In this paper, we propose a method that uses Local Zernike Moments (LZM) for face recognition in low-resolution face images. Global Zernike Moments produce one moment value for whole image, whereas LZM are based on the evaluation of the moments for each pixel. LZM are shown to achieve significant success and robustness in face recognition. In order to further increase the robustness of LZM agai...

In this paper, we present a new and effective color image retrieval scheme for combining all the three i.e. color, texture and shape information, which achieved higher retrieval efficiency. Firstly, the image is predetermined by using fast color quantization algorithm with clusters merging, and then a small number of dominant colors and their percentages can be obtained. Secondly, the spatial t...

Current merit functions for 2D/3D registration usually rely on comparing pixels or small regions of images using some sort of statistical measure. Problems connected to this paradigm the sometimes problematic behaviour of the method if noise or artefacts (for instance a guide wire) are present on the projective image. We present a merit function for 2D/3D registration which utilizes the decompo...

In order to improve the detection of malicious tampering images, it is necessary to decrease the fragility of hidden watermarks, even for digital images which have been incidentally distorted. In this paper, we propose a new invariant semi-fragile digital watermarking technique based on eigenvalues and eigenvectors of real symmetric matrix generated by the four pixel pairs. A signature bit for ...

This paper presents a new feature selection method for learning based single image super-resolution (SR). The performance of learning based SR strongly depends on the quality of the feature. Better features produce better co-occurrence relationship between low-resolution (LR) and high-resolution (HR) patches, which share the same local geometry in the manifold. In this paper, Zernike moment is ...

This thesis presents a novel lip-reading approach to classifying utterances from video data, without evaluating voice signals. This work addresses two important issues which are • the efficient representation of mouth movement for visual speech recognition • the temporal segmentation of utterances from video. The first part of the thesis describes a robust movement-based technique used to ident...

Offline Tamil Handwritten character recognition system using a combination of Zernike moments and diagonal features of Zones are proposed in this paper. The proposed recognition system yields higher rate of recognition accuracy compared to the systems developed using the conventional feature extractions using horizontal and vertical methods. Since, Zernike moments are known as better descriptor...

In order to improve the detection of malicious tampering images, it is necessary to decrease the fragility of hidden watermarks, even for digital images which have been incidentally distorted. In this paper, we propose a new invariant semi-fragile digital watermarking technique based on eigenvalues and eigenvectors of real symmetric matrix generated by the four pixel pairs. A signature bit for ...

Handwritten automatic character recognition has attracted many researchers all over the world to contribute automatic character recognition domain. Shape identification and feature extraction is very important part of any character recognition system and success of method is highly dependent on selection of features. However feature extraction is the most important step in defining the shape of...

In order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of 3 classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments and Hu moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling c...