{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T03:17:55Z","timestamp":1785813475745,"version":"3.56.0"},"reference-count":42,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T00:00:00Z","timestamp":1646956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2022,6,9]]},"abstract":"<jats:p>\n                    The accuracy on MINST dataset for roman numerals is already 99.65%. However, same models showed low accuracy on Sindhi numerals. It is because Sindhi numerals have high correlation between the shapes of the numerals. In this paper, correlation based template matching is used to analyze the shape ambiguity by identifying the dominant false positives (FP) and false negatives (FN) for every numeral. Furthermore, the Gradients Histogram Orientation (GOH) features are used to improve the accuracy of existing classifiers by image-to-image matching. The classical OCR using simple binary features are not sufficient to address the problems of shape ambiguity in Sindhi numerals, i.e., the shape of digits 2,\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" orientation=\"portrait\" position=\"float\" xlink:href=\"10.3233_JIFS-219304-img1.jpg\"\/>\n                    , and 3,\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" orientation=\"portrait\" position=\"float\" xlink:href=\"10.3233_JIFS-219304-img2.jpg\"\/>\n                    , are very similar. The raw pixel values are used as features for the classification in the first stage. In second stage, the input image is matched with the dominant FP and FN of the predicted class, and the final decision is made by the image-to-image matching based on GOH features. Decision based on image to image matching with dominant FP and FN increase the accuracy of the classifier. Support vector machine (SVM), K-nearest neighbor, and template based matching classifiers are used. The proposed extension substantially improves the accuracy of all mentioned classifiers.\n                  <\/jats:p>","DOI":"10.3233\/jifs-219304","type":"journal-article","created":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T11:50:46Z","timestamp":1646999446000},"page":"2045-2056","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["Extended framework for Sindhi numerals OCR using gradient orientation histograms"],"prefix":"10.1177","volume":"43","author":[{"given":"Anwar Ali","family":"Sanjrani","sequence":"first","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junaid","family":"Baber","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maheen","family":"Bakhtyar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ihsan","family":"Ullah","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Shumail","family":"Naveed","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waheed","family":"Noor","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul","family":"Basit","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azam","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and IT, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveed","family":"Sheikh","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Balochistan, Quetta, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2022,3,11]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Riaz Ahmad Syed\u00a0Hassan Amin Mohammad\u00a0 and KhanA.U. Scale and rotation invariant recognition of cursive pashto script using sift features In Emerging Technologies (ICET) 2010 6th International Conference on pages 299\u2013303. IEEE 2010.","DOI":"10.1109\/ICET.2010.5638470"},{"issue":"5","key":"e_1_3_1_3_2","first-page":"195","article-title":"Sindhi handwritten-digits recognition usingmachine learning techniques","volume":"19","author":"Irfan Ali","year":"2019","unstructured":"Irfan Ali, Insaf Ali, Asif\u00a0Khan Subhash, Syed\u00a0Ahmed Raza, BasitHassan and Priha Bhatti, Sindhi handwritten-digits recognition usingmachine learning techniques, International Journal of ComputerScience and Network Applications 19(5) (2019), 195.","journal-title":"International Journal of ComputerScience and Network Applications"},{"issue":"2","key":"e_1_3_1_4_2","first-page":"42","article-title":"Urduhandwritten character recognition using deep learning","volume":"10","author":"Anwar Ali Sanjrani Maheen\u00a0Bakhtyar Ali\u00a0Jan","year":"2020","unstructured":"Anwar Ali Sanjrani Maheen\u00a0Bakhtyar Ali\u00a0Jan and Junaid\u00a0Baber, Urduhandwritten character recognition using deep learning, Journalof Communication Technologies and Robotics Applications 10(2) (2020), 42\u201351.","journal-title":"Journalof Communication Technologies and Robotics Applications"},{"issue":"2","key":"e_1_3_1_5_2","first-page":"205","article-title":"Segmentation ofsindhi handwritten text","volume":"50","author":"\u00a0Awan S.A.","year":"2018","unstructured":"\u00a0AwanS.A., \u00a0HakroD.N., \u00a0AbroZ.H. and \u00a0Jalbani,A.H., Segmentation ofsindhi handwritten text, Sindh University Research Journal-SURJ(Science Series) 50(2) (2018), 205\u2013208.","journal-title":"Sindh University Research Journal-SURJ(Science Series)"},{"issue":"1","key":"e_1_3_1_6_2","first-page":"6","article-title":"Handwritten sindhi character recognition usingneural networks","volume":"37","author":"Shafique\u00a0Ahmed Awan","year":"2018","unstructured":"Shafique\u00a0Ahmed Awan, Zahid\u00a0Hussain Abro, Akhtar\u00a0Hussain Jalbani, Maryam Hameed, et al., Handwritten sindhi character recognition usingneural networks, Mehran University Research Journal ofEngineering and Technology 37(1) (2018), 6.","journal-title":"Mehran University Research Journal ofEngineering and Technology"},{"key":"e_1_3_1_7_2","first-page":"57","article-title":"Handwrittencharacter recognition using multiclass svm classification withhybrid feature extraction","volume":"10","author":"Muhammad\u00a0Naeem Ayyaz","year":"2012","unstructured":"Muhammad\u00a0Naeem Ayyaz, Imran Javed and Waqar Mahmood, Handwrittencharacter recognition using multiclass svm classification withhybrid feature extraction, Pakistan Journal of Engineering &Applied Science 10 (2012), 57\u201367.","journal-title":"Pakistan Journal of Engineering &Applied Science"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.08.006"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2016.1212106"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009715923555"},{"issue":"1","key":"e_1_3_1_11_2","first-page":"2019","article-title":"Multi-font and multi-size printed sindhicharacter recognition using convolutional neural networks","volume":"24","author":"Asghar\u00a0Ali Chandio","unstructured":"Asghar\u00a0Ali Chandio, Mehwish Leghari, Mehjabeen Leghari and Akhtar\u00a0Hussain Jalbani, Multi-font and multi-size printed sindhicharacter recognition using convolutional neural networks, Pakistan Journal of Engineering and Applied Sciences 24(1), 2019.","journal-title":"Pakistan Journal of Engineering and Applied Sciences"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Hojin Cho Myungchul Sung and Bongjin Jun Canny text detector: Fast and robust scene text localization algorithm In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pages 3566\u20133573 2016.","DOI":"10.1109\/CVPR.2016.388"},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Premanand Ghadekar Shubham Ingole and Dhruv Sonone Handwritten digit and letter recognition using hybrid dwtdct with knn and svm classifier In In Proceedings of the 4th International Conference on Computing Communication Control and Automation pages 1\u20136 08 2018.","DOI":"10.1109\/ICCUBEA.2018.8697684"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.030"},{"issue":"2","key":"e_1_3_1_15_2","first-page":"2014","article-title":"Issues and challenges in sindhi ocr","volume":"46","author":"Dil\u00a0Nawaz Hakro","unstructured":"Dil\u00a0Nawaz Hakro, Imdad\u00a0A Ismaili, Abdullah\u00a0Zawawi Talib, ZeeshaniBhatti and Ghulam\u00a0Nabi Mojai, Issues and challenges in sindhi ocr, Sindh University Research Journal-SURJ (Science Series) 46(2), 2014.","journal-title":"Sindh University Research Journal-SURJ (Science Series)"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Ravindra\u00a0 HegadiS Template matching approach for printed kannada numeral recognition In Computational Intelligence and Information Technology pages 648\u2013651. Springer 2011.","DOI":"10.1007\/978-3-642-25734-6_111"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.02.018"},{"key":"e_1_3_1_18_2","unstructured":"Noman Islam Zeeshan Islam and Nazia Noor A survey on optical character recognition system arXiv preprint arXiv:1710.05703 2017."},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"\u00a0JangidM. and \u00a0SrivastavaS. Gradient local auto-correlation for handwritten devanagari character recognition In 2014 International Conference on High Performance Computing and Applications (ICHPCA) pages 1\u20135 2014.","DOI":"10.1109\/ICHPCA.2014.7045339"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Chul Kim Jang\u00a0Su Kim and U\u00a0Ju Kim A study on features for improving performance of chinese ocr by machine learning In Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference pages 51\u201355. ACM 2019.","DOI":"10.1145\/3341069.3342991"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.01.027"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-190339"},{"issue":"2","key":"e_1_3_1_23_2","first-page":"1","article-title":"Using ocr to read handwritten texts in search fornfrs in agile software engineering","volume":"3","author":"Richard\u00a0Rabin Maiti","year":"2019","unstructured":"Richard\u00a0Rabin Maiti, Aleksandr Krasnov, Deanna\u00a0Marie Wilborne and Frank Mitropoulos, Using ocr to read handwritten texts in search fornfrs in agile software engineering, Journal of SoftwareEngineering Practice 3(2) (2019), 1\u201310.","journal-title":"Journal of SoftwareEngineering Practice"},{"issue":"4","key":"e_1_3_1_24_2","first-page":"8","article-title":"Glyphidentification and character recognition for sindhi ocr","volume":"36","author":"Nisar\u00a0Ahmed Memon","year":"2017","unstructured":"Nisar\u00a0Ahmed Memon, Fatima Abbasi and Shehnila Zardari, Glyphidentification and character recognition for sindhi ocr, MehranUniversity Research Journal of Engineering and Technology 36(4) (2017), 8.","journal-title":"MehranUniversity Research Journal of Engineering and Technology"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(03)00431-4"},{"key":"e_1_3_1_26_2","first-page":"112","article-title":"Performancecomon of svm and k-nn for oriya character recognition","volume":"20","author":"Sanghamitra Mohanty","year":"2011","unstructured":"Sanghamitra Mohanty and Himadri Nandini\u00a0Das Bebartta, Performancecomon of svm and k-nn for oriya character recognition, International Journal of Advanced Computer Science and Applications,Special Issue on Image Processing and Analysis 20 (2011), 112\u2013116.","journal-title":"International Journal of Advanced Computer Science and Applications,Special Issue on Image Processing and Analysis"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jesit.2017.02.001"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Yadav Vikash Ahmad Hifzan Sah Dinesh Kumar Barna\u00a0CornelNinawe\u00a0Aniket and Mallick Ajay\u00a0Kumar Cathedral and indian mughal monument recognition using tensorflow In Soft Computing Applications pages 186\u2013196. Springer International Publishing 2021.","DOI":"10.1007\/978-3-030-51992-6_16"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJCSYSE.2020.111208"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJAIP.2017.081179"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.11.016"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.05.033"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJAIP.2020.107017"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJAIP.2020.109523"},{"key":"e_1_3_1_35_2","unstructured":"Andrey Rosenberg and Nachum Dershowitz Using SIFT Descriptors for OCR of Printed Arabic Citeseer 2012."},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Anwar\u00a0Ali Sanjrani Junaid Baber Maheen Bakhtyar Waheed Noor and Muhammad Khalid Handwritten optical character recognition system for sindhi numerals In Computing Electronic and Electrical Engineering (ICE Cube) 2016 International Conference on pages 262\u2013267 2016.","DOI":"10.1109\/ICECUBE.2016.7495235"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102773"},{"key":"e_1_3_1_38_2","unstructured":"Mohamed Sirajudeen and R\u00a0Anitha Forgery document detection in information management system using cognitive techniques Journal of Intelligent & Fuzzy Systems pages 1\u201312 2020."},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Yasir\u00a0Ali Solangi Zulfiqar\u00a0Ali Solangi Ali Raza Noor\u00a0AhmedShaikh Ghulam\u00a0Ali Mallah and Asadullah Shah Offline-printed sindhi optical text recognition: Survey In 2018 IEEE 5th International Conference on Engineering Technologies and Applied Sciences (ICETAS) pages 1\u20135. IEEE 2018.","DOI":"10.1109\/ICETAS.2018.8629110"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.04.007"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.05.012"},{"key":"e_1_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Myung-Chul Sung Bongjin Jun Hojin Cho and Daijin Kim Scene text detection with robust character candidate extraction method In 2015 13th International conference on document analysis and recognition (ICDAR) pages 426\u2013430. IEEE 2015.","DOI":"10.1109\/ICDAR.2015.7333797"},{"issue":"7","key":"e_1_3_1_43_2","first-page":"1480","article-title":"Text detection and recognition in imagery: A survey","volume":"37","author":"Qixiang Ye","year":"2014","unstructured":"Qixiang Ye and David Doermann, Text detection and recognition in imagery: A survey, IEEE Transactions on Pattern Analysis and Machine Intelligence 37(7) (2014), 1480\u20131500.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219304","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-219304","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:46:06Z","timestamp":1777455966000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-219304"}},"subtitle":[],"editor":[{"given":"Valentina Emilia","family":"Balas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,3,11]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6,9]]}},"alternative-id":["10.3233\/JIFS-219304"],"URL":"https:\/\/doi.org\/10.3233\/jifs-219304","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,11]]}}}