arXiv subjects

Subhadip Basu

Publications and source records attributed to Subhadip Basu.

35 records · Page 2Linked to original sources

arXiv2012

Segmentation of Offline Handwritten Bengali Script

Character segmentation has long been one of the most critical areas of optical character recognition process. Through this operation, an image of a sequence of characters, which may be connected in some cases, is decomposed into sub-images of individual alphabetic symbols. In this paper, segmentation of cursive handwritten script of world's fourth popular language, Bengali, is considered. Unlike English script, Bengali handwritten characters and its components often encircle the main character, making the conventional segmentation methodologies inapplicable. Experimental results, using the proposed segmentation technique, on sample cursive handwritten data containing 218 ideal segmentation points show a success rate of 97.7%. Further feature-analysis on these segments may lead to actual recognition of handwritten cursive Bengali script.

cs.CV↗

arXiv2011

Design of an Optical Character Recognition System for Camera-based Handheld Devices

This paper presents a complete Optical Character Recognition (OCR) system for camera captured image/graphics embedded textual documents for handheld devices. At first, text regions are extracted and skew corrected. Then, these regions are binarized and segmented into lines and characters. Characters are passed into the recognition module. Experimenting with a set of 100 business card images, captured by cell phone camera, we have achieved a maximum recognition accuracy of 92.74%. Compared to Tesseract, an open source desktop-based powerful OCR engine, present recognition accuracy is worth contributing. Moreover, the developed technique is computationally efficient and consumes low memory so as to be applicable on handheld devices.

cs.CV↗

arXiv2011

Segmentation of Camera Captured Business Card Images for Mobile Devices

Due to huge deformation in the camera captured images, variety in nature of the business cards and the computational constraints of the mobile devices, design of an efficient Business Card Reader (BCR) is challenging to the researchers. Extraction of text regions and segmenting them into characters is one of such challenges. In this paper, we have presented an efficient character segmentation technique for business card images captured by a cell-phone camera, designed in our present work towards developing an efficient BCR. At first, text regions are extracted from the card images and then the skewed ones are corrected using a computationally efficient skew correction technique. At last, these skew corrected text regions are segmented into lines and characters based on horizontal and vertical histogram. Experiments show that the present technique is efficient and applicable for mobile devices, and the mean segmentation accuracy of 97.48% is achieved with 3 mega-pixel (500-600 dpi) images. It takes only 1.1 seconds for segmentation including all the preprocessing steps on a moderately powerful notebook (DualCore T2370, 1.73 GHz, 1GB RAM, 1MB L2 Cache).

cs.CV↗

arXiv2010

Text/Graphics Separation for Business Card Images for Mobile Devices

Separation of the text regions from background texture and graphics is an important step of any optical character recognition sytem for the images containg both texts and graphics. In this paper, we have presented a novel text/graphics separation technique for business card images captured with a cell-phone camera. At first, the background is eliminated at a coarse level based on intensity variance. This makes the foreground components distinct from each other. Then the non-text components are removed using various characteristic features of text and graphics. Finally, the text regions are skew corrected and binarized for further processing. Experimenting with business card images of various resolutions, we have found an optimum performance of 98.54% with 0.75 MP images, that takes 0.17 seconds processing time and 1.1 MB peak memory on a moderately powerful computer (DualCore 1.73 GHz Processor, 1 GB RAM, 1 MB L2 Cache). The developed technique is computationally efficient and consumes low memory so as to be applicable on mobile devices.

cs.GR↗

arXiv2010

Development of a multi-user handwriting recognition system using Tesseract open source OCR engine

The objective of the paper is to recognize handwritten samples of lower case Roman script using Tesseract open source Optical Character Recognition (OCR) engine under Apache License 2.0. Handwritten data samples containing isolated and free-flow text were collected from different users. Tesseract is trained with user-specific data samples of both the categories of document pages to generate separate user-models representing a unique language-set. Each such language-set recognizes isolated and free-flow handwritten test samples collected from the designated user. On a three user model, the system is trained with 1844, 1535 and 1113 isolated handwritten character samples collected from three different users and the performance is tested on 1133, 1186 and 1204 character samples, collected form the test sets of the three users respectively. The user specific character level accuracies were obtained as 87.92%, 81.53% and 65.71% respectively. The overall character-level accuracy of the system is observed as 78.39%. The system fails to segment 10.96% characters and erroneously classifies 10.65% characters on the overall dataset.

cs.CV↗

arXiv2010

Recognition of Handwritten Roman Script Using Tesseract Open source OCR Engine

In the present work, we have used Tesseract 2.01 open source Optical Character Recognition (OCR) Engine under Apache License 2.0 for recognition of handwriting samples of lower case Roman script. Handwritten isolated and free-flow text samples were collected from multiple users. Tesseract is trained to recognize user-specific handwriting samples of both the categories of document pages. On a single user model, the system is trained with 1844 isolated handwritten characters and the performance is tested on 1133 characters, taken form the test set. The overall character-level accuracy of the system is observed as 83.5%. The system fails to segment 5.56% characters and erroneously classifies 10.94% characters.

cs.CV↗

arXiv2010

Recognition of Handwritten Textual Annotations using Tesseract Open Source OCR Engine for information Just In Time (iJIT)

Objective of the current work is to develop an Optical Character Recognition (OCR) engine for information Just In Time (iJIT) system that can be used for recognition of handwritten textual annotations of lower case Roman script. Tesseract open source OCR engine under Apache License 2.0 is used to develop user-specific handwriting recognition models, viz., the language sets, for the said system, where each user is identified by a unique identification tag associated with the digital pen. To generate the language set for any user, Tesseract is trained with labeled handwritten data samples of isolated and free-flow texts of Roman script, collected exclusively from that user. The designed system is tested on five different language sets with free- flow handwritten annotations as test samples. The system could successfully segment and subsequently recognize 87.92%, 81.53%, 92.88%, 86.75% and 90.80% handwritten characters in the test samples of five different users.

cs.CV↗

arXiv2010

Development of a Multi-User Recognition Engine for Handwritten Bangla Basic Characters and Digits

The objective of the paper is to recognize handwritten samples of basic Bangla characters using Tesseract open source Optical Character Recognition (OCR) engine under Apache License 2.0. Handwritten data samples containing isolated Bangla basic characters and digits were collected from different users. Tesseract is trained with user-specific data samples of document pages to generate separate user-models representing a unique language-set. Each such language-set recognizes isolated basic Bangla handwritten test samples collected from the designated users. On a three user model, the system is trained with 919, 928 and 648 isolated handwritten character and digit samples and the performance is tested on 1527, 14116 and 1279 character and digit samples, collected form the test datasets of the three users respectively. The user specific character/digit recognition accuracies were obtained as 90.66%, 91.66% and 96.87% respectively. The overall basic character-level and digit level accuracy of the system is observed as 92.15% and 97.37%. The system fails to segment 12.33% characters and 15.96% digits and also erroneously classifies 7.85% characters and 2.63% on the overall dataset.

cs.CV↗

arXiv2010

Recognition of handwritten Roman Numerals using Tesseract open source OCR engine

The objective of the paper is to recognize handwritten samples of Roman numerals using Tesseract open source Optical Character Recognition (OCR) engine. Tesseract is trained with data samples of different persons to generate one user-independent language model, representing the handwritten Roman digit-set. The system is trained with 1226 digit samples collected form the different users. The performance is tested on two different datasets, one consisting of samples collected from the known users (those who prepared the training data samples) and the other consisting of handwritten data samples of unknown users. The overall recognition accuracy is obtained as 92.1% and 86.59% on these test datasets respectively.

cs.CV↗

arXiv2010

Text Region Extraction from Business Card Images for Mobile Devices

Designing a Business Card Reader (BCR) for mobile devices is a challenge to the researchers because of huge deformation in acquired images, multiplicity in nature of the business cards and most importantly the computational constraints of the mobile devices. This paper presents a text extraction method designed in our work towards developing a BCR for mobile devices. At first, the background of a camera captured image is eliminated at a coarse level. Then, various rule based techniques are applied on the Connected Components (CC) to filter out the noises and picture regions. The CCs identified as text are then binarized using an adaptive but light-weight binarization technique. Experiments show that the text extraction accuracy is around 98% for a wide range of resolutions with varying computation time and memory requirements. The optimum performance is achieved for the images of resolution 1024x768 pixels with text extraction accuracy of 98.54% and, space and time requirements as 1.1 MB and 0.16 seconds respectively.

cs.CV↗

arXiv2010

A comparative study of different feature sets for recognition of handwritten Arabic numerals using a Multi Layer Perceptron

The work presents a comparative assessment of seven different feature sets for recognition of handwritten Arabic numerals using a Multi Layer Perceptron (MLP) based classifier. The seven feature sets employed here consist of shadow features, octant centroids, longest runs, angular distances, effective spans, dynamic centers of gravity, and some of their combinations. On experimentation with a database of 3000 samples, the maximum recognition rate of 95.80% is observed with both of two separate combinations of features. One of these combinations consists of shadow and centriod features, i. e. 88 features in all, and the other shadow, centroid and longest run features, i. e. 124 features in all. Out of these two, the former combination having a smaller number of features is finally considered effective for applications related to Optical Character Recognition (OCR) of handwritten Arabic numerals. The work can also be extended to include OCR of handwritten characters of Arabic alphabet.

cs.CV↗

arXiv2010

Binarizing Business Card Images for Mobile Devices

Business card images are of multiple natures as these often contain graphics, pictures and texts of various fonts and sizes both in background and foreground. So, the conventional binarization techniques designed for document images can not be directly applied on mobile devices. In this paper, we have presented a fast binarization technique for camera captured business card images. A card image is split into small blocks. Some of these blocks are classified as part of the background based on intensity variance. Then the non-text regions are eliminated and the text ones are skew corrected and binarized using a simple yet adaptive technique. Experiment shows that the technique is fast, efficient and applicable for the mobile devices.

cs.CV↗

arXiv2010

Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier

A novel approach for recognition of handwritten compound Bangla characters, along with the Basic characters of Bangla alphabet, is presented here. Compared to English like Roman script, one of the major stumbling blocks in Optical Character Recognition (OCR) of handwritten Bangla script is the large number of complex shaped character classes of Bangla alphabet. In addition to 50 basic character classes, there are nearly 160 complex shaped compound character classes in Bangla alphabet. Dealing with such a large varieties of handwritten characters with a suitably designed feature set is a challenging problem. Uncertainty and imprecision are inherent in handwritten script. Moreover, such a large varieties of complex shaped characters, some of which have close resemblance, makes the problem of OCR of handwritten Bangla characters more difficult. Considering the complexity of the problem, the present approach makes an attempt to identify compound character classes from most frequently to less frequently occurred ones, i.e., in order of importance. This is to develop a frame work for incrementally increasing the number of learned classes of compound characters from more frequently occurred ones to less frequently occurred ones along with Basic characters. On experimentation, the technique is observed produce an average recognition rate of 79.25 after three fold cross validation of data with future scope of improvement and extension.

cs.CV↗

arXiv2010

A Hough Transform based Technique for Text Segmentation

Text segmentation is an inherent part of an OCR system irrespective of the domain of application of it. The OCR system contains a segmentation module where the text lines, words and ultimately the characters must be segmented properly for its successful recognition. The present work implements a Hough transform based technique for line and word segmentation from digitized images. The proposed technique is applied not only on the document image dataset but also on dataset for business card reader system and license plate recognition system. For standardization of the performance of the system the technique is also applied on public domain dataset published in the website by CMATER, Jadavpur University. The document images consist of multi-script printed and hand written text lines with variety in script and line spacing in single document image. The technique performs quite satisfactorily when applied on mobile camera captured business card images with low resolution. The usefulness of the technique is verified by applying it in a commercial project for localization of license plate of vehicles from surveillance camera images by the process of segmentation itself. The accuracy of the technique for word segmentation, as verified experimentally, is 85.7% for document images, 94.6% for business card images and 88% for surveillance camera images.

cs.IR↗

arXiv2010

Design of a Smart Unmanned Ground Vehicle for Hazardous Environments

A smart Unmanned Ground Vehicle (UGV) is designed and developed for some application specific missions to operate predominantly in hazardous environments. In our work, we have developed a small and lightweight vehicle to operate in general cross-country terrains in or without daylight. The UGV can send visual feedbacks to the operator at a remote location. Onboard infrared sensors can detect the obstacles around the UGV and sends signals to the operator.

cs.RO↗

arXiv2010

Text/Graphics Separation and Skew Correction of Text Regions of Business Card Images for Mobile Devices

Separation of the text regions from background texture and graphics is an important step of any optical character recognition system for the images containing both texts and graphics. In this paper, we have presented a novel text/graphics separation technique and a method for skew correction of text regions extracted from business card images captured with a cell-phone camera. At first, the background is eliminated at a coarse level based on intensity variance. This makes the foreground components distinct from each other. Then the non-text components are removed using various characteristic features of text and graphics. Finally, the text regions are skew corrected for further processing. Experimenting with business card images of various resolutions, we have found an optimum performance of 98.25% (recall) with 0.75 MP images, that takes 0.17 seconds processing time and 1.1 MB peak memory on a moderately powerful computer (DualCore 1.73 GHz Processor, 1 GB RAM, 1 MB L2 Cache). The developed technique is computationally efficient and consumes low memory so as to be applicable on mobile devices.

cs.GR↗

arXiv2010

Word level Script Identification from Bangla and Devanagri Handwritten Texts mixed with Roman Script

India is a multi-lingual country where Roman script is often used alongside different Indic scripts in a text document. To develop a script specific handwritten Optical Character Recognition (OCR) system, it is therefore necessary to identify the scripts of handwritten text correctly. In this paper, we present a system, which automatically separates the scripts of handwritten words from a document, written in Bangla or Devanagri mixed with Roman scripts. In this script separation technique, we first, extract the text lines and words from document pages using a script independent Neighboring Component Analysis technique. Then we have designed a Multi Layer Perceptron (MLP) based classifier for script separation, trained with 8 different wordlevel holistic features. Two equal sized datasets, one with Bangla and Roman scripts and the other with Devanagri and Roman scripts, are prepared for the system evaluation. On respective independent text samples, word-level script identification accuracies of 99.29% and 98.43% are achieved.

cs.LG↗