Retrieval of colour and texture images using local directional peak valley binary pattern
- PDF / 2,841,941 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 207 Views
THEORETICAL ADVANCES
Retrieval of colour and texture images using local directional peak valley binary pattern Srishti Gupta1 · Partha Pratim Roy2 · Debi Prosad Dogra3 · Byung‑Gyu Kim4 Received: 6 April 2019 / Accepted: 30 March 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Many content-based image retrieval (CBIR) methods are being developed to store more and more information about images in shorter feature vectors and to improve image retrieval rate. In the proposed method, two-step approach to CBIR has been developed. The first step generates an image mask from local binary pattern (LBP). This LBP mask is then utilized to draw comparison between the centre pixel and the eight surrounding pixels. The second step involves drawing the peak and valley patterns of local directional binary pattern for each image which is then combined with the colour histogram to retrieve similar images. Existing methods suffer from lower average image retrieval accuracy even with larger feature vectors. The proposed method overcomes such problems through shorter feature vectors that can store more information about the image. As illustrated through experimental results, the proposed method produces promising results with shorter feature vector of length 56 and improved image retrieval rate of about 5–10%. Our method outperforms similar techniques when tested with public data sets. Keywords LBP value · Image retrieval · Image classification · Feature vector · Texture database · Face database · Local binary pattern
1 Introduction Digital era has seen many technological advancements leading to the surge in number of digital images available online or with the users. Different kinds of images such as photographs, texture images, diagrams and paintings are available for processing. Texture images include pictures of fabric, wood, flower, metal, grass, leaf, rock, etc. Retrieval of the proper image has become very important in many contexts. Since such a task cannot be done manually, content-based image retrieval (CBIR) has become more important. Lot of research works are going on to make CBIR more efficient
* Partha Pratim Roy [email protected] 1
Indian Institute of Technology Roorkee, Roorkee, India
2
Department of CSE, Indian Institute of Technology Roorkee, Roorkee, India
3
School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar, India
4
Department of IT Engineering, Sookmyung Women’s University, Seoul, Republic of Korea
and less time-consuming [17]. CBIR involves capturing visual contents of an image in the form of a feature vector [14]. Feature vector of an image typically stores vital information about it. Drawing similarity between images involves comparing these feature vectors. Researchers have proposed many local features over the years [19]. Often these local features extract local information of the image by comparing pixel intensity of a centre pixel with the pixel intensity of its nearest neighbours [3]. This work mainly focuses on improving t
Data Loading...
