Content-Based Image Retrieval through Region Uniformly Partition

2012 ◽  
Vol 500 ◽  
pp. 471-474 ◽  
Author(s):  
Xiao Xiao ◽  
De Wen Zhuang ◽  
Shou Jue Wang
Keyword(s):  
Image Segmentation ◽  
Image Retrieval ◽  
Similarity Measure ◽  
Open Problem ◽  
Texture Features ◽  
Gabor Wavelet ◽  
Content Based Image Retrieval ◽  
Retrieval Performance ◽  
Color Features ◽  
Better Than

It has been demonstrated that accurate image segmentation is still an open problem. For avoiding this difficulties in content-based image retrieval, an region uniform partition approaching was proposed. Based on fusing regional color features using smooth slide histogram and texture features extracted using Gabor wavelet, we provided the corresponding similarity measure. The image retrieval performance on a subset of the COREL database are better than SIMPLIcity system showed the effectiveness of the proposed method.

scholarly journals Learning effective color features for content based image retrieval in dermatology

2011 ◽  
Vol 44 (9) ◽  
pp. 1892-1902 ◽  
Author(s):  
Kerstin Bunte ◽  
Michael Biehl ◽  
Marcel F. Jonkman ◽  
Nicolai Petkov
Keyword(s):  
Image Retrieval ◽  
Content Based Image Retrieval ◽  
Color Features

scholarly journals Modified JSEG algorithm for reducing over-segmentation problems in underwater coral reef images

2019 ◽  
Vol 9 (6) ◽  
pp. 5244
Author(s):  
Mohammad Sameer Aloun ◽  
Muhammad Suzuri Hitam ◽  
Wan NuralJawahir Hj Wan Yussof ◽  
Abdul Aziz K Abdul Hamid ◽  
Zainuddin Bachok
Keyword(s):  
Image Segmentation ◽  
Coral Reef ◽  
Texture Features ◽  
Color Histogram ◽  
Similarity Measurement ◽  
Segmentation Problem ◽  
Better Than ◽  
Observation Results ◽  
Color And Texture Features

<p>The original JSEG algorithm has proved to be very useful and robust in variety of image segmentation case studies.However, when it is applied into the underwater coral reef images, the original JSEG algorithm produces over-segementation problem, thus making this algorithm futile in such a situation. In this paper, an approach to reduce the over-segmentation problem occurred in the underwater coral reef image segmentation is presented. The approach works by replacing the color histogram computation in region merge stage of the original JSEG algorithm with the new computation of color and texture features in the similarity measurement. Based on the perceptual observation results of the test images, the proposed modified JSEG algorithm could automatically segment the regions better than the original JSEG algorithm.</p>

scholarly journals Implementation of early and late fusion methods for content-based image retrieval

2021 ◽  
Vol 8 (7) ◽  
pp. 97-105
Author(s):  
Ali Ahmed ◽  
◽  
Sara Mohamed ◽  
Keyword(s):  
Image Retrieval ◽  
Texture Features ◽  
Image Features ◽  
Distance Measures ◽  
Content Based Image Retrieval ◽  
Late Fusion ◽  
Query Image ◽  
Fusion Methods ◽  
And Performance ◽  
Image Repository

Content-Based Image Retrieval (CBIR) systems retrieve images from the image repository or database in which they are visually similar to the query image. CBIR plays an important role in various fields such as medical diagnosis, crime prevention, web-based searching, and architecture. CBIR consists mainly of two stages: The first is the extraction of features and the second is the matching of similarities. There are several ways to improve the efficiency and performance of CBIR, such as segmentation, relevance feedback, expansion of queries, and fusion-based methods. The literature has suggested several methods for combining and fusing various image descriptors. In general, fusion strategies are typically divided into two groups, namely early and late fusion strategies. Early fusion is the combination of image features from more than one descriptor into a single vector before the similarity computation, while late fusion refers either to the combination of outputs produced by various retrieval systems or to the combination of different rankings of similarity. In this study, a group of color and texture features is proposed to be used for both methods of fusion strategies. Firstly, an early combination of eighteen color features and twelve texture features are combined into a single vector representation and secondly, the late fusion of three of the most common distance measures are used in the late fusion stage. Our experimental results on two common image datasets show that our proposed method has good performance retrieval results compared to the traditional way of using single features descriptor and also has an acceptable retrieval performance compared to some of the state-of-the-art methods. The overall accuracy of our proposed method is 60.6% and 39.07% for Corel-1K and GHIM-10K ‎datasets, respectively.

Sign in / Sign up

Export Citation Format

Share Document