• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.277-286
• /
• 2014

In this paper, we propose a texture feature-based language identification by fusion of Gabor, MDLC (multi-lag directional local correlation), and co-occurrence features. In the proposed method, for a test image, Gabor magnitude images are first obtained by Gabor transform followed by magnitude operator. Moments for the Gabor magniude images are then computed and vectorized. MDLC images are then obtained by MDLC operator and their moments are computed and vectorized. GLCM (gray-level co-occurrence matrix) is next calculated from the test image and co-occurrence features are computed using the GLCM, and the features are also vectorized. The three vectors of the Gabor, MDLC, and co-occurrence features are fused into a feature vector. In classification, the WPCA (whitened principal component analysis) classifier, which is usually adopted in the face identification, searches the training feature vector most similar to the test feature vector. We evaluate the performance of our method by examining averaged identification rates for a test document image DB obtained by scanning of documents with 15 languages. Experimental results show that the proposed method yields excellent language identification with rather low feature dimension for the test DB.

• Mass Spectrometry Letters
• /
• v.5 no.4
• /
• pp.95-103
• /
• 2014

Characterization and studies of proteome are challenging because biological samples are complex, with a wide dynamic range of abundance. At present the proteins are identified by digestion into peptides, with subsequent identification of the peptides by mass spectrometry (MS). MS is a powerful technique for the purpose, but it cannot identify every peptide in such complex mixtures simultaneously. For accurate analysis and quantification it is important to separate the peptides first by chromatography into fractions of a size that MS can handle. With these less complex fractions, the probability is increased of identifying peptides of low abundance that would otherwise experience ion suppression effects due to the presence of peptides of high abundance. Enrichment for peptides with certain post-translational modifications helps to increase their detection rates as well. Electrostatic repulsion-hydrophilic interaction chromatography (ERLIC) is a mixed-mode chromatographic technique which combines the use of electrostatic repulsion and hydrophilic interaction. This review provides an overview of ERLIC and its various proteomics applications. ERLIC has been demonstrated to have good orthogonality to reverse phase liquid chromatography (RPLC), making it useful as a first dimension in multidimensional liquid chromatography (MDLC) and fractionation of digests in general. Peptides elute in order of their isoelectric points and polarity. ERLIC has also been successfully utilized for the enrichment for phosphopeptides and glycopeptides, facilitating their identification. In addition, it is promising for the study of peptide deamidation. ERLIC performs comparably well or better than established methods for these various applications, and serves as a viable and efficient workflow alternative.