Facial image retrieval based on local and regional features

Obulesu, A.; Kiran, J. Sasi; Kumar, V. Vijaya

doi:10.1109/icatcct.2015.7457000

Cited by 6 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Texture analysis has been studied extensively [1][2][3][4][5][6][7][8] from the past two decades due to its wide range of applications in industrial inspections [9], food science [10,11], content-based image retrieval [12,13,14], texture classification [15,16,17], medicine [18,19,20], face recognition [21,22,23], and age classification [24,25,26] among others. The goal of texture classification is assigning a sample image to one of the texture classes that are available.…”

Section: Introductionmentioning

confidence: 99%

Classification of Textures based on Noise Resistant Fundamental Units of Complete Texton Matrix

Kumari¹,

Kumar²,

Satyanarayana³

2018

IJIGSP

Self Cite

View full text Add to dashboard Cite

One of the popular descriptor for texture classification is the local binary pattern (LBP). LBP and its variants derives local texture features effectively. This paper integrates the significant local features derived from uniform LBPs(ULBP) and threshold based conversion factor non-uniform (NULBP) with complete textons. This integrated approach represents the complete local structural features of the image. The ULBPs are proposed to overcome the wide histograms of LBP. The ULBP contains fundamental aspects of local features. The LBP is more prone to noise and this may transform ULBP into NULBP and this degrades the overall classification rate. To addresses this, this paper initially transforms back, the ULBPs that are converted in to NULBPs due to noise using a threshold based conversion factor and derives noise resistant fundamental texture (NRFT) image. In the literature texton co-occurrence matrix(TCM) and multi texton histogram (MTH) are derived on a 2x2 window. The main disadvantage of the above texton groups is they fail in representing complete textons. In this paper we have integrated our earlier approach "complete texton matrix (CTM)" [16] on NRFT images. This paper computes the gray level cooccurrence matrix (GLCM) features on the proposed NRFCTM (noise resistant fundamental complete texton matrix) and the features are given to machine learning classifiers for a precise classification. The proposed method is tested on the popular databases of texture classification and classification results are compared with existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Textures based on Noise Resistant Fundamental Units of Complete Texton Matrix

Kumari¹,

Kumar²,

Satyanarayana³

2018

IJIGSP

Self Cite

View full text Add to dashboard Cite

show abstract

“…The two proposed descriptors TTMM H and TTMM GF are tested using the five popular databases namely: Colored Brodatz Texture (CBT) [36], Outex [37], UIUC [38], KTH-TIPS [39] and ALOT [40]. And brief description about these databases is given below and sample images of these databases are shown from figure 6 to 10.…”

Section: Resultsmentioning

confidence: 99%

Classification of Textures Based on Ternary Transition Motif Matrix Features

Bhamidipati

Kumar

2019

IJRTE

Self Cite

View full text Add to dashboard Cite

The various classification methods proposed in the literature are mostly extracted either local features or global features or color features. After an exhaustive study on various local, global and color descriptors this research found that one type of features may not yield good classification results. To address this paper, proposed new variant that integrates the color features derived from HSV color plane and transition based scan features. This paper initially converted RGB color plane image in to HSV color plane. The individual histograms of H, S and V plane are extracted as one of the features and these are named as pure color features. This paper derives a novel extension to the exiting motif frame works of the literature. The proposed ternary transition motif matrix (TTMM) is completely different from the existing motif frameworks and it is derived on the V-plane of the HSV color model. The TTTM scans the given 2x2 grid in a fixed format by visiting each pixel position exactly once. The TTMM derives a ternary transition pattern based on the relationship between grey level intensities of current pixel and its immediate pixel of scan instead of traversing on the incremental difference. The proposed TTMM derives a unique code for each 2x2 grid, ranging from 0 to 80 and replaces the 2x2 grid with this value. The co-occurrence matrix derived on this ternary transition motif (TTM) coded image is named as TTMM and it holds the spatial relationship between the TTM coded grids. The gray level co-occurrence matrix (GLCM) features derived on TTMM are integrated with the pure color features to derive final feature vector. This descriptor is applied on six popular databases using machine learning classifiers. The results are compared with existing motif based and other local based approaches. The results exhibit the high classification rate of the proposed method over the existing ones. .

show abstract

“…The LBP extracts the local information precisely. LBP is widely studied recently in age classification [37][38][39][40], face recognition [41,42], texture classification [43], segmentation [44,45], image retrieval [46,47,48] etc. and it obtained a good results.…”

Section: Related Work 21 Local Binary Pattern (Lbp)mentioning

confidence: 99%

Segmentation Method based on Texture Unit Approach Derived on Local Directional Pattern (LDP)

Subbaiah¹,

Kumar²

2017

IJCA

View full text Add to dashboard Cite

Image segmentation is one of the crucial steps for image analysis, interpretation and recognition. This paper presents cross diagonal neighborhood approach based on local direction pattern (LDP) descriptor. Edge based segmentation divides images into regions based on local edge responses. The local attributes and edge responses are the crucial factors for edge based segmentation scheme. The LDP descriptor precisely measures the amount of each edge response in and around a centre pixel. The LDP overcomes the noise related problems of the local binary operator (LBP). On LDP images three categories of texture units are derived by partitioning the 3 x 3 neighborhood in to cross texture unit (CTU) and diagonal texture unit (DTU), to reduce the huge dimensionalities involved in the basic texture units and to characterize the local edge information precisely. The segmentation method is tested on five large databases namely Wang, Oxford flowers, Indian facial expressions, Brodatz textures and standard images from Google. The segmentation results demonstrate the efficacy of the proposed method.

show abstract

Facial image retrieval based on local and regional features

Cited by 6 publications

References 25 publications

Classification of Textures based on Noise Resistant Fundamental Units of Complete Texton Matrix

Classification of Textures based on Noise Resistant Fundamental Units of Complete Texton Matrix

Classification of Textures Based on Ternary Transition Motif Matrix Features

Segmentation Method based on Texture Unit Approach Derived on Local Directional Pattern (LDP)

Contact Info

Product

Resources

About