Search

Retinal diseases are the source for blindness in human eyes. These diseases are diagnosed by examining the fundus images of the retina. People who are affected by eye diseases have different types of lesions on their retina and some abnormalities in the retinal blood vessels as well as in optic disc. An automatic computerized retinal disease detection system requires the retinal structures to be segmented properly. In order to do it, quality of the image is to be enhanced to eliminate the image acquisition issues so as to separate easily the dark and bright retinal structures from its background. This can be done through various contrast enhancement and illumination equalization techniques in the preprocessing steps. Hence, this paper analyzes the performance of three different contrast enhancement techniques without illumination equalization and with illumination equalization for retinal fundus images on three benchmark datasets namely, diaretdb1, drive and ROC. Mean Square Error and Peak Signal-Noise Ratio are the two performance metrics considered.

Texture descriptors have an important role in recognizing face images. However, almost all the existing local texture descriptors use nearest neighbors to encode a texture pattern around a pixel. But in face images, most of the pixels have similar characteristics with that of its nearest neighbors because the skin covers large area in a face and the skin tone at neighboring regions are same. Therefore this paper presents a general framework called Local Texture Description Framework that uses only eight pixels which are at certain distance apart either circular or elliptical from the referenced pixel. Local texture description can be done using the foundation of any existing local texture descriptors. In this paper, the performance of the proposed framework is verified with three existing local texture descriptors Local Binary Pattern (LBP), Local Texture Pattern (LTP) and Local Tetra Patterns (LTrPs) for the five issues viz. facial expression, partial occlusion, illumination variation, pose variation and general recognition. Five benchmark databases JAFFE, Essex, Indian faces, AT&T and Georgia Tech are used for the experiments. Experimental results demonstrate that even with less number of patterns, the proposed framework could achieve higher recognition accuracy than that of their base models.

Texture is one of the fundamental features for describing image characteristics. Face can be seen as a composition of micro-patterns of textures. The texture analysis community has proposed a variety of descriptors for face recognition. Local binary pattern (LBP) is a very popular texture operator used in a wide variety of applications including face recognition. Many variants of LBP have been proposed so far and let more emerges due to its overwhelming success. In this series, a new face recognition algorithm called local derivative ternary pattern (LDTP) is proposed in this paper in order to alleviate the face recognition rate under real-time challenges. The strength of the descriptor is demonstrated on four different databases containing more than 2000 face images under variations in lighting, facial expression, and pose. The experimental results show that the proposed LDTP approach provides a better representation of face patterns and achieves higher recognition rates than LBP and its derivatives.

Automatic face recognition remains an interesting but challenging computer vision open problem. Poor illumination is considered as one of the major issue, since illumination changes cause large variation in the facial features. To resolve this, illumination normalization preprocessing techniques are employed in this paper to enhance the face recognition rate. The methods such as Histogram Equalization (HE), Gamma Intensity Correction (GIC), Normalization chain and Modified Homomorphic Filtering (MHF) are used for preprocessing. Owing to great success, the texture features are commonly used for face recognition. But these features are severely affected by lighting changes. Hence texture based models Local Binary Pattern (LBP), Local Derivative Pattern (LDP), Local Texture Pattern (LTP) and Local Tetra Patterns (LTrPs) are experimented under different lighting conditions. In this paper, illumination invariant face recognition technique is developed based on the fusion of illumination preprocessing with local texture descriptors. The performance has been evaluated using YALE B and CMU-PIE databases containing more than 1500 images. The results demonstrate that MHF based normalization gives significant improvement in recognition rate for the face images with large illumination conditions.

Texture feature plays a predominant role in recognizing face images. However different persons can have similar texture features that may degrade the system performance. Hence in this paper, the problem of face similarity is addressed by proposing a solution which combines textural and geometrical features. An algorithm is proposed to combine these two features. Five texture descriptors and few geometrical features are considered to validate the proposed system. Performance evaluations of these features are carried out independently and jointly for three different issues such as expression variation, illumination variation and partial occlusion with objects. It is observed that the combination of textural and geometrical features enhance the accuracy of face recognition. Experimental results on Japanese Female Facial Expression (JAFFE) and ESSEX databases indicate that the texture descriptor Local Binary Pattern achieves better recognition accuracy for all the issues considered.

Texture is one of the chief characteristics of an image. In recent years, local texture descriptors have garnered attention among researchers in describing effective texture patterns to demarcate facial images. A feature descriptor titled Local Texture Description Framework-based Modified Local Directional Number pattern (LTDF_MLDN), capable of encoding texture patterns with pixels that lie at dissimilar regions, has been proposed recently to describe effective features for face images. However, the role of the descriptor can differ with different classifiers and distance metrics for diverse issues in face recognition. Hence, in this paper, an extensive evaluation of the LTDF_MLDN is carried out with an Extreme Learning Machine (ELM), a Support Vector Machine (SVM) and a Nearest Neighborhood Classifier (NNC) which uses Euclidian, Manhattan, Minkowski, G-statistics and chi-square dissimilarity metrics to illustrate differences in performance with respect to assorted issues in face recognition using six benchmark databases. Experimental results depict that the proposed descriptor is best suited with NNC for general case and expression variation, whereas, for the other facial variations ELM is found to produce better results.

Texture is the surface property that is used to identify and recognise objects. This property is widely used in many applications including texture-based face recognition systems, surveillance, identity verification and so on. The Local binary pattern (LBP) texture method is most successful for face recognition. Owing to the great success of LBP, recently many models, which are variants of LBP have been proposed for texture analysis. Some of the derivatives of LBPs are multivariate local binary pattern, centre symmetric local binary pattern, local binary pattern variance, dominant local binary pattern, advanced local binary pattern, local texture pattern (LTP) and local derivative pattern (LDP). In this scenario, it is essential to review, whether LBP or their derivatives perform better for face recognition. The real-time challenges such as illumination changes, rotations, angle variations and facial expression variations are evaluated by different LBP-based models. Experiments were conducted on the Japanese female facial expression, YALE and FRGC version2 databases. The results show that LDP and LTP perform much better than the other LBP-based models.

Texture features alone cannot help us to recognize faces, because there may be several people with similar texture features. Likewise geometry based features can also be similar in different people. When the two methods are experimented separately, there may be inaccurate results. There might be better results when the two methods are combined and used. So this paper tries to evaluate the performance of both the features independently and jointly in face recognition. Texture feature extraction methods such as Grey Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP) and Elliptical Local Binary Template (ELBT) are proposed to combine with geometry based method. Japanese Female Facial Expression (JAFFE) database is used to conduct the test. Experiments are carried out in two ways. First, all the methods are experimented with images having less expression. Then they are tested with all images in the database. Experimental results show that ELBT outperform the other methods and also the recognition rate is higher when texture features are combined with geometry based features. For classification K-nearest neighbourhood algorithm is used. And for recognition Chi square statistic (χ 2) is used as dissimilarity measure.

Automatic face recognition is an emerging active research area spanning several disciplines such as image processing, computer vision and pattern recognition. Face recognition is a challenging problem because of diversity in faces and variations caused by expressions, illuminations, pose, occlusion, aging and so on. In this paper, multi-resolution techniques are combined with texture features to mitigate the effect of facial variations. Multi-resolution techniques investigated in this paper are discrete wavelet transform (DWT), ridgelet, curvelet and contourlet. Texture features are extracted from these transforms by using local binary pattern (LBP), local texture pattern (LTP), local derivative pattern (LDP), local tetra patterns (LTrPs) and local derivative ternary pattern (LDTP). The proposed method is tested on JAFFE, ORL, Yale, Essex and Georgia Tech databases containing more than 4,000 face images. From the results, it is observed that, the combined approach of multi-resolution techniques with texture features enhances the face recognition rate. In particular, contourlet transform with LDTP perform better than the other techniques considered for investigation.