Time filter

Source Type

Walia E.,South Asian University | Goyal A.,Guru Nanak Institute of Management and Technology | Brar Y.S.,Guru Nanak Institutions
Signal, Image and Video Processing | Year: 2014

This paper proposes a new algorithm using global and local features for content-based image retrieval. Global features are extracted using the magnitude of Zernike moments (ZMs). Local features are obtained through local directional pattern (LDP). Generally, LDP is used to extract texture-based features from an image. In this paper, LDP is used to encode both texture and shape information of an image to represent more meaningful features. To encode texture-based features, original image is used to compute the LDP features. To extract shape information from an image, dual-tree complex wavelet transform (DT-CWT) is applied on image which generates six directional wavelets. These six directional wavelets are superimposed in order to obtain shape-encoded image. LDP is then applied on this wavelet-based shape-encoded image. Further, to enhance retrieval accuracy, LDP features are extracted from patches of both original and shape-encoded images. These patches are assigned with weights based on average discrimination capability of features in a patch. Experiments are performed using three different standard databases with various variations such as pose, distortion, partial occlusion and complex structure. The proposed technique achieves 96.4 and 98.76 % retrieval accuracy at a recall of 50 %, for Kimia-99 and COIL-100 databases, respectively. For MPEG-7 CE-2 shape database, retrieval accuracy of 61.93 % is achieved in terms of average Bull's eye performance (BEP). The proposed technique is also tested on Springer medical image database to explore its scope in other areas, wherein it attains average BEP of 69.68 % in comparison with 61.52 % with ZMs. It is observed that the proposed technique outperforms other well-known existing methods of image retrieval. © 2013 Springer-Verlag London.


Walia E.,MM University | Singh C.,Punjabi University | Goyal A.,Guru Nanak Institute of Management and Technology
Journal of Real-Time Image Processing | Year: 2012

A fast and numerically stable recursive method for the computation of orthogonal Fourier-Mellin moments (OFMMs) is proposed. Fast recursive method is developed for the radial polynomials which occur in the kernel function of the OFMMs, thus enhancing the overall computation speed. The proposed method is free from any overflow situations as it does not consist of any factorial term. It is also free from underflow situations as no power terms are involved. The proposed recursive method is claimed to be fastest in comparison with the direct and other methods to compute OFMMs till date. The elimination of the computation of factorial terms makes the moments very stable even up to an order of 200, which become instable in conventional or in any other recursive methods proposed earlier wherein instability occurs at moment order ≥25. Experiments are performed on standard test images to prove the superiority of the proposed method on existing methods in terms of speed and numerical stability. © 2010 Springer-Verlag.


Goyal A.,Guru Nanak Institute of Management and Technology | Walia E.,South Asian University
International Journal of Imaging and Robotics | Year: 2012

Zernike Moments (ZMs) have been most widely used in extracting the region based shape features of an image such as Logo, Trademark, Clip-art etc. Though ZMs are assumed to be the best descriptors, still retrieval of accurate images is an important research area. In most of the researches, emphasis is given only on magnitude of ZMs and phase component is ignored. Complex Zernike Moments (CZMs) take both Phase and Magnitude component for feature extraction. Global features are extracted using ZMs or CZMs. In order to capture local details of an image, variety of options are available i.e. Wavelets, Mean and Standard deviation of Centroid distance, Curvature on edged images etc. The retrieval results of global features are compared with results obtained using combined local and global features. Experiments are performed on MPEG-7 CE-2 shape database. Recall and Precision, Bulls Eye Performance (BEP) are chosen as measures for retrieval performance. It is observed that a combination of local and global features i.e. Wavelets and Complex Zernike Moments (WCZMs) perform better in terms of retrieval accuracy without any overhead of increased feature space. Based on our experiments, WCZMs are recommended for SBIR system to achieve better retrieval accuracy. In addition to being rotationally invariant, WCZMs are found to be robust towards blur and noise. Other local features like Curvature and Centroid distance when used with ZMs prove better in terms of retrieval accuracy but WCZMs outperform this descriptor also. © 2012 by IJIR (CESER Publications).


Goyal A.,Guru Nanak Institute of Management and Technology | Walia E.,South Asian University
Signal, Image and Video Processing | Year: 2014

Shape, being an important part of an object, has a special place in the field of shape-based image retrieval (SBIR). To retrieve most appropriate images, various descriptors are applied in SBIR like Zernike moments (ZMs), complex Zernike moments (CZMs) etc. Though ZMs/CZMs are good in SBIR but they are capable of extracting only global details of an image, hence something in addition to this is desirable to improve the performance of SBIR system. This paper presents experimental analysis of pixel-based dense descriptors such as local binary pattern (LBP), local directional pattern (LDP) and their variants. These descriptors are used as local features along with ZMs global features in achieving higher and accurate retrieval rate in SBIR system. We have analyzed these variants of LBP/LDP with various similarity measures on images. In case of ZMs, the magnitude component is used as global features. These methods are tested separately on suitable shape databases. Various databases used in the paper are MPEG-7 CE-2 region-based database, MPEG-7 CE-1 contour-based database and Trademark database. It can be concluded from the experimental analysis that the performance of LDP along with ZMs is better than that of ZMs alone and of ZMs along with other variants of LBP and LDP. © 2012, Springer-Verlag London Limited.

Loading Guru Nanak Institute of Management and Technology collaborators
Loading Guru Nanak Institute of Management and Technology collaborators