Papers by Manisha Deshmukh
SSRN Electronic Journal
The significant information related to current era is preserved in the thousands of the archaic h... more The significant information related to current era is preserved in the thousands of the archaic handwritten Modi documents at official and public sectors. The automatic recognition of these documents is essential because of three major crises as lack of Modi script experts, crucial content and destroying stage of these Modi documents. Intelligent historical handwritten Modi document recognition is a crucial research task. The major obstacles are the writing style of Modi script, huge number of character symbols and degraded handwritten historical Modi documents. Here, supervised classification approach is presented for the handwritten Modi characters classification. Experimental results are analyzed by using the multiple extended feature extraction and classification techniques. The collaborative classification and feature extraction approach with maximum voting is used for the classification of the Modi character. The results are verified with handwritten Modi character data set with fifty-five classes of size 95000 characters. Minimum distance classifier and GSC features based intelligent handwritten Modi character recognition system gives better recognition rate. The average classification rate achieved is 83.09%.
Review Editor
(United States)
A New Approach for Unified Characters Cluster Segmentation of Ancient Handwritten Modi Documents
Computer Vision and Robotics, 2022
Music is used to change mood in everyday life and to maintain physical and psychological health o... more Music is used to change mood in everyday life and to maintain physical and psychological health of human being. Number of research papers on Raga Chikitsa (Music Therapy) evaluated the evidence that music improves health and well-being of human being through the motivation and pleasure; stress and arousal; immunity and social affiliation. This paper presented an online Expert System based on Indian Classical Music therapy for health care. In this Expert System knowledge base has been contain information about the Indian classical Ragas and the symptoms of the disease which will be used to solve the query of the user. Then Expert System diagnosis the patient's disabilities and advice to listen tunes of appropriate Raga based songs, instrumental tunes with duration and specific time. The Forward chaining inference approach is used for the implementation of Expert System.
SSRN Electronic Journal, 2019
Segmentation of archaic handwritten degraded Modi script text lines in the isolated characters is... more Segmentation of archaic handwritten degraded Modi script text lines in the isolated characters is the key steps of the offline automated Modi script document recognition system. The improved segmentation of characters gravitated towards the higher accuracy of the recognition. The intricacy of archaic handwritten degraded Modi script documents put forwards the number of challenges in character segmentation. This paper presents a multistep technique for Modi script character segmentation based on the analysis of background pixel density of global and local horizontal zones of the text line. At the initial isolation stage two types of fragments are segmented as isolated individual characters and cluster of overlapping/ touching characters. Further, the cluster of overlapping or touching characters are segmented in isolated individual characters. The isolated, overlapping, and touching characters are segmented efficiently using the proposed Modi character segmentation technique.
Off-line Handwritten Modi Numerals Recognition using Chain Code
Proceedings of the Third International Symposium on Women in Computing and Informatics - WCI '15, 2015
In this paper a system for recognition of off-line handwritten Modi Numerals is presented. To ext... more In this paper a system for recognition of off-line handwritten Modi Numerals is presented. To extract the features of handwritten Modi numeral chain code feature extraction technique is used with non-overlapping blocking strategy. A correlation coefficient is used for Modi numeral recognition. Experimental results are evaluated using two strategies: different numeral image non-overlapping division and different sizes of data set. On experimentation the maximum recognition rate of 85.21% is achieved on a database of 30000 images. The recognition results shows better performance for 5X5 grids divisions.
3 A divide-and-conquer based algorithm is presented here to detect the skew angle in handwritten ... more 3 A divide-and-conquer based algorithm is presented here to detect the skew angle in handwritten old age Modi document images. The skew angle detection range is estimated by determining the inclination of the document image. A new horizontal projection profile based criterion function is proposed and used here to compute the concentration of the black pixels. The criterion function is scrutinized to estimate the rotational angle range and detect the skew angle of the document image. The results prove that the proposed technique has corrected skew angle in diverse types of document images. This method accurately identifies skew angle in the clockwise or anticlockwise direction in estimated rotational angle range up to ±89 degree with angular resolution 0.1 degree. The Modi Lipi document image dataset and benchmark online datasets are used to test and compare the performance of the proposed approach.
A dynamic statistical nonparametric cleaning and enhancement system for highly degraded ancient handwritten modi lipi documents
2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017
A nonparametric technique for the cleaning and enhancement of the chronic old age Modi document i... more A nonparametric technique for the cleaning and enhancement of the chronic old age Modi document images is presented here. The technique is based on the dynamic thresholding and connected component analysis. The automatic fixation of the Niblack factor k is proposed as per the document degradation type. The dynamic thresholding algorithm is used to segment the noisy pixels from the text area and background of the document image. To eliminate some sort of noise like clutter, marginal and blobs, connected components are calculated and analyzed. To improve the quality of the document image filtering techniques, and morphological operations are employed. The performance of the approach is tested and verified on the variety of old age degraded noisy Modi script documents. To evaluate the performance of the proposed approach, it is compared with benchmarking techniques illustrated in literature.
Unsupervised Page Area Detection Approach for the Unconstrained Chronic Handwritten Modi Document Images
The sparse old age historical Modi documents are archived in government and non-government sector... more The sparse old age historical Modi documents are archived in government and non-government sectors from long time. These documents are pasted on card-sheet like material for preservation. In the processes of intelligent archaic Modi document recognition system there is a need to detect the actual page area before to other preprocessing stages. Over the past period there has been a growing interest in addressing of object detection of document images or removal of clutter noise. However, no comprehensive studies have been exists which are work on the proposed problem statement. This paper presents page boundary extraction and page area detection approach for highly degraded chronic handwritten Modi document images. This algorithm is based on the analysis of the gray level frequency of the document image with statistical scrutiny. The ground-truth region-based evaluation methods are used to evaluate and compare the results. Actual page area of the ancient handwritten Modi document ima...
A Modified Approach for the Segmentation of Unconstrained Cursive Modi Touching Characters Cluster
A hybrid text line segmentation approach for the ancient handwritten unconstrained freestyle Modi script documents
The Imaging Science Journal
Uploads
Papers by Manisha Deshmukh