Orthogonal moments are the projections of image functions onto particular kernel functions. They play vital role in digital image feature extraction being rotation, scaling, translation invariant, robust to image noise and contain minimal information redundancy. These moments are derived from statistically independent orthogonal polynomials which can be continuous or discrete. Most of the modern researches have explored integer-order orthogonal moments, but fractional-order moments are in fact superclass of integer order and more efficient but underrated. This paper proposes fractional-order Zernike moments (FZM) along with SVM to recognize grape leaf diseases. Comparative analysis with integer-order Zernike moments along with other feature selection methods has been explored. FZM–SVM-based technique outperforms other state-of-art techniques yielding $$97.34\%$$
 at order 30.

Plant disease recognition using fractional-order Zernike moments and SVM classifier

This paper presents a novel biometric watermarking algorithm for improving the recognition accuracy and protecting the face and fingerprint images from tampering. Multi-resolution Discrete Wavelet Transform is used for embedding the face image in a fingerprint image. An intelligent learning algorithm based on υ-Support Vector Machine (SVM) is introduced to enhance the quality of the extracted face image. The performance of the watermarking algorithm is experimentally validated using existing fingerprint and face recognition algorithms. The results show that the extracted fingerprint and face images are of high quality. The use of SVM enhances the performance of face recognition by at least 10% even when the watermarked image is subjected to certain geometric and frequency attacks such as scaling, cropping, compression and filtering.

Improving biometric recognition accuracy and robustness using DWT and SVM watermarking

The magnitude of Zernike moments (ZMs) has been used as rotation invariant features for classification problems in the past. Their individual real and imaginary components and phase coefficients are ignored, because they change with rotation. This study presents a new method to modify the individual real and imaginary components of ZMs which change due to image rotation. The modified real and imaginary components are then used as invariant image descriptors. The performance of the proposed method and magnitude-based ZM method is analysed on grayscale face images and binary character images in application to the fields of face recognition and character recognition, respectively. Experimental results show that the proposed method is robust to image rotation. For classification, the authors use L 1 -norm as the similarity measure. It is shown that the proposed method gives better recognition rate over the magnitude-based ZM method, comparatively at low orders of moment and thus it is recommended for pose invariant face recognition and also for rotation invariant character recognition. This has been proved by comparing the results of the proposed method with existing prominent methods of feature extraction in face and character recognition. On ORL database, the proposed method achieves the highest recognition rate of 96.5%, whereas a recognition rate of 99.7% is obtained on binary Roman character images.

Rotation invariant complex Zernike moments features and their applications to human face and character recognition

This paper presents a robust two-stage face recognition approach that combines the traits of global features in first stage and the local features in second stage. The global features are extracted from Zernike moments (ZMs) method that encompasses the useful characteristics of being invariant to image rotation, scale, and noise. The local features are obtained from the histogram-based Weber Law Descriptor (WLD) having tremendous qualities like invariance to scale, change in image intensities, rotation, and noise. The novelty of this paper is twofold: (1) an efficient approach is used for combining the global and local features which is based on the human psychology to trace and memorize the known persons, i.e., locate some similar faces from the overall appearance of different persons and later identify from this the specific individual on the basis of their interior differences like shape of eyes, nose, etc.; (2) a method is used for providing the weights to individual face patches in extraction of local features, which is based on the averaged discrimination competence of features within a patch. The performance of proposed two-stage face recognition approach is analyzed against some major hurdles of this system, i.e., illumination, expression, scale, pose, occlusion, and noise variations. The proposed method achieves the highest recognition rate of 98.0% and 94.1% on ORL and Yale databases, respectively. The experimental results on these well-known face databases demonstrate that the proposed method is highly robust to illumination variation and also generates superior results against other variations.

Robust two-stage face recognition approach using global and local features

A new set of Gegenbauer moment invariants is proposed for pattern recognition applications. These moment invariants are expressed as a linear combination of geometric moment invariants where the later are invariants under translation, scaling and rotation of the image they describe. The invariance of Gegenbauer moments is tested by using different binary- and gray-level images. The obtained results show the accuracy of the new set of Gegenbauer moment invariants.

New Set of Gegenbauer Moment Invariants for Pattern Recognition Applications

This paper presents an approach to boost the performance of pseudo Zernike moments in face recognition. This approach is a hybrid of a kernel trick, discriminant function and pseudo Zernike moments (PZM), namely as Kernel-based Fisher Pseudo Zernike Moments (KFPZM). KFPZM maps the moment-based features into a high dimensional feature space via kernel function for disclosing the underlying variables which carry significant information about the image. Then, it performs discriminant analysis onto the mapped features to enhance the discrimination power via Fisher's Linear Discriminant (FLD). Experimental results show that the proposed method outperforms the sole PZM and the integrated FLD with PZM methods, achieving recognition rate of 98.11% and 93.03% in the face databases with facial expression variations and illumination variations, respectively.

Andrew Ben Jin Teoh

Papers

Enhanced pseudo Zernike moments in face recognition