Color-based image retrieval using binary signatures

Nascimento, Mário A.; Chitkara, Vishal

doi:10.1145/508791.508923

Cited by 26 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Median filters effectively remove these outliers thus has an averaging effect on the pixel values which also contributes to the robustness of the identifier against affine transformations. [11] so derived is collision resistant and occupies minimal memory space in the database. Hamming distance is used to measure the similarity between the query image identifier and the image identifier set from the database.…”

Section: Figure 2 Flow Diagram Of Proposed Algorithmmentioning

confidence: 99%

Optimized trace transform based content based image retrieval algorithm

Bankapur

Bhoomaraddi

Maralappanavar

2012

Proceedings of the International Conference on Advances in Computing, Communications and Informatics

View full text Add to dashboard Cite

The last decade has seen a rapid increase in the use of visual information leading to storage and accessibility problems. To improve human access, there must be effective and precise retrieval algorithm for the user to search, browse and interact with these collections in real time. In this paper we propose a trace transform based content based image retrieval algorithm (TTB-CBIR). The proposed algorithm applies trace transform which is robust to affine transform for feature extraction. Similarity measure is done using hamming distance. The TTB-CBIR algorithm is tested on corel database of images. The proposed algorithm shows optimum performance in terms of memory utilization and retrieval time.

show abstract

Section: Figure 2 Flow Diagram Of Proposed Algorithmmentioning

confidence: 99%

Optimized trace transform based content based image retrieval algorithm

Bankapur

Bhoomaraddi

Maralappanavar

2012

Proceedings of the International Conference on Advances in Computing, Communications and Informatics

View full text Add to dashboard Cite

show abstract

“…We have adopted a binary signature scheme for content-based image retrieval proposed by Nascimento and Chitkara [22]. Our scheme integrates this global binary signature with Sobel's edge detection [23] for single-cycle image recognition with the DHGN.…”

Section: Multi-feature Dhgnmentioning

confidence: 99%

“…, p n }, where p i represents the normalised percentage of colour pixels that corresponds to each colour element c i within an image. Nascimento and Chitkara [22] have proposed an alternative approach for colour distribution representation by using a global binary signature scheme. It is a compact form of existing GCH that uses binary bit-strings as a signature.…”

Section: Global Binary Signature Scheme For Colour Recognitionmentioning

confidence: 99%

Distributed Multi-Feature Recognition Scheme for Greyscale Images

Amin

Khan

2010

Neural Process Lett

View full text Add to dashboard Cite

Contemporary image recognition schemes either rely on single-feature recognition or focus on solving multi-feature recognition using complex computational approaches. Furthermore these approaches tend to be of tightly-coupled nature, thus not readily deployable within computational networks. Distributed Hierarchical Graph Neuron (DHGN) is a distributed single-cycle learning pattern recognition algorithm that can scale from coarsegrained to fine-grained networks and it has comparable accuracy to contemporary image recognition schemes. In this paper, we present an implementation of DHGN that works for multi-feature recognition of images. Our scheme is able to disseminate recognition of each feature within an image to a separate computational subnetwork. Thereby allowing a number of features being analysed simultaneously using a uniform recognition process. We have conducted tests on a collection of greyscale facial images. The results show that our approach produces high recognition accuracy through a simple distributed process. Furthermore, our approach implements single-cycle learning known as collaborative-comparison learning where new patterns are continuously stored using collaborative approach without affecting previously stored patterns. Our proposed scheme demonstrates higher classification accuracy in comparison with Back-Propagation Neural Network for multi-class images.

show abstract

“…One of such limitations is that a high value in a single histogram bin dominates the distance between two histograms, no matter the relative importance of this single value [6,8]. If we think about an image in terms of background/foreground regions, in general it is true that the foreground determines the semantic of the image and as such, it is more important in determining the similarity among images.…”

Section: Dlog Distance Functionmentioning

confidence: 99%

A compact and efficient image retrieval approach based on border/interior pixel classification

Stehling

Nascimento

Falcão

2002

Proceedings of the Eleventh International Conference on Information and Knowledge Management

Self Cite

202

View full text Add to dashboard Cite

This paper presents BIC (Border/Interior pixel Classification), a compact and efficient CBIR approach suitable for broad image domains. It has three main components: (1) a simple and powerful image analysis algorithm that classifies image pixels as either border or interior, (2) a new logarithmic distance (dLog) for comparing histograms, and (3) a compact representation for the visual features extracted from images. Experimental results show that the BIC approach is consistently more compact, more efficient and more effective than state-of-the-art CBIR approaches based on sophisticated image analysis algorithms and complex distance functions. It was also observed that the dLog distance function has two main advantages over vectorial distances (e.g., L1): (1) it is able to increase substantially the effectiveness of (several) histogram-based CBIR approaches and, at the same time, (2) it reduces by 50% the space requirement to represent a histogram.

show abstract

Color-based image retrieval using binary signatures

Cited by 26 publications

References 13 publications

Optimized trace transform based content based image retrieval algorithm

Optimized trace transform based content based image retrieval algorithm

Distributed Multi-Feature Recognition Scheme for Greyscale Images

A compact and efficient image retrieval approach based on border/interior pixel classification

Contact Info

Product

Resources

About