Content based image indexing and retrieval using directional local extrema and magnitude patterns

G Model AEUE-51154; No. of Pages 7

ARTICLE IN PRESS Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

Contents lists available at ScienceDirect

International Journal of Electronics and Communications (AEÜ) journal homepage: www.elsevier.com/locate/aeue

Content based image indexing and retrieval using directional local extrema and magnitude patterns P. Vijaya Bhaskar Reddy ∗ , A. Rama Mohan Reddy Department of Computer Science & Engineering, SVU College of Engineering, Sri Venkateswara University, Tirupati 517502, Andhra Pradesh, India

a r t i c l e

i n f o

Article history: Received 17 June 2013 Accepted 23 January 2014 Keywords: Ditectional local extrema patterns (DLEPs) Local binary patterns (LBPs) Image retrieval Pattern recognition Databases

a b s t r a c t In this paper, we integrate the concept of directional local extremas and their magnitude based patterns for content based image indexing and retrieval. The standard ditectional local extrama pattern (DLEP) extracts the directional edge information based on local extrema in 0◦ , 45◦ , 90◦ , and 135◦ directions in an image. However, they are not considering the magnitudes of local extremas. The proposed method integrates these two concepts for better retrieval performance. The sign DLEP (SDLEP) operator is a generalized DLEP operator and magnitude DLEP (MDLEP) operator is calculated using magnitudes of local extremas. The performance of the proposed method is compared with DLEP, local binary patterns (LBPs), block-based LBP (BLK LBP), center-symmetric local binary pattern (CS-LBP), local edge patterns for segmentation (LEPSEG) and local edge patterns for image retrieval (LEPINV) methods by conducting two experiments on benchmark databases, viz. Corel-5K and Corel-10K databases. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to other existing methods on respective databases. © 2014 Elsevier GmbH. All rights reserved.

1. Introduction Retrieval of images from large image databases has been an active area of research for long due to its applications in various fields like satellite imaging, medicine, etc. Content based image retrieval (CBIR) systems extract features from the raw images and calculate an associative measure (similarity or dissimilarity) between a query image and database images based on these features. Hence the feature extraction is a very important step and the effectiveness of a CBIR system depends typically on the method of extraction of features from raw images. Several methods achieving effective feature extraction have been proposed in the literature [1–4]. Texture is the most important feature for CBIR. Smith and Chang used the mean and variance of the wavelet coefficients as texture features for CBIR [5]. Moghaddam et al. proposed the Gabor wavelet correlogram (GWC) for CBIR [6,7]. Ahmadian and Mostafa used the wavelet transform for texture classification [8]. Moghaddam et al. Introduced new algorithm called wavelet correlogram (WC) [9]. Saadatmand and Moghaddam [7,10] improved the performance of the WC algorithm by optimizing the quantization thresholds using genetic algorithm (GA).

∗ Corresponding author. Tel.: +91 9666508044. E-mail addresses: [email protected] (P. Vijaya Bhaskar Reddy), [email protected] (A. Rama Mohan Reddy).

Birgale et al. [11] and Subrahmanyam et al. [12] combined the color (color histogram) and texture (wavelet transform) features for CBIR. Subrahmanyam et al. proposed correlogram algorithm for image retrieval using wavelets and rotated wavelets (WC + RWC) [13]. Ojala et al. proposed the local binary pattern (LBP) features for texture description [14] and these LBPs are converted to rotational invariant for texture classification [15]. Pietikainen et al. proposed the rotational invariant texture classification using feature distributions [16]. Ahonen et al. [17] and Zhao and Pietikainen [18] used the LBP operator facial expression analysis and recognition. Heikkila and Pietikainen proposed the background modeling and detection by using LBP [19]. Huang et al. proposed the extended LBP for shape localization [20]. Heikkila et al. used the LBP for interest region description [21]. Li and Staunton used the combination of Gabor filter and LBP for texture segmentation [22]. Zhang et al. proposed the local derivative pattern for face recognition [23]. They have considered LBP as a nondirectional first order local pattern, which are the binary results of the first-order derivative in images. The block-based texture feature which use the LBP texture feature as the source of image description is proposed in [24] for CBIR. The center-symmetric local binary pattern (CS-LBP) which is a modified version of the well-known LBP feature is combined with scale invariant feature transform (SIFT) in [25] for description of interest regions. Yao and Chen [26] have proposed two types of local edge patterns (LEP) histograms, one is

1434-8411/$ – see front matter © 2014 Elsevier GmbH. All rights reserved. http://dx.doi.org/10.1016/j.aeue.2014.01.012

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model

ARTICLE IN PRESS

AEUE-51154; No. of Pages 7

P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

2

LEPSEG for image segmentation, and the other is LEPINV for image retrieval. The LEPSEG is sensitive to variations in rotation and scale, on the contrary, the LEPINV is resistant to variations in rotation and scale. Subrahmanyam et al. [27] have proposed the DLEP which collects the directional edge information for image retrieval. The above discussed various extensions of LBP features consider only the sign of differences but not magnitudes. The main contributions of this work are summarized as follows: (a) the existing DLEPs are considering only sign of difference between the pixels whereas our method considers the both sign as well as magnitudes and (b) the performance of the proposed method is tested on benchmark image databases. The paper is summarized as follows: in Section 1, a brief review of content based image retrieval and related work is given. Section 2, presents a concise review of local pattern operators. The proposed system framework and query matching are illustrated in Section 3. Experimental results and discussions are given in Section 4. Based on above work, conclusions and future scope are derived in Section 5.

computed by comparing its gray scale value with its neighborhoods based on Eq. (1) and (2): LBPP,R =

P 

 f1 (x) =

2(p−1) × f1 (I(gp ) − I(gc ))

(1)

p=1

1 x≥0 0

(2)

else

where I(gc ) denotes the gray value of the center pixel, I(gp ) represents the gray value of its neighbors, P stands for the number of neighbors and R, the radius of the neighborhood. After computing the LBP pattern for each pixel (j, k), the whole image is represented by building a histogram as shown in Eq. (3). HLBP (l) =

N1 N2  

f2 (LBP(j, k), l);

l ∈ [0, (2P − 1)]

(3)

j=1 k=1

 f2 (x, y) =

1 x=y 0

else

(4)

where the size of input image is N1 × N2 . Fig. 1 shows an example of obtaining an LBP from a given 3 × 3 pattern. The histograms of these patterns contain the information on the distribution of edges in an image.

2. Local patterns 2.1. Local binary patterns (LBPs) The LBP operator was introduced by Ojala et al. [14] for texture classification. Success in terms of speed (no need to tune any parameters) and performance is reported in many research areas such as texture classification [14–16], face recognition [17,18], object tracking, bio-medical image retrieval and finger print recognition. Given a center pixel in the 3 × 3 pattern, LBP value is

2.2. Block based local binary patterns (BLK LBP) Takala et al. [24] have proposed the block based LBP for CBIR. The block division method is a simple approach that relies on subimages to address the spatial properties of images. It can be used together with any histogram descriptors similar to LBP. The method works

Fig. 1. Calculation of LBP.

Fig. 2. Proposed image retrieval system framework.

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model

ARTICLE IN PRESS

AEUE-51154; No. of Pages 7

P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

3

in the following way: First it divides the model images into square blocks that are arbitrary in size and overlap. Then the method calculates the LBP distributions for each of the blocks and combines the histograms into a single vector of sub-histograms representing the image. 2.3. Center-symmetric local binary patterns (CS LBP) Instead of comparing each pixel with the center pixel, Heikkila et al. [25] have compared center-symmetric pairs of pixels for CS LBP as shown in Eq. (5): CS LBPP,R =

P 

2(p−1) × f1 (I(gp ) − I(gp+(P/2) ))

(5)

p=1

After computing the CS LBP pattern for each pixel (j, k), the whole image is represented by building a histogram as similar to the LBP. 2.4. Directional local extrema patterns (DLEPs) Subrahmanyam et al. [27] directional local extrema patterns (DLEPs) for CBIR. DLEP describes the spatial structure of the local texture using the local extrema of center gray pixel gc . In proposed DLEP for a given image the local extrema in 0◦ , 45◦ , 90◦ , and 135◦ directions are obtained by computing local difference between the center pixel and its neighbors as shown below: I  (gi ) = I(gc ) − I(gi );

i = 1, 2, . . ., 8

(6)

The local extremas are obtained by Eq. (7). ˆI˛ (gc ) = f3 (I  (gj ), I  (gj+4 ));

 



f3 (I (gj ), I (gj+4 )) =

j=

1+˛ ∀˛ = 0◦ , 45

1 I  (gj ) × I  (gj+4 )≥0 0

(7)

(8)

else

The DLEP is defined (˛ = 0◦ , 45◦ , 90◦ , and 135◦ ) as follows:



DLEP(I(gc )) = {ˆI˛ (gc ); ˆI˛ (g1 ); ˆI˛ (g2 ); . . .ˆI˛ (g8 )} ˛

(9)

Eventually, the given image is converted to DLEP images with values ranging from 0 to 511. After calculation of DLEP, the whole image is represented by building a histogram supported by Eq. (10) [27]. H DLEP| (l) =

N1 N2  



f2 ( DLEP(j, k) , l); ˛

˛

l ∈ [0, 511]

(10)

j=1 k=1

where the size of input image is N1 × N2 . In literature [28] and [29], it is already proved that the magnitude of the difference patterns along with sign patterns show a significant improvement in the retrieval performance as compared with the sign patterns. The concept which is available in [28,29] is motivated us to propose the magnitude DLEP patterns for image retrieval. In this paper, we combine the DLEP and magnitude DLEP features for image retrieval and shows a significant improvement as compared to the DLEP alone (see Section 4).

Fig. 3. Comparison of proposed method with other existing methods on Corel-5K. (a) Category wise performance in terms of precision, (b) category wise performance in terms of recall, (c) total database performance in terms of average precision and (d) total database performance in terms of ARR.

analyze that there is a possible to increase the performance of the system by considering the magnitude of local extremas. The magnitude patterns for local extremas are calculated follows. ˆI˛M (gc ) = f4 (I  (gj ), I  (gj+4 ));

j=

1+˛ ∀˛ = 0◦ , 45◦ , 90◦ , and 135◦ 45 (11)

2.5. Magnitude directional local extrema patterns (MDLEPs) The existing DLEP [27] considers only the sign of local extrema values which are calculated between the given center pixel and its surrounding neighbors. From the above observation it can be

 



f4 (I (gj ), I (gj+4 )) =

1 abs(I  (gj )) + abs(I  (gj+4 ))≥Th 0

(12)

else

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model

ARTICLE IN PRESS

AEUE-51154; No. of Pages 7

P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

4

Table 1 Results of various methods in terms of precision and recall on Corel-5K and Corel-10K databases PM: DLEP + MDLEP; BLK LBP: block based LBP [24]. Database

Performance

CS LBP

LEPSEG

LEPINV

BLK LBP

LBP

DLEP

PM

Corel-5K

Precision (%) Recall (%)

32.9 14.0

41.5 18.3

35.1 14.8

45.7 20.3

43.6 19.2

48.8 21.1

54.4 24.1

Corel-10K

Precision (%) Recall (%)

26.4 10.1

34.0 13.8

28.9 11.2

38.1 15.3

37.6 14.9

40.0 15.7

45.4 18.4

   1 (abs( I  (gj ) ) + abs( I  (gj+4 ) )) (i,k) (i,k) N1 × N2 N1

Th =

Method

N2

3. Proposed system framework (13) 3.1. Image retrieval system

i=1 k=1

The MDLEP is defined

(˛ = 0◦ ,

45◦ ,

90◦ ,

and

135◦ )

as follows:

 MDLEP(I(gc )) = {ˆI˛M (gc ); ˆI˛M (g1 ); ˆI˛M (g2 ); .. . .ˆI˛M (g8 )} ˛

(14)

After calculation of MDLEP, the whole image is represented by building a histogram supported by Eq. (10).

In this paper, we integrate the features of DLEP and magnitude DLEP for image retrieval. First, the image is loaded and converted into gray scale if it is RGB. Secondly, the DLEPs and magnitude DLEPs (MDLEPs) are collected and then go for the histograms calculation. Finally, the feature vector is generated by concatenating the

Fig. 4. Two examples of image retrieval by proposed method (DLEP) on Corel-5K database.

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model

ARTICLE IN PRESS

AEUE-51154; No. of Pages 7

P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

5

histograms of DLEP and MDLEP. Fig. 2 depicts the flowchart of the proposed technique and algorithm for the same is presented here: Algorithm. Input: Image; Output: Retrieval result Load the image and converted in to gray scale (if it is RGB). 1. Calculate the local extrema in 0◦ , 45◦ , 90◦ , and 135◦ directions. 2. Compute the DLEP and MDLEP patterns in 0◦ , 45◦ , 90◦ , and 135◦ 3. directions. 4. Construct the histograms for DLEP and MDLEP patterns in 0◦ , 45◦ , 90◦ , and 135◦ directions. Construct the feature vector by concatenating all histograms. 5. Compare the query image with the image in the database using Eq. (15). 6. Retrieve the images based on the best matches. 7.

3.2. Query matching Feature vector for query image Q is represented as fQ = (fQ1 , fQ2 , . . .fQLg ) obtained after the feature extraction. Similarly each image in the database is represented   with feature vector fDBj = (fDBj1 , fDBj2 , . . .fDBjLg ); j = 1, 2, . . ., DB. The goal is to select n best images that resemble the query image. This involves selection of n top matched images by measuring   the distance between query image and image in the database DB. In order to match the images we used d1 similarity distance metric [27] computed by Eq. (15). D(Q, DB) =

Lg    fDBji − fQi   1 + fDBji + fQ i=1

i

   

(15)





where fDBji is ith feature of jth image in the database DB. 4. Experiments The effectiveness of the proposed method is analyzed by conducting two experiments on benchmark databases. Further, it is mentioned that the databases used are Corel-5K and Corel-10K. In experiments #1 and #2, images from Corel database [30] have been used. This database consists of large number of images of various contents ranging from animals to outdoor sports to natural images. These images have been pre-classified into different categories each of size 100 by domain professionals. Some researchers think that Corel database meets all the requirements to evaluate an image retrieval system, due its large size and heterogeneous content. In all experiments, each image in the database is used as the query image. For each query, the system collects n database images X = (x1 , x2 , . . ., xn ) with the shortest image matching distance computed using Eq. (15). If the retrieved image xi = 1, 2, . . ., n belongs to same category as that of the query image then we say the system has appropriately identified the expected image else the system fails to find the expected image. The performance of the proposed method is measured in terms of average precision/average retrieval precision (ARP), average recall/average retrieval rate (ARR) as shown below: For the query image Iq , the precision is defined as follows: precision, P(Iq ) =

number of relevant images retrieved total number of images retrieved

     average precision, ARP = P(Ii ) DB  i=1 1

|DB| 

(16)

number of relevant images retrieved total number of relevant images in the database

  |DB|   1 average recall, ARR =   R(Ii ) DB 

(19)

i=1

4.1. Corel-5K database (17)

recall, R(Iq ) =

Fig. 5. Comparison of proposed method with other existing methods on Corel-10K. (a) Category wise performance in terms of precision, (b) category wise performance in terms of recall, (c) total database performance in terms of average precision and (d) total database performance in terms of ARR.

(18)

Corel-5K database consists of 5000 images which are collected from 50 different domains have 100 images per domain. The performance of the proposed method is measured in terms of ARP and ARR as shown in Eqs. (16)–(19). Table 1 illustrates the retrieval results of proposed method and other existing methods on Corel-5K and Corel-10K databases in

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model AEUE-51154; No. of Pages 7 6

ARTICLE IN PRESS P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

Fig. 6. Two examples of image retrieval by proposed method (DLEP) on Corel-10K database.

terms of average precision and recall. Fig. 3(a) and (b) shows the category wise performance of methods in terms of precision and recall on Corel-5K database. The performance of all techniques in terms of average precision and ARR on Corel-5K database can be seen in Fig. 3(c) and (d), respectively. From Table 1 and Fig. 3, the following points are observed. 1. The proposed method (DLEP + MDLEP) showing 21.5%, 12.9%, 19.3%, 8.7%, 10.8% and 5.6% more performance as compared to CS LBP, LEPSEG, LEPINV, BLK LBP, LBP and DLEP, respectively, in terms of ARP on Core-5K database. 2. The proposed method (DLEP + MDLEP) showing 10.1%, 5.8%, 9.3%, 3.8%, 4.9% and 3% more performance as compared to CS LBP, LEPSEG, LEPINV, BLK LBP, LBP and DLEP, respectively, in terms of ARR on Core-5K database. From Table 1, Fig. 3 and above observations, it is clear that the proposed method shows a significant improvement as compared to other existing methods in terms of their evaluation measures on Corel-5K database. Fig. 4 illustrates the query results of proposed method on Corel-5K database (top left image is the query image). 4.2. Corel-10K database Corel-5K database consists of 10,000 images which are collected from 100 different domains have 100 images per domain. The performance of the proposed method is measured in terms of average precision, average recall, and average retrieval rate (ARR) as shown in Eqs. (16)–(19) (Fig. 4). Fig. 5(a) and (b) shows the category wise performance of methods in terms of precision and recall on Corel-10K database. The performance of all techniques in terms of average precision and ARR on Corel-10K database can be seen in Fig. 5(c) and (d), respectively. From Table 1 and Fig. 5, it is clear that the proposed method shows a significant improvement as compared to other existing

Table 2 Computational cost of various methods for the feature extraction time and retrieval time for a given query image. Method

Feature extraction time (s)

Retrieval time (s)

Total

LBP CS LBP LEPSEG LEPINV DLEP PM

0.03 0.04 0.10 0.15 0.21 0.25

0.02 0.015 0.02 0.02 0.026 0.027

0.05 0.055 0.12 0.17 0.236 0.277

Query image size is 256 × 384.

methods in terms of their evaluation measures on Corel-10K database. Fig. 6 illustrates the query results of proposed method on Corel-10K database (top left image is the query image). 4.3. Computational cost vs. performance Table 2 illustrates the computational cost of various methods for the feature extraction time and retrieval time for a given query image. The computational cost of the proposed method is little bit more as compared to the DLEP, as it outperforms: 1. 2. 3. 4.

The DLEP by 5.6% in terms of ARP on Corel-5K database. The DLEP by 3.0% in terms of ARR on Corel-5K database. The DLEP by 5.4% in terms of ARP on Corel-10K database. The DLEP by 2.7% in terms of ARR on Corel-10K database.

From the above observations, it is clear that the proposed method shows a significant improvement in retrieval performance with the small increment of computational cost. 5. Conclusions A new approach which integrates the DLEP and MDLEP features for content based image retrieval is presented in this paper. The

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012

G Model AEUE-51154; No. of Pages 7

ARTICLE IN PRESS P. Vijaya Bhaskar Reddy, A. Rama Mohan Reddy / Int. J. Electron. Commun. (AEÜ) xxx (2014) xxx–xxx

proposed MDLEP differs from the existing DLEP in a manner that it extracts the directional edge information based on the magnitudes of local extrema in 0◦ , 45◦ , 90◦ , and 135◦ directions in an image. Performance of the proposed method is tested by conducting two experiments on benchmark image databases and retrieval results show a significant improvement in terms of their evaluation measures as compared to other existing methods on respective databases. Acknowledgment Our sincere thanks to Dr. Subrahmanyam Murala, Post-Doc Fellow, University of Windsor, ON, Canada for providing the source code and results for DLEP and LBP variant methods on Corel-5K and Corel-10K databases. References [1] Rui Y, Huang TS. Image retrieval: current techniques, promising directions and open issues. J Vis Commun Image Represent 1999;10:39–62. [2] Smeulders AWM, Worring M, Santini S, Gupta A, Jain R. Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 2000;22(12):1349–80. [3] Kokare M, Chatterji BN, Biswas PK. A survey on current content based image retrieval methods. IETE J Res 2002;48(3/4):261–71. [4] Liu Y, Zhang D, Lu G, Ma W-Y. A survey of content-based image retrieval with high-level semantics. Pattern Recogn 2007;40:262–82. [5] Smith JR, Chang SF. Automated binary texture feature sets for image retrieval. In: Proc. IEEE int. conf. acoustics, speech and signal processing. New York: Columbia Univ.; 1996. p. 2239–42. [6] Moghaddam HA, Khajoie TT, Rouhi AH. A new algorithm for image indexing and retrieval using wavelet correlogram. In: Int. conf. image processing, vol. 2. Tehran, Iran: K.N. Toosi Univ. of Technol.; 2003. p. 497–500. [7] Saadatmand MT, Moghaddam HA. Enhanced wavelet correlogram methods for image indexing and retrieval. In: IEEE int. conf. image processing. Tehran, Iran: K.N. Toosi Univ. of Technol.; 2005. p. 541–4. [8] Ahmadian A, Mostafa A. An Efficient Texture Classification Algorithm using Gabor wavelet. In: 25th annual international conf. of the IEEE EMBS. 2003. p. 930–3. [9] Moghaddam HA, Khajoie TT, Rouhi AH, Saadatmand MT. Wavelet correlogram: a new approach for image indexing and retrieval. Pattern Recogn 2005;38(12):2506–18. [10] Saadatmand MT, Moghaddam HA. A novel evolutionary approach for optimizing content based image retrieval. IEEE Trans Syst Man Cybern 2007;37(1):139–53. [11] Birgale L, Kokare M, Doye D. Color and texture features for content based image retrieval. In: International conf. computer graphics, image and visualisation. 2006. p. 146–9. [12] Subrahmanyam M, Gonde AB, Maheshwari RP. Color and texture features for image indexing and retrieval. In: IEEE int. advance computing conf. 2009. p. 1411–6. [13] Subrahmanyam M, Maheshwari RP, Balasubramanian R. A correlogram algorithm for image indexing and retrieval using wavelet and rotated wavelet filters. Int J Signal Imaging Syst Eng 2011;4(1):27–34. [14] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classification based on feature distributions. J Pattern Recogn 1996;29(1):51–9. [15] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 2002;24(7):971–87. [16] Pietikainen M, Ojala T, Scruggs T, Bowyer KW, Jin C, Hoffman K, et al. Overview of the face recognition using feature distributions. Pattern Recogn 2000;33(1):43–52.

7

[17] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: applications to face recognition. IEEE Trans Pattern Anal Mach Intell 2006;28(12):2037–41. [18] Zhao G, Pietikainen M. Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach Intell 2007;29(6):915–28. [19] Heikkil MA, Pietikainen M. A texture based method for modeling the background and detecting moving objects. IEEE Trans Pattern Anal Mach Intell 2006;28(4):657–62. [20] Huang X, Li SZ, Wang Y. Shape localization based on statistical method using extended local binary patterns. In: Proc. int. conf. image graphics. 2004. p. 184–7. [21] Heikkila M, Pietikainen M, Schmid C. Description of interest regions with local binary patterns. Pattern Recogn 2009;42:425–36. [22] Li M, Staunton RC. Optimum Gabor filter design and local binary patterns for texture segmentation. Pattern Recogn 2008;29:664–72. [23] Zhang B, Gao Y, Zhao S, Liu J. Local derivative pattern versus local binary pattern: face recognition with higher-order local pattern descriptor. IEEE Trans Image Proc 2010;19(2):533–44. [24] Takala V, Ahonen T, Pietikainen M. Block-based methods for image retrieval using local binary patterns. In: SCIA 2005, vol. 3450. 2005. p. 882–91. [25] Heikkil M, Pietikainen M, Schmid C. Description of interest regions with local binary patterns. Pattern Recogn 2009;42:425–36. [26] Yao C-H, Chen S-Y. Retrieval of translated, rotated and scaled color textures. Pattern Recogn 2003;36:913–29. [27] Subrahmanyam M, Maheshwari RP, Balasubramanian R. Directional local extrema patterns: a new descriptor for content based image retrieval. Int J Multimedia Inform Retrieval 2012;1(3):191–203. [28] Subrahmanyam M, Maheshwari RP, Balasubramanian R. Sign and magnitude patterns for image indexing and retrieval. Int J Comput Vis Robot 2010;1(3):279–96. [29] Subrahmanyam M, Maheshwari RP, Balasubramanian R. Local tetra patterns: a new feature descriptor for content based image retrieval. IEEE Trans Image Process 2012;21(5):2874–86. [30] Corel-10K image database. Available: http://www.ci.gxnu.edu.cn/cbir/Dataset. aspx P. Vijaya Bhaskar Reddy has completed his M. Tech in Computer Science and Engineering from Bharath University, Chennai in 2008. Currently he is pursuing the Ph.D. degree in the Department of Computer Science and Engineering, Sri Venkateswara University, Tirupati, Andhra Pradesh, India. His major fields of interests are Content Based Image Retrieval, Image Processing and Patterns Recognition.

A. Rama Mohan Reddy is working as Professor & HOD at Department of Computer Science and Engineering, Sri Venkateswara University, Tirupati, Andhra Pradesh, India. He Completed his M. Tech. in Computer Science from NIT Warangal. After that, he completed his Ph.D. in the area of software Architecture from Sri Venkateswara University, Tirupati, Andhra Pradesh, India. He has more than 20 years of teaching experience. He published many papers in the peer-refereed journals and conferences. His major fields of interests are Image Processing, Software Engineering, Software Architecture and Data Mining.

Please cite this article in press as: Vijaya Bhaskar Reddy P, Rama Mohan Reddy A. Content based image indexing and retrieval using directional local extrema and magnitude patterns. Int J Electron Commun (AEÜ) (2014), http://dx.doi.org/10.1016/j.aeue.2014.01.012