Handwritten Bangla character recognition in machine-printed forms using gradient information and Haar wavelet

Mandal, Sekhar; Sur, Sanjib; Dan, Avishek; Bhowmick, Partha

doi:10.1109/iciip.2011.6108911

Cited by 16 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Presence of long edges (vertical or horizontal) [30]; Image histogram Image Processing based Bag-of-feature [39]; Haar wavelet [8]; Discrete-continuous ADM [25]; Compressive sensing [50] Deep Learning based Convolution kernels from last conv layer (before fully connected layers) of LeNet Global descriptor (GIST-based) [32]; Local descriptor (SIFT-based) [48]; Bag-ofvisual-words; Histogram of Oriented Gradient (HOG)-based: HoGgles [44] Deep Learning based Convolution kernels from last conv layer (before fully connected layers) of (Ima-geNet) pre-trained AlexNet…”

Section: Typementioning

confidence: 99%

“…Labeling Functions used Heuristic Presence of long edges (vertical or horizontal) [30]; Image histogram Image Processing based Bag-of-feature [39]; Haar wavelet [8]; Discrete-continuous ADM [25]; Compressive sensing [50] Deep Learning based Convolution kernels from last conv layer (before fully connected layers) of LeNet Table 1: Labeling functions used for MNIST and SVHN datasets, both of which represent the digit recognition task…”

Section: Typementioning

confidence: 99%

See 1 more Smart Citation

Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data

Pal

Balasubramanian

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant supervision signals in the form of labeling functions can be used to obtain labels for given data in near-constant time. In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label has given a set of weak labeling functions. We validated our method on the MNIST, Fashion MNIST, CIFAR 10 and SVHN datasets, and it outperformed many state-of-the-art models. We conducted extensive experiments to study its usefulness, as well as showed how the proposed ADP framework can be used for transfer learning as well as multi-task learning, where data from two domains are generated simultaneously using the framework along with the label information. Our future work will involve understanding the theoretical implications of this new framework from a game-theoretic perspective, as well as explore the performance of the method on more complex datasets.

show abstract

Section: Typementioning

confidence: 99%

Section: Typementioning

confidence: 99%

Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data

Pal

Balasubramanian

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…A two-stage framework that combines modified quadratic discriminant function (MQDF) [21] and MLPs was used for the recognition of Bangla characters [6]. Other databases of the Bangla characters (50 classes), Mandal et al use features based on the combination of gradient features and Haar wavelet coefficients at different scales with a k-nn classifier to reach an accuracy of 88.95% [27].…”

Section: Databasesmentioning

confidence: 99%

Active graph based semi-supervised learning using image matching: Application to handwritten digit recognition

Cecotti

2016

Pattern Recognition Letters

View full text Add to dashboard Cite

With the availability of large amounts of documents and multimedia content to be classified, the creation of new databases with labeled examples is an expensive task. Efficient supervised classifiers often require large training databases that are not always immediately available. Active learning approaches solve this issue by querying an expert to set a label to particular instances. In this paper, we present a novel active learning strategy for the classification of handwritten digits. The proposed method is based on a k-nearest neighbor graph obtained with an image deformation model, which takes into account local deformations. During the active learning procedure, the user is first asked to label the vertices with the highest number of neighbors. Thus, the expert sets the label to the examples that are more likely to propagate their labels to a high number of close neighbors. Then, a label propagation function is performed to automatically label the examples. The procedure is repeated until all the images are labeled. We evaluate the performance of the method on four databases corresponding to different scripts (Latin, Bangla, Devnagari, and Oriya). We show that it is possible to label only 332 images in the MNIST training database to obtain an accuracy of 98.54% on this same database (60000 images). The robustness of the method is highlighted by the performance of handwritten digit recognition in different scripts.

show abstract

“…In [34], they propose a twostage framework that combines modified quadratic discriminant function (MQDF) [35] and MLPs for the recognition of Bangla characters. On other databases of the Bangla characters (50 classes), Mandal et al use features based on the combination of gradient features and Haar wavelet coefficients at different scales with a k-nn classifier to reach an accuracy of 88.95% [36]. In [37], Bhattacharya et al…”

Section: A Indian Handwritten Digitsmentioning

confidence: 99%

Handwritten digit recognition of Indian scripts: A cascade of distances approach

Cecotti

2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The recognition of handwritten digits remains a difficult problem, particularly in some scripts where there exists a large variation of style across writers. This large variability is an interesting challenge for algorithms in image processing and pattern recognition. Thanks to the accelerating progress and availability of low cost computers, high speed networks, and software for high performance distributed computing, it is possible to use computational expensive technique on large databases. In this paper, we propose to investigate the impact on the accuracy of different parameters and preprocessing methods of a distance based on image distortion models. A key challenge is to reduce the processing time of the nearest neighbor classification by considering rejection rules and adaptive distances. We propose to evaluate the performance of single character recognition on three databases of Indian handwritten digits, each database corresponds to a popular Indian script: Bangla, Devnagari, and Oriya. We show that the extraction of features related to four directions allows a significant improvement of the accuracy. The proposed approach takes advantages of GPU and high performance clusters, providing state-of-the-art performances.

show abstract

Handwritten Bangla character recognition in machine-printed forms using gradient information and Haar wavelet

Cited by 16 publications

References 10 publications

Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data

Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data

Active graph based semi-supervised learning using image matching: Application to handwritten digit recognition

Handwritten digit recognition of Indian scripts: A cascade of distances approach

Contact Info

Product

Resources

About