large database with a collection of digital images. Images can be retrieved with the help of caption, description of the image and keyword. In the conventional image retrieval system corner detection method has been used. This corner detection method is not user friendly and also it takes more time for retrieving images when the database have a large number of images in it. In this project work we have improved the performance of the image retrieving system by applying concepts of neural networks and also combining the corner and edge based detection using Harris corner algorithm for retrieving text and caption from image. By Edge detection method we remove unwanted information of the image without affecting its original structural properties.From the corner gives the area in which more gradient is present in more than one direction will be found out. This helps to detect the edges and corners of the texts and captions on the image. We finally convert the detected characters to speech using Text-To-speech (TTS) synthesizer
R.MADHAN AND MR.S.P.CHOKKALINGAM
Harris Corner Algorithm, Text-To-Speech synthesizer.
913-921