Abstract
A hierarchical system to perform automatic categorization and reorientation of images using content analysis is pre-sented. The proposed system first categorizes images to some a priori defined categories using rotation invariant features. At the second stage, it detects their correct orientation out of {0o, 90o, 180o, and 270o} using category specific model. The system has been specially designed for embedded devices applications using only low level color and edge features. Machine learning algorithms optimized to suit the embedded implementation like support vector machines (SVMs) and scalable boosting have been used to develop classifiers for categorization and orientation detection. Results are presented on a collection of about 7000 consumer images collected from open resources. The proposed system finds it applications to various digital media products and brings pattern recognition solutions to the consumer electronics domain.
Highlights
Digital Content Management (DCM) has become an area of vital importance with growing multimedia information available to consumers through various mediums such as internet, digital cameras, camcorders, mobile phones, and home recorders
We have trained support vector machines (SVMs) with normalized color correlogram features extracted from images in the training dataset randomly rotated to any of the four directions {0o, 90o, 180o, 270o}
The parameters of the SVM were optimized by cross validation during training
Summary
Digital Content Management (DCM) has become an area of vital importance with growing multimedia information available to consumers through various mediums such as internet, digital cameras, camcorders, mobile phones, and home recorders. We present a DCM solution for still digital images which can automatically categorize images into four broad categories and detect their orientations from {0o, 90o, 180o, and 270o} based on the content analysis. Orientation detection is an important problem because often digital camera users rotate the camera before image capture and when such images are fetched to the computer they are rotated and not synchronized with the view geometry and human visual system. The solution proposed by us is hierarchical in nature, i.e., first categorization and orientation detection. To make the proposed approach suitable for embedded devices, we make use of simple and computationally inexpensive features based on color and edge information of images.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Journal of Intelligent Learning Systems and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.