Terms Of Average Retrieval Rate Research Articles

An extension of local mesh peak valley edge based feature descriptor for image retrieval in bio-medical images

Various texture based approaches have been proposed for image indexing in bio-medical image processing and a precise description of image for indexing in bio-medical image database has always been a challenging task. In this paper, an extension of local mesh peak valley edge pattern (LMePVEP) has been proposed and its effectiveness is experimentally justified. The proposed algorithm explores the relationship of center pixel with the surrounding ones along with the relationship of pixels amongst each other in five different directions. It is then compared with the original LMePVEP as well as a directional local ternary quantized extrema pattern (DLTerQEP) based approach using two bench mark databases viz. ELCAP database for lungs and Wiki cancer data set for thyroid cancer. Further a live dataset for brain tumor is also used for experimental evaluation. The experimental results show that an average improvement of 11.16% in terms of average retrieval rate (ARR) and 5.37% in terms of average retrieval precision (ARP) is observed for proposed enhanced LMePVEP over conventional LMePVEP.

New local sedec pattern descriptor for improving the retrieval efficiency in content-based image retrieval

In this paper, a novel content-based image retrieval (CBIR) method is proposed using the local sedec pattern (LScP). The local binary pattern (LBP) and the local ternary pattern (LTP), encode the relationship between the referenced pixel and its surrounding pixels, by computing gray-level difference, but in a different way. The proposed methods encode the relationship between the centre pixel and its neighbours, based on directions such as vertical, horizontal and diagonal. Calculation based on first order derivatives is used here. Second order derivative is also applied to obtain LScP. The performance of the proposed method is compared with the LTrP and other local pattern (LBP, LDP and LTP) which results are obtained using benchmark image databases viz., Corel 1000 database (DB1), Brodatz texture database (DB2). Performance of the LScP shows improvement in retrieval from 75.9%/48.7% to 86.52%/54.4% in DB1, for average precision/average recall as compared with LTrP and other local patterns. A similar comparison shows improvement from 85.30% to 91.5% in terms of average retrieval rate on database DB2.

A novel scale and rotation invariant texture image retrieval method using fuzzy logic classifier

A novel approach for content-based texture image retrieval system using fuzzy logic classifier is proposed in this paper. The novelty of this method is demonstrated by handling the complexity issues in texture image retrieval arising from rotation and scale variance. These issues are divided into four groups as non rotated non scaled, rotation invariant, scale invariant and scale and rotation invariant texture retrieval for retrieval performance analysis. Features of texture images are obtained using discrete wavelet transform based statistical features and gray level co-occurrence matrix based co-occurrence features. The fuzzy logic classifier is developed with Gaussian membership function with mean and standard deviations of the features. The retrieval performance improvement is carried out by considering various combinations of the features. The average retrieval rates for the four issues have been achieved at 99.40% with 40 features, 91% with 80 features, 65.2% with 40 features, and 63.4% with 65 features respectively. This method outperforms the existing methods in terms of average retrieval rate. The scale and rotation invariant texture retrieval is an incomparable work that has been demonstrated in the present paper.

Modified color motif co-occurrence matrix for image indexing and retrieval

In this paper, the modified color motif co-occurrence matrix (MCMCM) is presented for content-based image retrieval. The proposed method collects the inter-correlation between the red, green, and blue color planes which is absent in color motif co-occurrence matrix. The proposed method integrates the MCMCM and difference between the pixels of a scan pattern (DBPSP) features with equal weights in contrast to the system which integrates motif co-occurrence matrix, DBPSP, and color histogram with k-mean features with optimized weights. The retrieval results of the proposed method are tested on different image databases i.e. MIT VisTex (DB1) and Corel-1000 (DB2). The results after being investigated show a significant improvement in terms of average retrieval rate and average retrieval precision on DB1 database and average precision, average recall and average retrieval rate on DB2 database as compared to the state-of-art techniques on respective databases.

Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval

In this paper, we propose a novel image indexing and retrieval algorithm using local tetra patterns (LTrPs) for content-based image retrieval (CBIR). The standard local binary pattern (LBP) and local ternary pattern (LTP) encode the relationship between the referenced pixel and its surrounding neighbors by computing gray-level difference. The proposed method encodes the relationship between the referenced pixel and its neighbors, based on the directions that are calculated using the first-order derivatives in vertical and horizontal directions. In addition, we propose a generic strategy to compute nth-order LTrP using (n - 1)th-order horizontal and vertical derivatives for efficient CBIR and analyze the effectiveness of our proposed algorithm by combining it with the Gabor transform. The performance of the proposed method is compared with the LBP, the local derivative patterns, and the LTP based on the results obtained using benchmark image databases viz., Corel 1000 database (DB1), Brodatz texture database (DB2), and MIT VisTex database (DB3). Performance analysis shows that the proposed method improves the retrieval result from 70.34%/44.9% to 75.9%/48.7% in terms of average precision/average recall on database DB1, and from 79.97% to 85.30% and 82.23% to 90.02% in terms of average retrieval rate on databases DB2 and DB3, respectively, as compared with the standard LBP.

Multiresolution LBP Correlogram for Texture Image Indexing and Retrieval

A new image indexing and retrieval algorithm known as local binary pattern (LBP) correlogram is presented in this paper. LBP histogram captures only the patterns distribution in a texture while the spatial correlation between the pair of patterns is gathered by LBP correlogram. Multi-resolution texture decomposition and color correlation has been efficiently used in the proposed method where multi-resolution texture images are computed using Gaussian filter for collection of LBPs from these particular textures. Eventually, feature vectors are constructed by making into play the auto-correlation that exists between binary patterns. The retrieval results of the proposed method are examined on different texture image databases viz Brodatz database (DB1), MIT VisTex database (DB2), rotated Brodatz database (DB3) and small set of rotated Brodatz database (DB4), and shows a major improvement in terms of average retrieval rate as when weighed against with LBP histogram and some existing transform domain technique.

Sign and magnitude of local patterns for image indexing and retrieval

This paper presents a new image indexing and retrieval algorithm called sign and magnitude of local pattern (LP) operator. The local region of image is represented by using local difference operator (LDO) by separating the local region of the image into two components (the sign and the magnitude). The sign LP operator (S_LP) is a generalised LBP operator and magnitude LP operator (M_LP) is the mean and variances of the magnitudes of LDO. The combination of both operators (S_LP and M_LP) has been proposed in this paper as well as the combination of Gabor transform and LP operators (S_LP and M_LP) has proposed. The retrieval results of the proposed methods are tested on two different image databases, i.e., Brodatz database (DB1) and MIT VisTex database. The experimental results after investigation shows a significant improvement in terms of average retrieval rate as compared to S_LP (LBP) and some previously reported transform domain methods [dual tree complex wavelet transform (DT-CWT), dual tree rotated complex wavelet transform (DT-RCWT), DT-CWT+DT-RCWT etc.].