Taxonomy and phylogeny of the manna lichens and allied species (Megasporaceae)

This dissertation is focused on the taxonomy, phylogeny, and ecology of the vagrant, erratic and allied terricolous and saxicolous species of the genera Aspicilia A. Massal. and Circinaria Link (Megasporaceae), particularly those traditionally referred to as manna lichens . The group has previously been defined on the basis of few morphological characters. The phylogeny of the family Megasporaceae is inferred from the combined dataset of nuLSU and mtSSU sequences. Five genera Aspicilia, Circinaria, Lobothallia, Megaspora, and Sagedia are recognized. Lobothallia is sister of the four other genera, while Aspicilia and Sagedia form the next clade. All these genera have small asci with eight spores. Circinaria is a sister genus of Megaspora, and these two have in common asci with (1 4) 6 8 large spores. Circinaria forms a monophyletic group and sphaerothallioid species form a monophyletic group within Circinaria. The presence of certain morphological characters such as pseudocyphellae, thickness of cortex and medulla layers, as well as ecological differences in sphaerothallioid species distinguish it from some other crustose species, especially those containing aspicilin and characterised by thin cortex and medulla layers, conidium length c. 6 12 µm and absence of pseudocyphellae. If sphaerothallioid species are accepted as a distinct genus, the rest of the Circinaria species would remain as a paraphyletic assemblage. Currently, the genus Circinaria includes all the sphaerothallioid species and its generic position is confirmed and accepted. Thus, it is proposed as a correct generic name also for the manna lichens described originally in other genera. Phylogeny at the species level was studied using nrITS sequence data. Traditionally, morphological characters have been used for the recognition of species. They were re-evaluated in the light of molecular data. Since characters such as vagrant, erratic and crustose growth forms proved to be misleading for the recognition of some species, a combination of several characters (including molecular data) is recommended. Vagrant growth form seems to have evolved several times among the distantly related lineages and even within a single population. The reasons behind the high plasticity in the external morphology of the sphaerothallioid Circinaria remain, however, unknown. Six new species are recognized: Aspicilia tibetica, Circinaria arida, C. digitata nom provis., C. gyrosa nom. provis., C. rogeri nom. provis., and C. rostamii nom. provis. Based on an analysis of nrITS dataset, three new erratic, vagrant and crustose species were also recognized, but these require additional study. The results also reveal that C. elmorei and C. hispida are not monophyletic as currently understood. In addition, 13 new combinations in the genus Circinaria are proposed.

Choice of Classifiers in Hierarchical Recognition of Online Handwritten Kannada and Tamil Aksharas

In this paper, we propose a novel dexterous technique for fast and accurate recognition of online handwritten Kannada and Tamil characters. Based on the primary classifier output and prior knowledge, the best classifier is chosen from set of three classifiers for second stage classification. Prior knowledge is obtained through analysis of the confusion matrix of primary classifier which helped in identifying the multiple sets of confused characters. Further, studies were carried out to check the performance of secondary classifiers in disambiguating among the confusion sets. Using this technique we have achieved an average accuracy of 92.6% for Kannada characters on the MILE lab dataset and 90.2% for Tamil characters on the HP Labs dataset.

Machine recognition of printed Kannada text

This paper presents the design of a full fledged OCR system for printed Kannada text. The machine recognition of Kannada characters is difficult due to similarity in the shapes of different characters, script complexity and non-uniqueness in the representation of diacritics. The document image is subject to line segmentation, word segmentation and zone detection. From the zonal information, base characters, vowel modifiers and consonant conjucts are separated. Knowledge based approach is employed for recognizing the base characters. Various features are employed for recognising the characters. These include the coefficients of the Discrete Cosine Transform, Discrete Wavelet Transform and Karhunen-Louve Transform. These features are fed to different classifiers. Structural features are used in the subsequent levels to discriminate confused characters. Use of structural features, increases recognition rate from 93% to 98%. Apart from the classical pattern classification technique of nearest neighbour, Artificial Neural Network (ANN) based classifiers like Back Propogation and Radial Basis Function (RBF) Networks have also been studied. The ANN classifiers are trained in supervised mode using the transform features. Highest recognition rate of 99% is obtained with RBF using second level approximation coefficients of Haar wavelets as the features on presegmented base characters.

Optimal feature extraction for bilingual OCR

Feature extraction in bilingual OCR is handicapped by the increase in the number of classes or characters to be handled. This is evident in the case of Indian languages whose alphabet set is large. It is expected that the complexity of the feature extraction process increases with the number of classes. Though the determination of the best set of features that could be used cannot be ascertained through any quantitative measures, the characteristics of the scripts can help decide on the feature extraction procedure. This paper describes a hierarchical feature extraction scheme for recognition of printed bilingual (Tamil and Roman) text. The scheme divides the combined alphabet set of both the scripts into subsets by the extraction of certain spatial and structural features. Three features viz geometric moments, DCT based features and Wavelet transform based features are extracted from the grouped symbols and a linear transformation is performed on them for the purpose of efficient representation in the feature space. The transformation is obtained by the maximization of certain criterion functions. Three techniques : Principal component analysis, maximization of Fisher's ratio and maximization of divergence measure have been employed to estimate the transformation matrix. It has been observed that the proposed hierarchical scheme allows for easier handling of the alphabets and there is an appreciable rise in the recognition accuracy as a result of the transformations.

Taxonomic Implications of a Field Study of Morphotypes of Hanuman Langurs (Semnopithecus entellus) in Peninsular India

The Hanuman langur is one of the most widely distributed and morphologically variable non-human primates in South Asia. Even though it has been extensively studied, the taxonomic status of this species remains unresolved due to incongruence between various classification schemes. This incongruence, we believe, is largely due to the use of plastic morphological characters such as coat color in classification. Additionally these classification schemes were largely based on reanalysis of the same set of museum specimens. To bring greater resolution in Hanuman langur taxonomy we undertook a field survey to study variation in external morphological characters among Hanuman langurs. The primary objective of this study is to ascertain the number of morphologically recognizable units (morphotypes) of Hanuman langur in peninsular India and to compare our field observations with published classification schemes. We typed five color-independent characters for multiple adults from various populations in South India. We used the presence-absence matrix of these characters to derive the pair-wise distance between individuals and used this to construct a neighbor-joining (NJ) tree. The resulting NJ tree retrieved six distinct clusters, which we assigned to different morphotypes. These morphotypes can be identified in the field by using a combination of five diagnostic characters. We determined the approximate distributions of these morphotypes by plotting the sampling locations of each morphotype on a map using GIS software. Our field observations are largely concordant with some of the earliest classification schemes, but are incongruent with recent classification schemes. Based on these results we recommend Hill (Ceylon Journal of Science, Colombo 21:277-305, 1939) and Pocock (Primates and carnivora (in part) (pp. 97-163). London: Taylor and Francis, 1939) classification schemes for future studies on Hanuman langurs.

Wavelet Transform Codec for Fast Retrieval of Slices of 3D Objects

We propose a method to encode a 3D magnetic resonance image data and a decoder in such way that fast access to any 2D image is possible by decoding only the corresponding information from each subband image and thus provides minimum decoding time. This will be of immense use for medical community, because most of the PET and MRI data are volumetric data. Preprocessing is carried out at every level before wavelet transformation, to enable easier identification of coefficients from each subband image. Inclusion of special characters in the bit stream facilitates access to corresponding information from the encoded data. Results are taken by performing Daub4 along x (row), y (column) direction and Haar along z (slice) direction. Comparable results are achieved with the existing technique. In addition to that decoding time is reduced by 1.98 times. Arithmetic coding is used to encode corresponding information independently

Online character recognition using regression techniques

This paper introduces a scheme for classification of online handwritten characters based on polynomial regression of the sampled points of the sub-strokes in a character. The segmentation is done based on the velocity profile of the written character and this requires a smoothening of the velocity profile. We propose a novel scheme for smoothening the velocity profile curve and identification of the critical points to segment the character. We also porpose another method for segmentation based on the human eye perception. We then extract two sets of features for recognition of handwritten characters. Each sub-stroke is a simple curve, a part of the character, and is represented by the distance measure of each point from the first point. This forms the first set of feature vector for each character. The second feature vector are the coeficients obtained from the B-splines fitted to the control knots obtained from the segmentation algorithm. The feature vector is fed to the SVM classifier and it indicates an efficiency of 68% using the polynomial regression technique and 74% using the spline fitting method.

Creation of a Huge Annotated Database for Tamil and Kannada OHR

This paper describes the efforts at MILE lab, IISc, to create a 100,000-word database each in Kannada and Tamil for the design and development of Online Handwritten Recognition. It has been collected from over 600 users in order to capture the variations in writing style. We describe features of the scripts and how the number of symbols were reduced to be able to effectively train the data for recognition. The list of words include all the characters, Kannada and Indo-Arabic numerals, punctuations and other symbols. A semi-automated tool for the annotation of data from stroke to word level is used. It segments each word into stroke groups and also acts as a validation mechanism for segmentation. The tool displays the stroke, stroke groups and aksharas of a word and hence can be used to study the various styles of writing, delayed strokes and for assigning quality tags to the words. The tool is currently being used for annotating Tamil and Kannada data. The output is stored in a standard XML format.

Online Handwriting Recognition of Tamil Script Using Fractal Geometry

We present a fractal coding method to recognize online handwritten Tamil characters and propose a novel technique to increase the efficiency in terms of time while coding and decoding. This technique exploits the redundancy in data, thereby achieving better compression and usage of lesser memory. It also reduces the encoding time and causes little distortion during reconstruction. Experiments have been conducted to use these fractal codes to classify the online handwritten Tamil characters from the IWFHR 2006 competition dataset. In one approach, we use fractal coding and decoding process. A recognition accuracy of 90% has been achieved by using DTW for distortion evaluation during classification and encoding processes as compared to 78% using nearest neighbor classifier. In other experiments, we use the fractal code, fractal dimensions and features derived from fractal codes as features in separate classifiers. While the fractal code is successful as a feature, the other two features are not able to capture the wide within-class variations.

Prototype learning methods for online handwriting recognition

In this paper, we study different methods for prototype selection for recognizing handwritten characters of Tamil script. In the first method, cumulative pairwise- distances of the training samples of a given class are used to select prototypes. In the second method, cumulative distance to allographs of different orientation is used as a criterion to decide if the sample is representative of the group. The latter method is presumed to offset the possible orientation effect. This method still uses fixed number of prototypes for each of the classes. Finally, a prototype set growing algorithm is proposed, with a view to better model the differences in complexity of different character classes. The proposed algorithms are tested and compared for both writer independent and writer adaptation scenarios.

Kannada WordNet - a lexical database

This paper presents the preliminary analysis of Kannada WordNet and the set of relevant computational tools. Although the design has been inspired by the famous English WordNet, and to certain extent, by the Hindi WordNet, the unique features of Kannada WordNet are graded antonyms and meronymy relationships, nominal as well as verbal compoundings, complex verb constructions and efficient underlying database design (designed to handle storage and display of Kannada unicode characters). Kannada WordNet would not only add to the sparse collection of machine-readable Kannada dictionaries, but also will give new insights into the Kannada vocabulary. It provides sufficient interface for applications involved in Kannada machine translation, spell checker and semantic analyser.

A new species of Raorchestes (Amphibia: Anura: Rhacophoridae) from mid-elevation evergreen forests of the southern Western Ghats, India

A new species of the shrub frog genus Raorchestes Biju, Souche, Dubois, Dutta and Bossuyt is described as Raorchestes kakachi sp. nov. from Agastyamalai hill region in the southern Western Ghats, India. The small sized Raorchestes (male: 24.7–25.8 mm, n = 3 and female: 24.3–34.1 mm, n = 3) is distinguished from all other known congeners by the following suite of characters. Snout oval in dorsal view; tympanum indistinct; head wider than long; moderate webbing in feet; colour on dorsum varying from ivory to brown, blotches of dark brown on flanks, brown mottling on throat reducing towards vent; inner and outer surface of thigh, inner surface of shank and inner surface of tarsus with a distinct dark brown horizontal band which extends upto first three toes on upper surface. A detailed description, advertisement call features, ecology, natural history notes and comparison with closely related species are provided for the new species.

Phalangopsidae crickets from the Indian Region (Orthoptera, Grylloidea), with the descriptions of new taxa, diagnoses for genera, and a key to Indian genera

The Indian region is presently the second region after the Neotropics in terms of diversity of phalangopsid crickets. Yet their study is impeded by the lack of necessary taxonomic tools for taxon identification. In the present paper, all generic diagnoses are clarified, using morphological and genitalic characters; female genitalia are described and illustrated for all genera with known females. New taxa are described from southern India: Kempiola flavipunctatus Desutter-Grandcolas n. sp., Opiliosina meridionalis Desutter-Grandcolas n. gen., n. sp., Phalangopsina bolivari Desutter-Grandcolas n. sp., P. chopardi Desutter-Grandcolas n. sp., P. gravelyi Desutter-Grandcolas n. sp., and Speluncasina Desutter-Grandcolas n. gen. The list of phalangopsid crickets from the Indian Region is updated, and a key to phalangopsid genera proposed. A lectotype and a paralectotype are designated to fix the name of Phalangopsina dubia (Bolivar, 1900). Opilionacris annandalei Chopard, 1928, previously transferred to the African genus Phaeophilacris Walker, 1871, is transferred to the genus Speluncasina Desutter-Grandcolas n. gen., while Larandopsis jharnae Bhowmik, 1981 and L. newguineae Bhowmik, 1981 described from New Guinea are transferred to the eneopterine genus Lebinthus Stal, 1877. Finally Luzaropsis confusa Chopard, 1969 is removed from its synonymy with L. ferruginea Walker, 1871.

An algorithm to find all palindromic sequences in proteins

A palindrome is a set of characters that reads the same forwards and backwards. Since the discovery of palindromic peptide sequences two decades ago, little effort has been made to understand its structural, functional and evolutionary significance. Therefore, in view of this, an algorithm has been developed to identify all perfect palindromes (excluding the palindromic subset and tandem repeats) in a single protein sequence. The proposed algorithm does not impose any restriction on the number of residues to be given in the input sequence. This avant-garde algorithm will aid in the identification of palindromic peptide sequences of varying lengths in a single protein sequence.

MAST: multi-script annotation toolkit for scenic text

This paper describes a semi-automatic tool for annotation of multi-script text from natural scene images. To our knowledge, this is the maiden tool that deals with multi-script text or arbitrary orientation. The procedure involves manual seed selection followed by a region growing process to segment each word present in the image. The threshold for region growing can be varied by the user so as to ensure pixel-accurate character segmentation. The text present in the image is tagged word-by-word. A virtual keyboard interface has also been designed for entering the ground truth in ten Indic scripts, besides English. The keyboard interface can easily be generated for any script, thereby expanding the scope of the toolkit. Optionally, each segmented word can further be labeled into its constituent characters/symbols. Polygonal masks are used to split or merge the segmented words into valid characters/symbols. The ground truth is represented by a pixel-level segmented image and a '.txt' file that contains information about the number of words in the image, word bounding boxes, script and ground truth Unicode. The toolkit, developed using MATLAB, can be used to generate ground truth and annotation for any generic document image. Thus, it is useful for researchers in the document image processing community for evaluating the performance of document analysis and recognition techniques. The multi-script annotation toolokit (MAST) is available for free download.