Structural Feature Based Classification of Printed Gujarati Characters

Goswami, Mukesh M.; Mitra, Suman K.

doi:10.1007/978-3-642-45062-4_10

Cited by 9 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These feature vectors were used with the general regression neural network (GRNN) classifier and obtained 96% accuracy [24]. The structural feature extraction approach was introduced to classify printed Gujarati characters by Goswami and Mitra [25]. They evaluated their approach on 4000 different printed Gujarati characters and showed 92.7% accuracy.…”

Section: A Traditional Machine Learning Approachesmentioning

confidence: 99%

Handwritten Gujarati Numerals Classification Based on Deep Convolution Neural Networks Using Transfer Learning Scenarios

Goel

Ganatra

2023

IEEE Access

View full text Add to dashboard Cite

In recent years, handwritten numeral classification has achieved remarkable attention in the field of computer vision. Handwritten numbers are difficult to recognize due to the different writing styles of individuals. In a multilingual country like India, negligible research attempts have been carried out for handwritten Gujarati numerals recognition using deep learning techniques compared to the other regional scripts. The Gujarati digit dataset is not available publicly and deep learning requires a large amount of labeled data for the training of the models. If the number of annotated data is not sufficient enough to train Convolutional Neural Networks (CNN) from the scratch, transfer learning can be applied. However, the issue arises by using transfer learning is that how deep to fine-tune the pre-trained convolutional neural network while training the target model. In this paper, we addressed these problems using three deep transfer learning scenarios to classify handwritten Gujarati numerals from the images of zero to nine. We presented transfer learning scenarios using ten pre-trained CNN architectures including LeNet, VGG16, InceptionV3, ResNet50, Xception, ResNet101, MobileNet, MobileNetV2, DenseNet169 and EfficientNetV2S to find the best performing model by freezing and fine-tuning the weight parameters. We implemented the pretrained models using a self-created handwritten Gujarati digit dataset with 8000 images of zero to nine digits with data augmentation. Exhaustive experiments are performed using various performance evaluation matrices. EfficientNetV2S model showed promising results among all the models including three transfer learning scenarios and achieved 98.39% training accuracy, 97.92% testing accuracy, 97.69% f1-score, and 97.15% AUC. Our handwritten Gujarati digit dataset is available on https://github.com/Parth-Goel/gujaratihandwritten-digit-dataset/.

show abstract

Section: A Traditional Machine Learning Approachesmentioning

confidence: 99%

Handwritten Gujarati Numerals Classification Based on Deep Convolution Neural Networks Using Transfer Learning Scenarios

Goel

Ganatra

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The density of each zone [43] geometric features (connected and disconnected components, endpoint, closed loop) [44], and other geometric features (endpoint, joints, lines, left curves, right curves, circles) [45] as feature extraction methods were applied to extract the features of Gujarati characters, achieving accuracies of 86.66%, 88.78%, and 95%, respectively, showing that geometric features were the best feature extraction method to achieve a high recognition rate.…”

Section: Literature Reviewmentioning

confidence: 99%

Brahmi Word Recognition by Supervised Techniques

Gautam¹,

Chai²,

Afrin³

et al. 2020

Preprint

View full text Add to dashboard Cite

Significant progress has made in pattern recognition technology. However, one obstacle that has not yet overcome is the recognition of words in the Brahmi script, specifically the recognition of characters, compound characters, and word because of complex structure. For this kind of complex pattern recognition problem, it is always difficult to decide which feature extraction and classifier would be the best choice. Moreover, it is also true that different feature extraction and classifiers offer complementary information about the patterns to be classified. Therefore, combining feature extraction and classifiers, in an intelligent way, can be beneficial compared to using any single feature extraction. This study proposed the combination of HOG +zonal density with SVM to recognize the Brahmi words. Keeping these facts in mind, in this paper, information provided by structural and statistical based features are combined using SVM classifier for script recognition (word-level) purpose from the Brahmi words images. Brahmi word dataset contains 6,475 and 536 images of Brahmi words of 170 classes for the training and testing, respectively, and the database is made freely available. The word samples from the mentioned database are classified based on the confidence scores provided by support vector machine (SVM) classifier while HOG and zonal density use to extract the features of Brahmi words. Maximum accuracy suggested by system is 95.17% which is better than previously suggested studies.

show abstract

“…Resizing is performed by using bicubic image resize algorithm, to convert the signatures to size 500X1000. [9]. However, the features are general and can also be used with other applications.…”

Section: ) Image Resizingmentioning

confidence: 99%

“…This research attempts to use LLS features for offline signature verification. Low Level Strokes [9] represent basic elements of any geometry, namely end points, lines, curves and junction points (as shown in Fig.4). Total number of 8 different low level stroke feature were captured using template matching approach.…”

Section: ) Image Resizingmentioning

confidence: 99%

Offline handwritten Signature Verification using low level stroke features

Joshi

Goswami

Adesara

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

Signatures are most widely used biometric identity for verification of a person or an individual. Signature is legally accepted as a mark of identification and authorization in almost all commercial, social, jurisdictional documents since a long time. Signature verification is a process of automatic recognition of human handwritten signature and differentiating between original and forge signature. In this research, we have used low level stroke feature, which were originally proposed for recognition of printed Gujarati text, for offline handwritten signature verification. Experiment was performed on the ICDAR 2009 Signature Verification Competition dataset which contains both genuine and forge signature. Recognition is performed using Support Vector Machine (SVM) classifier with 3-fold cross validation. Equal Error Rate (EER) achieved is 15.59, which is comparable with the ICDAR 2009 Signature Verification Competition Result.

show abstract

Structural Feature Based Classification of Printed Gujarati Characters

Cited by 9 publications

References 10 publications

Handwritten Gujarati Numerals Classification Based on Deep Convolution Neural Networks Using Transfer Learning Scenarios

Handwritten Gujarati Numerals Classification Based on Deep Convolution Neural Networks Using Transfer Learning Scenarios

Brahmi Word Recognition by Supervised Techniques

Offline handwritten Signature Verification using low level stroke features

Contact Info

Product

Resources

About