Corpus ID: 15333553

A CONTENT-BASED IMAGE RETRIEVAL SCHEME IN JPEG COMPRESSED DOMAIN

@inproceedings{Lu2006ACI,
  title={A CONTENT-BASED IMAGE RETRIEVAL SCHEME IN JPEG COMPRESSED DOMAIN},
  author={Zhe-ming Lu and Hans Burkhardt},
  year={2006}
}
Nowadays, a large number of images are compressed in JPEG (Joint Photo- graphic Experts Group) format. Therefore, content-based image retrieval (CBIR) for the JPEG images has attracted many people's attention and a series of algorithms directly based on the discrete cosine transform (DCT) domain have been proposed. However, the existing methods are far from the practical application. Thus, in this paper, a new image retrieval scheme for JPEG formatted images is presented. The color, spatial and… Expand
Fast JPEG compressed domain image retrieval
  • G. Schaefer
  • Computer Science
  • 2016 5th International Conference on Multimedia Computing and Systems (ICMCS)
  • 2016
TLDR
This paper presents efficient and effective CBIR techniques that operate directly in the JPEG compressed domain, hence not requiring full decompression for feature extraction, and explores how CBIR features can be extracted from DCT coefficients, from differentially coded DC data, and from information contained in thejpg headers. Expand
Grading Image Retrieval Based on DCT and DWT Compressed Domains Using Low-Level Features
TLDR
This work uses grading retrieval techniques to implement image retrieval based on discrete cosine transform (DCT) compressed domain and DWT compressed domain, and shows that the two grading image retrieval algorithms work better than other algorithms: store memory is reduced and retrieval accuracy is improved. Expand
Exploiting JPEG Compression for Image Retrieval
TLDR
This paper addresses various aspects of JPEG compressed images in the context of image retrieval, and proposes two new methods that are based solely on information available in the JPEG header that are shown to give retrieval performance comparable to existing methods while being magnitudes faster. Expand
An overview and evaluation of JPEG compressed domain retrieval techniques
TLDR
It is demonstrated conclusively that working in the compressed domain is consistently faster than in the pixel domain, typically requiring around 15% of the processing time. Expand
Feature Extraction in JPEG domain along with SVM for Content Based Image Retrieval
TLDR
This research work focuses on extracting the features from the compressed domain itself and then utilize support vector machines (SVM) for improving the retrieval results. Expand
An Optimal Codebook for Content-Based Image Retrieval in JPEG Compressed Domain
TLDR
A content-based image retrieval system in JPEG compressed domain is presented, which generates an optimal codebook and extract features that only require partial decoding of images, which shows robustness against compressed query images by using different quantization parameters. Expand
Performance comparison of JPEG compressed domain image retrieval techniques
  • D. Edmundson, G. Schaefer
  • Computer Science
  • 2012 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2012)
  • 2012
TLDR
Eight state-of-the-art CBIR algorithms that operate directly in the compressed domain of JPEG by performing retrieval based on DCT coefficients are benchmarked and it is concluded that several of the JPEG CBIR techniques allow much faster feature calculation and faster image retrieval, while providing retrieval performance similar to common pixel-domain algorithms. Expand
DC Stream Based JPEG Compressed Domain Image Retrieval
TLDR
This paper introduces a JPEG compressed domain retrieval algorithm that is based not directly on DCT coefficients but on differences of these, which are readily available in a JPEG compression stream and builds histograms of these differences and utilise them as image features, thus eliminating the need to undo the differential coding as in other methods. Expand
Fast JPEG Image Retrieval Based on AC Huffman Tables
TLDR
This paper presents a very fast method for content-based image retrieval of JPEG compressed images that works directly in the compressed domain of JPEG and is based solely on information available in the image header. Expand
Effective and Efficient Filtering of Retrieved Images Based on JPEG Header Information
TLDR
Two strategies for very fast image retrieval are presented which use solely information contained in the header of JPEG compressed files, one based on the tables that are responsible for the lossy quantisation step in JPEG, while the other is related to the Huffman tables used for entropy coding. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 14 REFERENCES
Image retrieval based on energy histograms of the low frequency DCT coefficients
  • J. Lay, L. Guan
  • Computer Science
  • 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
  • 1999
TLDR
This paper investigates the use of energy histograms of the low frequency DCT coefficients as features for the retrieval of DCT compressed images and proposes a feature set that is able to identify similarities on changes of image-representation due to several lossless DCT transformations. Expand
Image retrieval using texture based on DCT
  • H. Bae, Sung-Hwan Jung
  • Computer Science
  • Proceedings of ICICS, 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications (Cat.
  • 1997
TLDR
The approach for extracting features in the transform domain can provide a solution to storage space problem with its ease of computation. Expand
Image extraction in DCT domain
More and more digital images are being stored in compressed formats, among which the format using discrete cosine transform (DCT) coefficients is widely adopted (JPEG, MPEG, H.263 etc). To exploitExpand
Texture features for DCT-coded image retrieval and classification
  • Yu-Len Huang, R.-F. Chang
  • Computer Science
  • 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
  • 1999
TLDR
Comparisons with the subband-energy features extracted from the wavelet transform, conventional DCT using the Brodatz (1966) texture database indicate that the proposed method provides the best texture pattern retrieval accuracy and obtains a much better correct classification rate. Expand
The MPEG-7 color layout descriptor: a compact image feature description for high-speed image/video segment retrieval
  • E. Kasutani, A. Yamada
  • Computer Science
  • Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)
  • 2001
TLDR
The experimental results show that the descriptor enclosing six for luminance and three for each chrominance coefficient achieves the best trade-off between the storage cost and retrieval efficiency. Expand
Direct content access and extraction from JPEG compressed images
TLDR
A novel design of content access and extraction algorithm for compressed image browsing and indexing by analyzing the relationship between DCT coefficients of one block of 8×8 pixels and its four sub-blocks of 4×4 pixels is proposed. Expand
The JPEG still picture compression standard
TLDR
The Baseline method has been by far the most widely implemented JPEG method to date, and is sufficient in its own right for a large number of applications. Expand
Fast texture description and retrieval of DCT-based compressed images
TLDR
The proposed texture descriptor can be used for texture description and retrieval, and can be directly constructed from DCT-based compressed images or video such as JPEG, MPEG, H.263, etc. Expand
Performance evaluation in content-based image retrieval: overview and proposals
TLDR
The advantages and shortcomings of the performance measures currently used in CBIR are discussed and proposals for a standard test suite similar to that used in IR at the annual Text REtrieval Conference (TREC), are presented. Expand
QBIC project: querying images by content, using color, texture, and shape
TLDR
The main algorithms for color texture, shape and sketch query that are presented, show example query results, and discuss future directions are presented. Expand
...
1
2
...