Wyniki wyszukiwania - BazTech

1

Map image binarization and stitching using extraction of regions

Mandal S., Biswas S., Das A. K, Chanda B.

Journal of Theoretical and Applied Computer Science

|

2015

|

Vol. 9, nr 1

28--40

EN

Binarisation methods already reported are inadequate for binarisation of complex documents such as maps due to large intensity variations across the regions and entangled texts with lines representing borders, rivers, roads and similar other components. This paper proposes a new binarisation technique for coloured land map images by extracting the regions and analysing the hue, saturation spread and within class kurtosis. This is a region-wise adaptive algorithm to cope up with the sharp changes of the discriminating features across different regions. Here, local regions are selected as clusters having the same hue and saturation. The regions are individually binarised using the spread of their degree of within class kurtosis and finally combined together. The regions extracted are further utilised for stitching of map documents which contain some portion in common. We use a simple greedy technique using correlation matching to join two or more map images such that information from both can be viewed and compared. Our experiments include 446 colour maps from the map image database created for this purpose and made freely available at website. This work is an extended version of our previous work on map image binarisation [1].

2

Text Segmentation from Bangla Land Map Images

Biswas S., Das A. K, Chanda B.

Image Processing & Communications

|

2014

|

Vol. 19, no. 1

21--34

EN

Text segmentation from land map images is a non-trivial task as map components are interleaved and overlapped in a complex spatial form. The characters in a word in most of the Indic languages, including Bangla (the 6th most spoken language in the world), are connected through a headline (”matra” or ”shirorekha”) which makes the corresponding word a single component. It has been observed that the Delaunay triangulation (DT) forms a number of small triangles on the text regions compared to other regions of the map - a property very much discernible for Bangla (and some other Indic scripts) texts. This property is primarily exploited here to segment text from the complex background of the land map images. The proposed text segmentation approach is tested and compared with an existing method on a collected dataset of paper map images( containing Bangla, an Indian regional language texts) and the results are encouraging.

3

Land Map Image Dataset: Ground-Truth And Classification Using Visual And Textural Features

Mandal S., Biswas S., Kumar-Das A., Chanda B.

Image Processing & Communications

|

2014

|

Vol. 19, no. 4

37--55

EN

Research on document image analysis is actively pursued in the last few decades and services like OCR, vectorization of drawings/graphics and various types of form processing are very common. Handwritten documents, old historical documents and documents captured through camera are now being the subjects of active research. However, another very important type of paper document, namely the map document image processing research suffers due to the inherent complexities of the map document and also for nonavailability of benchmark public data-sets. This paper presents a new data-set, namely, the Land Map Image Database (LMIDb) that consists of a variety of land maps images (446 images at present and growing; scanned at 200/300 dpi in TIF format) and the corresponding ground-truth. Using semiautomatic tools non-text part of the images are deleted and the text-only ground-truth is also kept in the database. This paper also presents a classification strategy for map images using which the maps in the database are automatically classified into Political (Po), Physical (Ph), Resource (R) and Topographic (T) maps. The automatic classification of maps help indexing of the images in LMIDb for archival and easy retrieval of the right maps to get the appropriate geographical information. Classification accuracy is also tested on the proposed data-set and the result is encouraging.

4

RAM Simulation of BGS Model of Abstract-state Machines

Seshadhri S., Seth A., Biswas S.

Fundamenta Informaticae

|

2007

|

Vol. 77, nr 1,2

175-185

EN

We show in this paper that the BGS model of abstract state machines can be simulated by random access machines with at most a polynomial time overhead. This result is already stated in [5] with a very brief proof sketch. The present paper gives a detailed proof of the result. We represent hereditarily finite sets, which are the typical BGS ASM objects, by membership graphs of the transitive closure of the sets. Testing for equality between BGS objects can be done in linear time in our representation.

5

Transient trajectory of journal in hydrodynamic bearing

Hirani H., Athre K., Biswas S.

Applied Mechanics and Engineering

|

2000

|

Vol. 5, no 2

405-418

EN

A simple methodology to trace journal orbit under dynamic load conditions is presented. The non-linear fluid film bearing forces are derived using a closed-form two-dimensional pressure solution obtained from Reynolds equation for dynamic case. An implicit two-dimensional Newton-Raphson method is employed to determine journal center velocity by solving the equations of motion incorporating journal inertia and unbalance forces. A global technique is used to ensure convergence towards the root in each iteration. Finally, two connecting rod big end bearings are studied to demonstrate the effect of inertia forces at high speed.

6

Journal bearing design using TKSolver

Hirani H., Athre K., Biswas S.

Applied Mechanics and Engineering

|

1999

|

Vol. 4, no spec.

39-44

EN

An easili adaptable design for journal bearing is furnished as an improvement over bearing design evaluated by trial and error method using many design charts. Guidelines are arranged to decide bearing length, clearance and bearing materials. Simplified closed form algebraic expressions are used to reduce computational time and cost for the prediction of maximum pressure, fluid film temperature rise, quantity of lubricant, friction loss, load zapacity and whirl onset velocity. Automatic iterative solving feature of TKSolver software is applied to extract eccentricity for a given load. The results of load, maximum pressure, friction loss, maximum temperature and attitude angle are given in tabular form over a range of eccentricity ratio to optimize bearing design.

7

Derivation of nonlinear coefficients in multi lobe journal bearings

Rao T. V. V. L. N., Biswas S., Athre K.

Applied Mechanics and Engineering

|

1999

|

Vol. 4, no spec.

57-66

EN

The equivalent stiffness and damping coefficients calculated successively along the journal center locus with reference to the equilibrium position are obtained (in the case of stable journal orbit) using Taylor series expansion. To validate the accuracy of the derived coefficients, the journal orbit is compared with the transient simulation under similar operating conditions. The equivalent dynamic coefficients are further evaluated according to the modified journal position using linear interpolation procedure. The average value of the equivalent stiffness and damping coefficients are calculated at various perturbation amplitudes from equilibrium position along the transient orbit. The influence of journal center position and velocities is observed. With nonlinear coefficients close to actual simulation under stable conditions this methodology provides the bearing designer variation of dynamic coefficients in the bearings.