scispace - formally typeset
Proceedings ArticleDOI

Joint bitstream level identification and retrieval method of JPEG 2000 images for digital cinema

Reads0
Chats0
TLDR
The proposed method uses the number of zero bitplanes, which is obtained by parsing the header information without decoding JPEG 2000 codestream, to achieve joint identification and retrieving of JPEG 2000 image.
Abstract
A joint bitstream level identification and retrieval method for JPEG 2000 images is proposed in this paper. Although the main purpose is to identify a JPEG 2000 image, the proposed method simultaneously retrieves JPEG 2000 images from a certain query with the computation of similarity. The proposed method uses the number of zero bitplanes, which is obtained by parsing the header information without decoding JPEG 2000 codestream, to achieve joint identification and retrieving of JPEG 2000 image. Some experimental results on retrieving JPEG 2000 images are provided to evaluate the performance of the proposed method. The main advantage is not only accuracy but also fast processing. Since there is no need to decode JPEG 2000 images in the proposed method, averaged time consumption due to retrieving operation is about less than 1[ms] and is independent on image size. Moreover, the proposed method can be combined with the scalability of JPEG 2000 codestream to satisfy trade-off between accuracy and speed.

read more

Citations
More filters
Journal ArticleDOI

The Elephant Dream

Anne Szumigalski
- 21 Jan 1976 - 
Journal Article

DCT-Domain Image Retrieval Via Block-Edge-Patterns

TL;DR: Wang et al. as mentioned in this paper extract three edge patterns from compressed image data to construct an edge pattern histogram as an indexing key to retrieve images based on their content features.
References
More filters
Journal ArticleDOI

High performance scalable image compression with EBCOT

TL;DR: A new image compression algorithm is proposed, based on independent embedded block coding with optimized truncation of the embedded bit-streams (EBCOT), capable of modeling the spatially varying visual masking phenomenon.
Proceedings ArticleDOI

High performance scalable image compression with EBCOT

TL;DR: A new image compression algorithm is proposed, based on independent embedded block coding with optimized truncation of the embedded bit-streams (EBCOT), capable of modeling the spatially varying visual masking phenomenon.
Proceedings ArticleDOI

Fast and Robust Identification Methods for JPEG Images with Various Compression Ratios

TL;DR: By combining the two schemes, a faster and a more perfect identification can be achieved, in which FN and FP can be avoided.
Proceedings ArticleDOI

Fast Method for Joint Retrieval and Identification of JPEG Coded Images Based on DCT Sign

TL;DR: The proposed method is intended to retrieve similar images, including their compressed versions, and to identify exact match and all compressed versions of a query image simultaneously, and is robust to JPEG compression, particularly for image identification purpose.
Book ChapterDOI

DCT-Domain image retrieval via block-edge-patterns

TL;DR: This algorithm directly extract three edge patterns from compressed image data to construct an edge pattern histogram as an indexing key to retrieve images based on their content features to achieve superior performances in terms of retrieval precision and processing speed.
Related Papers (5)