Numerous works, tricks, approaches, techniques, and systems can also be found on this subject. For instance: The use of Self organizing maps [17], Shape matching [18], [19] A method involving the division of the image into grids and computing the Hu moments as features was proposed. Artificial neural network was then implemented as classifier. The method yielded good processing times and accuracy. Methods such as Restricted Boltzmann Machines (RBMs) [28], SVM with inverse fringe feature [29], Echo state networks [30], Discrete Cosine S-Transform (DCST) features with Artificial Neural Networks classifier [31], Neural Dynamics Classification algorithm [32], Bat Algorithm-Optimized SVM [33] have been applied. Similarly, promising results from numerous algorithms have prompted the extension to numerous languages and characters. Indian numerals were treated in [23], Persian digits in [24], Bangla Digits [25], Hindu and Arabic digits in [26], Sindhi Numerals [27].
Most recently, due to the advent of powerful computational systems such as GPUs and TPUs, more solutions have been proposed, especially, with Deep learning. In [21] for instance, the authors made a case for Online digit recognition using deep learning. They developed a software application to record a dataset which included user information such as age, sex, nationality, and handedness. Thereafter they presented a 1D and 2D ConvNet model which obtained results of 95.86% (using distance and angle), and 98.50% respectively.
Unfortunately, as deep learning methods have yielded exceptional results, they have also empowered Adversarial systems. It was shown by [22] that the changing of 1 pixel can lead to significant misclassification rates. The authors showed that 70.97% of the natural images can be perturbed to at least one target class simply by modifying a single pixel with 97.47% confidence on average. Further information can be found from academic resources.
To conclude this section of the survey, it is important to highlight from [20]:
Previous work on handwriting recognition has mainly focused on processing images of pen-on-paper writing, i.e. offline character recognition. Notably, the MNIST dataset was created using images of handwritten US census returns []. Excellent recognition accuracy (99.2%) was demonstrated on the MNIST dataset using a convolutional neural network (ConvNet) [LeCun et al., 1998]. In contrast, online character recognition systems take input in the form of the continuously sensed position of the pen, finger, or thumb. Online systems have the advantage of recording temporal information as well as spatial information. To date, most work on online character recognition has focused on pen based systems [Guyon et al., 1991, Bengio et al., 1995, Verma et al., 2004, Bahlmann, 2006].