P. Pavan Kumar

Pseudo one pass thinning algorithm

A One Pass Thinning Algorithm (OPTA) and a Pseudo One Pass Thinning Algorithm (POPTA) are proposed in this paper. The one pass thinning algorithm uses the concept of thinning and restoring. The OPTA deletes pixels from North, South, East, and West in one pass. The POPTA uses an additional concept of corner pixels, which detects the corner pixels and deletes them to yield better skeletons with little or no distortion. Experimental results show that each of the patterns is thinned to a skeleton of unit pixel width, with no loss of connectivity or distortion. The algorithms are width independent and work for both even pixel wide and odd pixel wide images.

Towards Improving the Accuracy of Telugu OCR Systems

Design of a high accuracy OCR system is a challenging task as the system performance is affected by its component modules. Each module has its own impact on the overall accuracy of the OCR system. An improvement in a module reflects upon overall system performance. In the present work, we have developed an OCR system for Telugu. Our experiments on a corpus of about 1000 images has shown that the system performance is degraded due to broken characters caused by the binarization module as well as due to improper character segmentation. Therefore, we address the issues of handling broken characters and poor segmentation. A novel approach which is based on feedback from the distance measure used by the classifier is proposed to handle broken characters. For character segmentation, our proposed approach exploits the orthographic properties of Telugu script. As a result, significant improvement is obtained in the performance of the system. These algorithms are generic and may be applicable to other Indian scripts, especially to south Indian scripts. In our experiments, an end-to-end system performance is evaluated which is not reported in the literature.

Theoretical studies on the stabilities of 1,2- and 1,3-isomers of cyclic H4A2X2 (AC, Si; XO,S,CH2): the anomeric effect at silicon

Abstract 1,2- and 1,3-isomers of dioxetanes, dithietanes, and their silicon analogues ( 1, 2 ) have been studied by Molecular Orbital methods (using both HF/3–21G and MNDO). The 1,3-isomers ( 2 ) are found to be more stable than their 1,2-counterparts ( 1 ) except for dithietane where the energy difference is negligible. The relative energies of the 1,2- and 1,3-isomers are also estimated using bond energy differences (eqn. 1) at the 3–21G level on models. These are corrected for the anomeric effect (eqn. 2) present in the 1,3-isomer and compared to the 3–21G estimate of the relative energies of 1 and 2 . The discrepancy between the two estimates is equated to the strain energy difference between the two four-membered rings. This is found to be maximum for dioxetane and disilacyclobutane. The anomeric effect at silicon (10.0 kcal mol −1 at the 3–21G level for oxygen substitution) is smaller than that at carbon (17.4 kcal mol −1 at the same level) for the same substituent.

A Structure Based Approach for Mathematical Expression Retrieval

Mathematical expression (ME) retrieval problem has currently received much attention due to wide-spread availability of MEs on the World Wide Web. As MEs are two-dimensional in nature, traditional text retrieval techniques used in natural language processing are not sufficient for their retrieval. In this paper, we have proposed a novel structure based approach to ME retrieval problem. In our approach, query given in \(\mbox{\LaTeX}\) format is preprocessed to eliminate extraneous keywords (like \displaystyle, \begin{array} etc.) while retaining the structure information like superscript and subscript relationships. MEs in the database are also preprocessed and stored in the same manner. We have created a database of 829 MEs in \(\mbox{\LaTeX}\) form, that covers various branches of mathematics like Algebra, Trigonometry, Calculus etc. Preprocessed query is matched against the database of preprocessed MEs using Longest Common Subsequence (LCS) algorithm. LCS algorithm is used as it preserves the order of keywords in the preprocessed MEs unlike bag of words approach in the traditional text retrieval techniques. We have incorporated structure information into LCS algorithm and proposed a measure based on the modified algorithm, for ranking MEs in the database. As proposed approach exploits structure information, it is closer to human intuition. Retrieval performance has been evaluated using standard precision measure.

A rule-based approach to form mathematical symbols in printed mathematical expressions

Automated understanding of mathematical expressions (MEs) is currently a challenging task due to their complex two- dimensional (2D) structure. Recognition of MEs can be online or offline and in either case, the process involves symbol recognition and analysis of 2D structure. This process is more complex for offline or printed MEs as they do not have temporal information. In our present work, we focus on the recognition of printed MEs and assume connected components (ccs) of a given ME image are labelled. Our approach to ME recognition comprises three stages,namely symbol formation, structural analysis and generation of encoding form like LATEX. In this paper, we present symbol formation process, where multi-cc symbols (like =, ≡ etc.) are formed, identity of context-dependent symbols (like a horizontal line can be MINUS, OVERBAR, FRACTION etc.) are resolved using spatial relations. Multi-line MEs like matrices and enumerated functions are also handled in this stage. A rule-based approach is proposed for the purpose, where the heuristics based on spatial relations are represented in the form of rules (knowledge) and those rules are fired depending on input data (labelled ccs). As knowledge is isolated from data like an expert system in our approach, it allows for easy adaptability and extensibility of the process. Proposed approach also handles both single-line and multi-line MEs in an unified manner. Our approach has been tested on around 800 MEs collected from various mathematical documents and experimental results are reported on them.

A Novel Stroke Width Based Binarization Method to Handle Closely Spaced Thick Characters

Signboards and billboards provide a challenge to image segmentation methods, since these images may also have pictures and graphical objects, apart from text objects. Methods that often succeed in more traditional text block segmentation situations do not perform well here since estimation of text lines and character widths etc fail due to the short sample sizes. Further, extraction of characters of different font sizes, which can be found in the real world and signboard images, remains a problem. In this paper, as a solution to the mentioned problem, we propose two stroke width based binarization approaches. These approaches can be used to eliminate extraneous objects based upon estimates of stroke width. We compare our methods with several other stroke width based binarization methods. We observe that the previous approaches fail, when there are closely spaced thick characters. We show that our second approach is able to extract closely spaced thick characters better than any of the other methods.

Possibility of bond stretch isomerism in [Cp(CO)2M]2(μ-E) complexes (M=Mn, Re, Cr and W; E=S, Se and Te); a molecular orbital study

Abstract Extended Huckel calculations have been carried out on [Cp(CO)2M]2(μ-E) complexes (M  Mn, Re, Cr and W; E  S, Se and Te) in linear, bent and triangular geometries. The possibility of double well potential and consequent “bond stretch isomerism” in these complexes is analyzed. All the complexes with a 38 valence electron count (VEC) are calculated to have a minimum corresponding to the triangular geometry. The Mn and Cr complexes with a tellurido bridge have an additional minimum for the bent geometry; only the bent structure is known experimentally. The triangular isomers of these two complexes are marginally higher in energy, but separated by substantial barriers. The other M2E combinations studied adopt a triangular geometry. The difference in the behaviour between these complexes is explained by the fragment molecular orbital approach and by considering the atomic radii of the M and E species. Single point ab initio calculations using the LANL1MB basis set on [cp(CO)2M]2(μ-E) (M  Mn and Re; E  S, Se and Te) confirm the relative energy orderings produced by the extended Huckel calculations. The relation between the ME bond orders and bond lengths and the extent of Main Group d-orbital participation is also analyzed. It is predicted that complexes with a VEC of 36 and 40 should adopt linear and bent geometries, respectively.

A Knowledge-Based Design for Structural Analysis of Printed Mathematical Expressions

Recognition of Mathematical Expressions (MEs) is a challenging Artificial Intelligence problem as MEs have a complex two dimensional structure. ME recognition involves two stages: Symbol recognition and Structural Analysis. Symbols are recognized in the first stage and spatial relationships like superscript, subscript etc., are determined in the second stage. In this paper, we have focused on structural analysis of printed MEs. For structural analysis, we have proposed a novel ternary tree based representation that captures spatial relationships among the symbols in a given ME. Proposed tree structure has been used for validation of generated ME structure. Structure validation process detects errors based on domain knowledge (mathematics) and the error feedback is used to correct the structure. Therefore, our validation process incorporates an intelligent mechanism to automatically detect and correct the errors. Proposed approach has been tested on an image database of 829 MEs collected from various mathematical documents and experimental results are reported on them.

On performance analysis of end-to-end OCR systems of Indic scripts

Performance evaluation of End-to-End OCR systems of Indic scripts requires matching of UNICODE sequences of OCR output and ground truth. In the literature, Levenshtein edit distance has been used to compute error rates of OCR systems but the accuracies are not explicitly reported. In the present work, we have proposed an accuracy measure based on edit distance and used it in conjunction with error rate to report the performance of an OCR system. We have analyzed the relationship between accuracy and error rates in a quantitative manner. Our analysis has shown that accuracy and error rate are independent of each other and so both are needed to report complete performance of an OCR system. Proposed approach is applicable to all the Indic scripts and the experimental results on different scripts like Devanagari, Telugu, Kannada etc. are shown.

Molecular orbital study of the structure and stability of transition metal polyhedral borane complexes. Position of bridging hydrogens

Abstract The dependence of bridging hydrogen atoms on terminal hydrogen positions in nido -metalloboranes has been studied using the model compounds B 4 H 8 X ( 6 , X = BH) and B 4 H 8 Fe(CO) 3 ( 1d ). Calculations on B 5 H 9 at both MNDO and extended Huckel levels have shown that the bridging hydrogen positions are controlled by the terminal hydrogen positions. Bridging hydrogen atoms might be observed above the B n plane (towards the cap), if the caps have sufficiently diffuse orbitals. Model studies at both MNDO and extended Huckel levels of B 4 H 8 X [X = BeH − , Li − and Fe(CO) 3 ] supported these results. The effects of increasing ring size from B 4 H 8 to B 5 H 10 are also studied. Suitable metal fragments for polyhedral borane ligands (rings) having five, six, seven, 11 and 13 vertex boron atoms can be selected using the ring—cap overlap match. Calculations have shown that B 6 H 6 4− ( 13 ) has more diffuse orbitals compared to B 11 H 11 4− ( 14 ) and B 13 H 13 4− ( 15 ). Compounds 14 and 15 preferred caps with less diffuse orbitals because of the rigidity of the ligands. The metal—ring boron distances in metalloboranes are controlled by this ring—cap compatibility. The concept of topological charge stabilization is also used in predicting the stabilities of various isomers of metalloboranes.