Visual Categorization Using Negative Bootstrap
Abstract
Existing system uses query by image content with multiple visual properties such as color, texture and shape. Traditional system uses text based image retrieval with satisfactory retrieval performance. Some existing system uses canny and sobel edge detection algorithm for extracting the shape features for the images. Much research has been conducted towards inexpensive solutions to acquire positive examples, e.g., from web image search results or socially tagged data, or by online collaborative annotation.
In proposed system we consider positive examples obtained from web image search results or socially tagged data, or by online collaborative annotation. Obtaining negative examples seems to be trivial, as they are abundant in large photo repositories such as Flickr and Facebook. And it focuses on obtaining relevant negatives for better classifier performance. The system will reduce the searching time and will have low cost.
In proposed system we consider positive examples obtained from web image search results or socially tagged data, or by online collaborative annotation. Obtaining negative examples seems to be trivial, as they are abundant in large photo repositories such as Flickr and Facebook. And it focuses on obtaining relevant negatives for better classifier performance. The system will reduce the searching time and will have low cost.
Keywords
Image processing; Negative bootstrapping; content based image retrieval; SVM
Full Text:
PDFCopyright (c) 2015 Manisha Bhimrao Waghmode, Abhijit V. Mophare
![Creative Commons License](http://licensebuttons.net/l/by-nc-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
All published Articles are Open Access at https://journals.pen2print.org/index.php/ijr/
Paper submission: ijr@pen2print.org