Local tri-directional patterns: A new texture feature descriptor for image retrieval

In this paper, combinations of spatial orientation tree (SOT), two-dimensional complex wavelet transform (CWT) and vocabulary tree (VT) is used for feature collection and retrieval of the images from natural as well as texture image database. SOT represents the parent-offspring relationship among the wavelet coefficients in multi-resolution wavelet sub-bands. Similarly, CWT captures directional information more accurately as compared to discrete wavelet transforms (DWT). SOT gives the set of descriptor vectors for each image which are further indexed by using vocabulary tree. The proposed method is tested on Corel 1000 and texture image database (Brodatz and USC) and the retrieval results have demonstrated a significant improvement in average precision, average recall and average rank compared to complex wavelet transform (CWT), optimal quantized wavelet correlogram (OQWC), Gabor wavelet correlogram (GWC).

The local binary pattern (LBP) and its variants have shown the effectiveness in texture images classification, face recognition, and other applications. However, most of these LBP methods only focus on the histogram of LBP patterns and ignore the spatial contextual information between LBP patterns. In this paper, we propose a 2D-LBP method which uses a sliding window to count the weighted occurrence number of the rotation invariant uniform LBP pattern pairs to obtain the spatial contextual information. The multi-resolution 2D-LBP features can also be obtained when the radius of 2D-LBP is changed. At last, a two-stage classifier which acts as an ensemble learning step is followed to achieve an accurate classification by combining the predictions on each 2D-LBP with single resolution. Theoretical proof shows that the proposed 2D-LBP is a general framework and can be integrated on other LBP variants to derive new feature extraction methods. Experimental results show that, the proposed method achieves 99.71%, 97.09%, 98.48%, and 49.00% classification accuracy on the public “Brodatz,” “CUReT,” “UIUC,” and “FMD” texture image databases, respectively. Compared with the original LBP and its variants, the proposed method obtains higher classification accuracy under different cases, and simultaneously owns shorter time complexity.

The texture is a two- and three-dimensional design element that is distinguished by the visual and physical properties perceived. Textured areas in the image can be marked with uniform or varying spatial intensity distribution. There are many techniques and methods from simple to sophisticated which available including machine learning-based methods to modify the texture map. The texture feature description becomes a new challenge in the field of computer vision and pattern recognition since the emergence of the local pattern binary method (LBP). This study proposes a new method called Local Weighting Pattern (LWP) for modifying textures based on the pixel's neighborhood of an RGB image. The results of this study obtained that LWP method produces a texture with a unique and artistic visualization. The Log function has been used to improve the image quality of the LWP method.

A new texture spectrum descriptor was proposed for region description in the paper, which is an extension of center-symmetric local ternary pattern (CS-LTP). Different from CS-LTP, the central piexl of the region are considered together in the definition of the extended center-symmetric local ternary pattern (eCS-LTP). Without adding the dimension of CS-LTP, the proposed operator contains more information of the region. The two methods, CS-LTP and eCS-LTP were tested on two commonly used texture image databases in the context of image retrieval and the experimental results show that eCS-LTP gives better performance than CS-LTP.Keywordslocal binary patterncenter-symmetric local binary patterncenter-symmetric local ternary patternextended center-symmetric local ternary pattern

In this paper, a new Face image classification or Recognition method based on Two Dimensional Discrete Cosine Transform (2D - DCT) with Linear Discriminant Analysis (LDA) and Probabilistic Neural Network (PNN) is proposed. This method consists of three steps, i) Transformation of images from special to frequency domain using Two dimensional discrete cosine transform ii) Feature extraction using Linear Discriminant Analysis and iii) classification using Probabilistic Neural Network. Linear Discriminant Analysis searches the directions for maximum discrimination of classes in addition to dimensionality reduction. Combination of Two Dimensional Discrete Cosine transform and Linear Discriminant Analysis is used for improving the capability of Linear Discriminant Analysis when few samples of images are available. Probabilistic Neural network (PNN) is a promising tool and gives fast and accurate classification of face images. Evaluation was performed on two face data bases. First database of 400 face images from AT&T (ORL) face database, and the second database of thirteen students are taken. The proposed method gives fast and better recognition rate when compared to other classifiers. The main advantage of this method is its high speed processing capability and low computational requirements in terms of both speed and memory utilizations.

The texture is a high-flying feature in an image and has been extracted to represent the image for image retrieval applications. Many texture features are being offered for image retrieval. This paper proposes a local binary pattern-based texture feature called Weber Global Statistics Tri-Directional Pattern (WGSTriDP) to retrieve the images. This pattern combines the advantages of differential excitation components in the Weber Local Binary Pattern (WLBP), sign and magnitude components in the Local Tri-Directional Pattern (LTriDP), and global statistics. Differential Excitation (DE) and Global Statistics TriDirectional Pattern (GSTriDP) are two components of WGSTriDP. The WGSTriDP gains the benefit of discrimination concerning human perception from differential excitation as well as incorporates global statistics into sign and magnitude components in the pattern derived from the local neighborhoods. The effectiveness of the pattern in image retrieval is experimented with in two benchmark databases, such as ORL (face database) and UIUC (texture database). According to the results of the experiments, WGSTriDP outperforms other local patterns in retrieving similar images from the database.

A new features based algorithm for face recognition is proposed. The algorithm is based on locating features on faces and finding the correspondence of these features between faces using an algorithm which is adopted from the works of Yasein and Agathoklis. The algorithm is using feature extraction through filtering with Mexican-hat wavelets and detection of correspondence of the feature points through comparison of Zernike moments. The transformation of the feature points between images is obtained using an iterative weighted least-squares algorithm which allows to eliminate outliers. The face recognition is based on the residual error between the feature points after transformation. The performance of the proposed method is evaluated using experiments with a face database and compared against existing techniques for face recognition. The results of experiments with varying pose and illumination conditions show that the proposed method performs well compared to existing feature based face recognition techniques.

A new illumination normalisation scheme based on reflectance ratio (RR) and contrast stretching (CS), feature extraction by integer wavelet transform (IWT) in fisher subspace for face recognition is proposed in this paper. RR is ratio of pixel intensity to average pixel intensity of its neighbourhood that discards illumination effects which is followed by CS to obtain further illuminated normalised images. Robust feature extraction is acquired by selecting low frequency coefficients and ignoring high frequency coefficients using IWT which makes proposed scheme computationally efficient. Illumination normalised feature extraction by combination of RR-CS and IWT model is followed by fisher linear discriminant analysis (FLDA) to achieve robust feature vector that provides best projection direction of training and test data sets. The recognition accuracy of 100% on CMU-PIE, Yale B and 99.05% (average) on extended Yale B face databases along with comparison with state of art methods proved strength of proposed model.

Principal curves are nonlinear generalizations of principal components analysis. They are smooth self-consistent curves that pass through the middle of the distribution. By analysis of existed principal curves, we learn that a soft k-segments algorithm for principal curves exhibits good performance in such situations in which the data sets are concentrated around a highly curved or self-intersecting curves. Extraction of features are critical to improve the recognition rate of off-line handwritten characters. Therefore, we attempt to use the algorithm to extract structural features of off-line handwritten characters. Experiment results show that the algorithm is not only feasible for extraction of structural features of characters, but also exhibits good performance. The proposed method can provide a new approach to the research for extraction of structural features of characters.

1D-local binary pattern based feature extraction for classification of epileptic EEG signals

A rapid growth in medical ultrasound database makes it difficult for medical practitioners to manage and search relevant data with good efficiency. Hence, a novel image retrieval technique using Mean Distance Local Binary Pattern (Mean Distance LBP) has been proposed for content-based image retrieval. The conventional local binary pattern (LBP) converts every pixel of image into a binary pattern based on their relationship with neighbourhood pixels. The proposed feature descriptor differs from local binary pattern as it transforms the mutual relationship of all neighbouring pixels in a binary pattern based on their standard deviation templates as well as Euclidean distance from the center pixel. Color feature and Gray Level Co-occurrence Matrix have also been used in this work. To prove the excellence of the proposed method, experiments have been conducted on two different databases of natural images and face images. Further, the method is applied on real time ultrasound database for retrieval of liver images from a set of ultrasound images of various organs. The performance has been observed using well-known evaluation measures, precision and recall, and compared with some state-of-art local patterns. Comparison shows a significant improvement in the proposed method over existing methods.

The goodness of the features extracted from the instances and the number of training instances are two key components in machine learning, and building an effective model is largely affected by these two factors. Acquiring a large number of training instances is very expensive in some situations such as in the medical domain. Designing a good feature set, on the other hand, is very hard and often requires domain expertise. In computer vision, image descriptors have emerged to automate feature detection and extraction; however, domain-expert intervention is typically needed to develop these descriptors. The aim of this paper is to utilize genetic programming to automatically construct a rotation-invariant image descriptor by synthesizing a set of formulas using simple arithmetic operators and first-order statistics, and determining the length of the feature vector simultaneously using only two instances per class. Using seven texture classification image datasets, the performance of the proposed method is evaluated and compared against eight domain-expert hand-crafted image descriptors. Quantitatively, the proposed method has significantly outperformed, or achieved comparable performance to, the competitor methods. Qualitatively, the analysis shows that the descriptors evolved by the proposed method can be interpreted.

1089-778X © 2017 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. The goodness of the features extracted from the instances and the number of training instances are two key components in machine learning, and building an effective model is largely affected by these two factors. Acquiring a large number of training instances is very expensive in some situations such as in the medical domain. Designing a good feature set, on the other hand, is very hard and often requires domain expertise. In computer vision, image descriptors have emerged to automate feature detection and extraction; however, domain-expert intervention is typically needed to develop these descriptors. The aim of this paper is to utilize genetic programming to automatically construct a rotation-invariant image descriptor by synthesizing a set of formulas using simple arithmetic operators and first-order statistics, and determining the length of the feature vector simultaneously using only two instances per class. Using seven texture classification image datasets, the performance of the proposed method is evaluated and compared against eight domain-expert hand-crafted image descriptors. Quantitatively, the proposed method has significantly outperformed, or achieved comparable performance to, the competitor methods. Qualitatively, the analysis shows that the descriptors evolved by the proposed method can be interpreted.

A human speaker recognition expert often observes the speech spectrogram in multiple different scales for speaker recognition, especially under the short utterance condition. Inspired by this action, this paper proposes a novel multi-resolution time frequency feature (MRTF) extraction method, which is obtained by performing a 2-Dimensional discrete cosine transform (DCT) in multi-scale on the time frequency spectrogram matrix and then selecting and combining to the final multi-scaled transformed elements. Compared to the traditional Mel-Frequency Cepstral Coefficient (MFCC) feature extraction, the proposed method can make better use of multi-resolution temporal-frequency information. Beyond this, we also proposed three complementary combination strategies of MFCC and MRTF: in feature level, in i-vector level and in score level. Comparing their performance. We found the best results are obtained by combination in i-vector level. In the three NIST 2008 Speaker Recognition Evaluation datasets, the proposed method is the most effective for improving the performance under short utterance than under long utterance. And after the combination, we can achieve an EER of 11.32 % and MinDCF of 0.054 in the 10sec-10sec trials on the male dataset, which is an absolute 3 % improvement of EER than the best reported result in this field.

A Non-Intrusive Load Monitoring (NILM) method for residential appliances based on ac- tive power signal is presented. This method works e ectively with a single active power measurement taken at a low sampling rate (1 s). The proposed method utilizes the Karhunen Lo eve (KL) expan- sion to decompose windows of active power signals into subspace components in order to construct a unique set of features, referred to as signatures, from individual and aggregated active power signals. Similar signal windows were clustered in to one group prior to feature extraction. The clustering was performed using a modified mean shift algorithm. After the feature extraction, energy levels of signal windows and power levels of subspace components were utilized to reduce the number of possible ap- pliance combinations and their energy level combinations. Then, the turned on appliance combination and the energy contribution from individual appliances were determined through the Maximum a Pos- teriori (MAP) estimation. Finally, the proposed method was modified to adaptively accommodate the usage patterns of appliances at each residence. The proposed NILM method was validated using data from two public databases: tracebase and reference energy disaggregation data set (REDD). The pre- sented results demonstrate the ability of the proposed method to accurately identify and disaggregate individual energy contributions of turned on appliance combinations in real households. Furthermore, the results emphasise the importance of clustering and the integration of the usage behaviour pattern in the proposed NILM method for real households