Compression of image patches for local feature extraction

Makar, Mina; Chang, Chuo-Ling; Chen, David; Tsai, Shiou‐Chuan; Girod, Bernd

doi:10.1109/icassp.2009.4959710

Cited by 45 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CHOG, at the rate of 8 bytes per descriptor, can achieve matching capabilities comparable to the uncompressed features. In [15], the local image patch around the interest point is compressed and sent over the network at low bit rate, which also shifts the workload of descriptor computation to the server side. Unlike the other approaches, the retrieval system in [16] sends a tree histogram in place of individual descriptors, which enables significant additional rate reduction.…”

Section: Rate-efficient Image Retrievalmentioning

confidence: 99%

Location coding for mobile image retrieval

Tsai

Chen

Takacs

et al. 2009

Proceedings of the 5th International Mobile Multimedia Communications Conference

Self Cite

View full text Add to dashboard Cite

For mobile image retrieval, efficient data transmission can be achieved by sending only the query features. Each query feature is composed of a descriptor and a location in the image. The former is used to find candidate matching images using a "bag-of-words" approach while the latter is used in a geometric consistency check to map features in the query image to corresponding features in the database image. We investigate how to compress the location information and how lossy compression affects the geometric consistency check. The location information is converted into a location histogram and a context-based arithmetic coding with location refinement method is then proposed to code the histogram. The effects of lossily compressing the location information are evaluated empirically in terms of the errors in corresponding features and the error of the estimated geometric transformation model. From our experiments, rates at ∼5.1 bits per feature can achieve errors comparable to lossless coding. The proposed scheme achieves a 12.5× rate reduction compared to the floating point representation, and 2.8× rate reduction compared to a fixed point representation.

show abstract

Section: Rate-efficient Image Retrievalmentioning

confidence: 99%

Location coding for mobile image retrieval

Tsai

Chen

Takacs

et al. 2009

Proceedings of the 5th International Mobile Multimedia Communications Conference

Self Cite

View full text Add to dashboard Cite

show abstract

“…transferred to the server. This allows for a more than fivefold rate reduction when compared to compressing features as proposed in [MCCT09] and thus a significant reduction of the overall query time. However, this approach requires performing the quantization of descriptors vectors into visual words on the mobile device at very low complexity to cope with the limited processing power as well as to avoid draining the battery.…”

Section: Multiple Hypothesis Vocabulary Treementioning

confidence: 97%

Mobile Visual Location Recognition

Schroth¹,

Huitl

Chen

et al. 2011

IEEE Signal Process. Mag.

Self Cite

107

View full text Add to dashboard Cite

“…In Chandrasekhar et al (2009), the authors studied dimensionality reduction of SIFT and SURF descriptors using KLT but followed by an entropy coding. Discrete Cosine Transform (Chadha et al 2011;Schwerin and Paliwal 2008;Makar et al 2009) and Discrete Wavelet Transform (Grzegorzek et al 2010;Lim et al 2009) were also proposed as feature quantization methods, but they did not perform results comparable to other state-of-the-art methods.…”

Section: Related Workmentioning

confidence: 97%

MDPV: metric distance permutation vocabulary

2014

View full text Add to dashboard Cite

Sub-image content-based similarity search forms an important operation in current image archives since it provides users with images that contain a query image as their part. Such a search can conveniently be implemented using the bag-of-features model. Its integral part is a construction of visual vocabulary. Most existing algorithms to create a visual vocabulary suffer from high computational (e.g. k-means) or supervisor-guidance (e.g. visual-bit classifier, or sparse coding) requirements. In this paper, we propose a novel approach to visual vocabulary construction called metric distance permutation vocabulary. It is based on permutations of metric distances to create compact visual words. Its major advantage over prior techniques is time and space efficiency of vocabulary construction and quantization process during querying, while achieving comparable or even better effectiveness (query result quality). Moreover, this basic concept is extended to combine more independent permutations. Both the proposals are experimented on well-known real-world data-sets and compared to other state-of-the-art techniques.

show abstract

Compression of image patches for local feature extraction

Cited by 45 publications

References 7 publications

Location coding for mobile image retrieval

Location coding for mobile image retrieval

Mobile Visual Location Recognition

MDPV: metric distance permutation vocabulary

Contact Info

Product

Resources

About